Compare commits
472 Commits
2015.01.02
...
2015.02.02
Author | SHA1 | Date | |
---|---|---|---|
869b4aeff4 | |||
cc9ca3ba6e | |||
ea71034bd3 | |||
9fffd0469f | |||
ae7773942e | |||
469a64cebf | |||
aae3fdcfae | |||
6a66904f8e | |||
78271e3319 | |||
92bf0bcdf8 | |||
1283204917 | |||
6789defea9 | |||
acf2a6e97b | |||
8cfb6efe6f | |||
04edb9caf5 | |||
044131ba21 | |||
0a7055c90d | |||
9e3f19919a | |||
4a3da4ebdb | |||
027008b14e | |||
c6df692466 | |||
acf757f42e | |||
dd8982f19c | |||
654bd52f58 | |||
a9551e9020 | |||
4e980275b5 | |||
c172440ac5 | |||
e332772531 | |||
437cac8cc1 | |||
9f281cacd2 | |||
748a0fab8a | |||
c1f06d6307 | |||
c4e817ce4a | |||
9a3e5e6955 | |||
228d30ed06 | |||
057c0609fc | |||
17d2712d9c | |||
fc09240e24 | |||
146303136f | |||
96aded8d3d | |||
2886be15aa | |||
ca0f500ecf | |||
29aef5a33c | |||
9158b2b301 | |||
0196149c5b | |||
8f9312c387 | |||
439b9a9e9b | |||
8c72beb25e | |||
1ee94db2d0 | |||
e77d2975af | |||
e41b1f7385 | |||
cd596028d6 | |||
cc57bd33a8 | |||
6d593c3276 | |||
91755ee384 | |||
0692ef86ef | |||
439d9be27d | |||
b80505a409 | |||
e4c17d7274 | |||
2c58674e0e | |||
ef1269fb07 | |||
e525d9a3df | |||
20b4492c71 | |||
dee3f73787 | |||
d543bdc351 | |||
c7ff0c6422 | |||
01c46659c4 | |||
b04b885271 | |||
dc35bfd2d5 | |||
70fca8d694 | |||
a52c633536 | |||
7b6c60393e | |||
83e7a314b4 | |||
749f2ca044 | |||
5468ff4d91 | |||
1d2daaea63 | |||
52585fd6dc | |||
c03844a4ec | |||
6449cd807e | |||
e2a08185c6 | |||
5d6677ca28 | |||
5a8a29cfea | |||
c1708b89c0 | |||
83fddfd493 | |||
1798791df1 | |||
6ebb0dca9f | |||
cf8d6ec865 | |||
f452f72c6b | |||
3198291f26 | |||
02c1d5e285 | |||
ec4161a57d | |||
03d8d4df38 | |||
03d2d6d51b | |||
83fda3c000 | |||
4fe8495a23 | |||
a16f6643f0 | |||
adc0ae3ceb | |||
7bb3ceb4c7 | |||
75a4fc5b72 | |||
87673cd438 | |||
f345fe9db7 | |||
e683a48d0e | |||
a7a14d9586 | |||
219337990b | |||
376a770cc4 | |||
7e500dbd93 | |||
affd04a45d | |||
c84130e865 | |||
4f264c02c7 | |||
d205476103 | |||
367cc95aa7 | |||
206dba27a4 | |||
dcf53d4408 | |||
63be3b8989 | |||
18b4e9e79d | |||
cb454b333d | |||
e0d9f85aee | |||
b04fbd789c | |||
aad9556414 | |||
48a1e5141a | |||
0865f397ae | |||
796df3c631 | |||
a28383834b | |||
3a0d2f520a | |||
6348ad12a0 | |||
fe7710cbcc | |||
2103d038b3 | |||
6ca85be6f8 | |||
9f0df77ab1 | |||
e72c7e4123 | |||
2b1bd292ae | |||
71e7da6533 | |||
80a49d3d7b | |||
d862a4f94f | |||
a57e8ce658 | |||
96a53167fa | |||
6d2749aac4 | |||
b1b0b1ca30 | |||
3dee7826e7 | |||
c9326b38b8 | |||
d4f64cabf4 | |||
fe41ddbb28 | |||
ee69b99af6 | |||
767ff0a2d1 | |||
8604e882a8 | |||
cc1237f484 | |||
37f4ce538a | |||
7d346331b5 | |||
e1ccc04e9f | |||
881e6a1f5c | |||
baeaeffce5 | |||
c14e88f0f5 | |||
8940b8608e | |||
ec82d85acd | |||
cfb56d1af3 | |||
1e10802990 | |||
6695916045 | |||
7906d199a1 | |||
1070711d60 | |||
4b405cfc6e | |||
e5660ee6ae | |||
8011fba3ae | |||
587a9c2749 | |||
e1554a407d | |||
3fcfb8e9fa | |||
384b62028a | |||
b95aab8482 | |||
fc2d6abfe7 | |||
27de5625d4 | |||
6aa4f54d66 | |||
222516d97d | |||
a055469faf | |||
fdaaaaa878 | |||
12d1fb5aa9 | |||
48f00d15b1 | |||
3e055aa5c3 | |||
6896a52721 | |||
5779b3e1fe | |||
62cd676c74 | |||
0c17278843 | |||
d229ee70da | |||
26e274666d | |||
ebd46aed51 | |||
e793f7671c | |||
c2e64f71d0 | |||
0920e5830f | |||
bf7fa94ec7 | |||
6f58db8982 | |||
aa42e87340 | |||
649f7966f7 | |||
5f0d813d93 | |||
501f13fbf3 | |||
ba55168157 | |||
d79323136f | |||
08ff6ab07e | |||
ba655a0e4c | |||
b59c17e543 | |||
61ca9a80b3 | |||
317239b097 | |||
c2a30b250c | |||
c994e6bd63 | |||
3ee2aa7a16 | |||
083c9df93b | |||
50789175ed | |||
dc1b027cd4 | |||
f353cbdb2f | |||
73e449b226 | |||
b4a64c592b | |||
78111136db | |||
650ab5beeb | |||
7932de6352 | |||
240b9b7a5c | |||
bb6e38787d | |||
898c23c03f | |||
b55ee18ff3 | |||
e5763a7a7e | |||
8bb1bdfae9 | |||
c62b449765 | |||
bb0aa4cb3c | |||
d63528c8c7 | |||
c5db6bb32b | |||
c8dc41a6e7 | |||
47e0e1e0e2 | |||
efcddaebe9 | |||
5fe5112589 | |||
564bb5e964 | |||
2df54b4ba8 | |||
030aa5d9e7 | |||
c511f13f22 | |||
bd3cbe0716 | |||
fdb2ed7455 | |||
ba319696a9 | |||
910c552052 | |||
cce81f192c | |||
9d22a7dfb0 | |||
4f4f642822 | |||
2875cf01bb | |||
e205db3bcd | |||
31d4a6e212 | |||
aaeb86f682 | |||
9fa6ea2680 | |||
a9b6b5cd15 | |||
a45c0a5d67 | |||
c8dfe360eb | |||
4cfaf85c65 | |||
be5f2c192c | |||
c9ef44ce29 | |||
e92d4a11f5 | |||
f2cbc96c3e | |||
a69801e2c6 | |||
034206cec1 | |||
04e0bac233 | |||
fbef83f399 | |||
3d5f7a3947 | |||
a5fb718c50 | |||
227d4822ff | |||
5c4a81d934 | |||
263255eb8d | |||
8e2ec95575 | |||
8e7a9016d5 | |||
c85f368370 | |||
a0977064ce | |||
15aecd8711 | |||
20dd0b2d20 | |||
f934860a07 | |||
2aeb06d6dc | |||
6ccbb335d2 | |||
4340decad2 | |||
f3ff1a3696 | |||
aa24de39aa | |||
a798e64c15 | |||
6a5fa75490 | |||
8ad6b5ed9f | |||
d5bb814d34 | |||
d156a1d981 | |||
987493aef3 | |||
8bfa75451b | |||
c071733fd4 | |||
cd3063f3fa | |||
58b1f00d19 | |||
149f05c7b6 | |||
8a1b9b068e | |||
c5a59d9391 | |||
500b8b41c1 | |||
be4a824d74 | |||
ed3958d714 | |||
6ce08764a1 | |||
c80ede5f13 | |||
bc694039e4 | |||
3462af03e6 | |||
ea1d5bdcdd | |||
121c09c7be | |||
76bfaf6daf | |||
d89c6e336a | |||
776dc3992a | |||
27ca82ebc6 | |||
385f8ae468 | |||
b9f030cc26 | |||
52afb2ac1b | |||
43bc88903d | |||
6ef9f88299 | |||
f71fdb0acc | |||
c24dfef63c | |||
6271f1cad9 | |||
fb4b030aaf | |||
ff21a8e0ee | |||
904fffffeb | |||
51897bb77c | |||
bd1a281ede | |||
45598f1578 | |||
d02115f837 | |||
34c781a24d | |||
1302394603 | |||
dd622d7c4e | |||
d120e9013f | |||
b8da6b9fc6 | |||
4baea47c42 | |||
176cf9e0c3 | |||
7b6faddfc8 | |||
f90ad27375 | |||
230b2287dd | |||
754c838903 | |||
aa2fd59857 | |||
9932a65370 | |||
5e4166478d | |||
b0e87c3110 | |||
ff0813313a | |||
c0bdf32a3c | |||
92b065dc53 | |||
9298d4e3df | |||
740a7fcbc8 | |||
5fbf25a681 | |||
db6e625005 | |||
811cacdc2c | |||
ce08a86462 | |||
11497d5bba | |||
0217c78377 | |||
bd6b25ce0e | |||
d51a853d5c | |||
9ed99402f5 | |||
ec3a6a3137 | |||
796858a53f | |||
5b78caca94 | |||
bec2248141 | |||
211503c39f | |||
adb1307b9a | |||
99673f04bc | |||
e9a537774d | |||
367f539769 | |||
398133cf55 | |||
52fc3ba405 | |||
fdd6e18b75 | |||
58a84b8cb6 | |||
c5d666d374 | |||
5d8993b06a | |||
c758bf9fd7 | |||
900813a328 | |||
2bad0e5d20 | |||
ccc5842bc9 | |||
fd86c2026d | |||
e4a8eae701 | |||
75e51819d0 | |||
8ee341500d | |||
0590062925 | |||
799d88d3d8 | |||
760aea9a96 | |||
d6a31b1766 | |||
0b54a5b10a | |||
6309cb9b41 | |||
27a82a1b93 | |||
ecd1936695 | |||
76b3c61012 | |||
0df2dea73b | |||
f8bb576c4f | |||
ee61f6f3e2 | |||
f14f2a6d79 | |||
2c322cc5d6 | |||
3b8f3a1504 | |||
8f9529cd05 | |||
f4bca0b348 | |||
6291438073 | |||
18c3c15391 | |||
dda620e88c | |||
d7cc31b63e | |||
5e3e1c82d8 | |||
aa80652f47 | |||
9d247bbd2d | |||
93e40a7b2f | |||
03ff2cc1c4 | |||
a285b6377b | |||
cd791a5ea0 | |||
87830900a9 | |||
dfc9d9f50a | |||
75311a7e16 | |||
628bc4d1e7 | |||
a4c3f48639 | |||
bdf80aa542 | |||
adf3c58ad3 | |||
caf90bfaa5 | |||
2f985f4bb4 | |||
67c2bcdf4c | |||
1d2d0e3ff2 | |||
9fda6ee39f | |||
bc3e582fe4 | |||
bc1fc5ddbc | |||
63948fc62c | |||
f4858a7103 | |||
26886e6140 | |||
7a1818c99b | |||
2ccd1b10e5 | |||
788fa208c8 | |||
8848314c08 | |||
c11125f9ed | |||
95ceeec722 | |||
b68ff25917 | |||
3e3327ea17 | |||
b158bb8693 | |||
2bf098eda4 | |||
382e05fa56 | |||
19b05d886e | |||
e65566a9cc | |||
baa3c3f0f6 | |||
f4f339529c | |||
7d02fae85b | |||
6e46c3f1fd | |||
c7e675940c | |||
d26b1317ed | |||
a221f22969 | |||
817f786fbb | |||
62420c73cb | |||
2522a0b7da | |||
46d32a12c9 | |||
c491418526 | |||
c067545c17 | |||
823a155293 | |||
324b2c78fa | |||
d34f98289b | |||
644096b15c | |||
15cebcc363 | |||
faa4ea68c0 | |||
476eae0c2a | |||
8399267671 | |||
5b9aefef77 | |||
defaf19f5d | |||
754f0008ec | |||
2415951ead | |||
995ad69c54 | |||
225e4b9633 | |||
6ce2c6783b | |||
29f400b97d | |||
0cd64bd077 | |||
0551a02b82 | |||
25fadd06d0 | |||
7a47d07c6d | |||
34e48bed3b | |||
5a000b45b3 | |||
40b1cbafac | |||
4231235cda | |||
7b61ac3ddf | |||
c816336cbd | |||
ca7a9c1bf7 | |||
247a5da704 | |||
d1b4617e1d | |||
74dcf42a85 | |||
a42c921598 | |||
f96252b913 | |||
04b89c9026 | |||
0c72eb9060 | |||
f9f86b0c64 | |||
0aed8df2bf | |||
2f61fe4ccc | |||
03359e9864 |
2
.gitignore
vendored
2
.gitignore
vendored
@ -31,3 +31,5 @@ updates_key.pem
|
||||
test/testdata
|
||||
.tox
|
||||
youtube-dl.zsh
|
||||
.idea
|
||||
.idea/*
|
@ -4,12 +4,14 @@ python:
|
||||
- "2.7"
|
||||
- "3.3"
|
||||
- "3.4"
|
||||
before_install:
|
||||
- sudo apt-get update -qq
|
||||
- sudo apt-get install -yqq rtmpdump
|
||||
script: nosetests test --verbose
|
||||
notifications:
|
||||
email:
|
||||
- filippo.valsorda@gmail.com
|
||||
- phihag@phihag.de
|
||||
- jaime.marquinez.ferrandiz+travis@gmail.com
|
||||
- yasoob.khld@gmail.com
|
||||
# irc:
|
||||
# channels:
|
||||
|
10
AUTHORS
10
AUTHORS
@ -98,3 +98,13 @@ Will Glynn
|
||||
Max Reimann
|
||||
Cédric Luthi
|
||||
Thijs Vermeir
|
||||
Joel Leclerc
|
||||
Christopher Krooss
|
||||
Ondřej Caletka
|
||||
Dinesh S
|
||||
Johan K. Jensen
|
||||
Yen Chi Hsuan
|
||||
Enam Mijbah Noor
|
||||
David Luhmer
|
||||
Shaya Goldberg
|
||||
Paul Hartmann
|
||||
|
@ -44,7 +44,7 @@ In particular, every site support request issue should only pertain to services
|
||||
|
||||
### Is anyone going to need the feature?
|
||||
|
||||
Only post features that you (or an incapicated friend you can personally talk to) require. Do not post features because they seem like a good idea. If they are really useful, they will be requested by someone who requires them.
|
||||
Only post features that you (or an incapacitated friend you can personally talk to) require. Do not post features because they seem like a good idea. If they are really useful, they will be requested by someone who requires them.
|
||||
|
||||
### Is your question about youtube-dl?
|
||||
|
||||
|
4
Makefile
4
Makefile
@ -46,7 +46,7 @@ test:
|
||||
ot: offlinetest
|
||||
|
||||
offlinetest: codetest
|
||||
nosetests --verbose test --exclude test_download --exclude test_age_restriction --exclude test_subtitles --exclude test_write_annotations
|
||||
nosetests --verbose test --exclude test_download --exclude test_age_restriction --exclude test_subtitles --exclude test_write_annotations --exclude test_youtube_lists
|
||||
|
||||
tar: youtube-dl.tar.gz
|
||||
|
||||
@ -63,7 +63,7 @@ youtube-dl: youtube_dl/*.py youtube_dl/*/*.py
|
||||
chmod a+x youtube-dl
|
||||
|
||||
README.md: youtube_dl/*.py youtube_dl/*/*.py
|
||||
COLUMNS=80 python -m youtube_dl --help | python devscripts/make_readme.py
|
||||
COLUMNS=80 python youtube_dl/__main__.py --help | python devscripts/make_readme.py
|
||||
|
||||
CONTRIBUTING.md: README.md
|
||||
python devscripts/make_contributing.py README.md CONTRIBUTING.md
|
||||
|
121
README.md
121
README.md
@ -60,10 +60,6 @@ which means you can modify it, redistribute it or use it however you like.
|
||||
they would handle
|
||||
--extractor-descriptions Output descriptions of all supported
|
||||
extractors
|
||||
--proxy URL Use the specified HTTP/HTTPS proxy. Pass in
|
||||
an empty string (--proxy "") for direct
|
||||
connection
|
||||
--socket-timeout None Time to wait before giving up, in seconds
|
||||
--default-search PREFIX Use this prefix for unqualified URLs. For
|
||||
example "gvsearch2:" downloads two videos
|
||||
from google videos for youtube-dl "large
|
||||
@ -82,9 +78,29 @@ which means you can modify it, redistribute it or use it however you like.
|
||||
--flat-playlist Do not extract the videos of a playlist,
|
||||
only list them.
|
||||
|
||||
## Network Options:
|
||||
--proxy URL Use the specified HTTP/HTTPS proxy. Pass in
|
||||
an empty string (--proxy "") for direct
|
||||
connection
|
||||
--socket-timeout SECONDS Time to wait before giving up, in seconds
|
||||
--source-address IP Client-side IP address to bind to
|
||||
(experimental)
|
||||
-4, --force-ipv4 Make all connections via IPv4
|
||||
(experimental)
|
||||
-6, --force-ipv6 Make all connections via IPv6
|
||||
(experimental)
|
||||
|
||||
## Video Selection:
|
||||
--playlist-start NUMBER playlist video to start at (default is 1)
|
||||
--playlist-end NUMBER playlist video to end at (default is last)
|
||||
--playlist-items ITEM_SPEC playlist video items to download. Specify
|
||||
indices of the videos in the playlist
|
||||
seperated by commas like: "--playlist-items
|
||||
1,2,5,8" if you want to download videos
|
||||
indexed 1, 2, 5, 8 in the playlist. You can
|
||||
specify range: "--playlist-items
|
||||
1-3,7,10-13", it will download the videos
|
||||
at index 1, 2, 3, 7, 10, 11, 12 and 13.
|
||||
--match-title REGEX download only matching titles (regex or
|
||||
caseless sub-string)
|
||||
--reject-title REGEX skip download for matching titles (regex or
|
||||
@ -116,7 +132,8 @@ which means you can modify it, redistribute it or use it however you like.
|
||||
## Download Options:
|
||||
-r, --rate-limit LIMIT maximum download rate in bytes per second
|
||||
(e.g. 50K or 4.2M)
|
||||
-R, --retries RETRIES number of retries (default is 10)
|
||||
-R, --retries RETRIES number of retries (default is 10), or
|
||||
"infinite".
|
||||
--buffer-size SIZE size of download buffer (e.g. 1024 or 16K)
|
||||
(default is 1024)
|
||||
--no-resize-buffer do not automatically adjust the buffer
|
||||
@ -124,6 +141,11 @@ which means you can modify it, redistribute it or use it however you like.
|
||||
automatically resized from an initial value
|
||||
of SIZE.
|
||||
--playlist-reverse Download playlist videos in reverse order
|
||||
--xattr-set-filesize (experimental) set file xattribute
|
||||
ytdl.filesize with expected filesize
|
||||
--external-downloader COMMAND (experimental) Use the specified external
|
||||
downloader. Currently supports
|
||||
aria2c,curl,wget
|
||||
|
||||
## Filesystem Options:
|
||||
-a, --batch-file FILE file containing URLs to download ('-' for
|
||||
@ -183,7 +205,6 @@ which means you can modify it, redistribute it or use it however you like.
|
||||
--write-info-json write video metadata to a .info.json file
|
||||
--write-annotations write video annotations to a .annotation
|
||||
file
|
||||
--write-thumbnail write thumbnail image to disk
|
||||
--load-info FILE json file containing the video information
|
||||
(created with the "--write-json" option)
|
||||
--cookies FILE file to read cookies from and dump cookie
|
||||
@ -198,6 +219,12 @@ which means you can modify it, redistribute it or use it however you like.
|
||||
--no-cache-dir Disable filesystem caching
|
||||
--rm-cache-dir Delete all filesystem cache files
|
||||
|
||||
## Thumbnail images:
|
||||
--write-thumbnail write thumbnail image to disk
|
||||
--write-all-thumbnails write all thumbnail image formats to disk
|
||||
--list-thumbnails Simulate and list all available thumbnail
|
||||
formats
|
||||
|
||||
## Verbosity / Simulation Options:
|
||||
-q, --quiet activates quiet mode
|
||||
--no-warnings Ignore warnings
|
||||
@ -219,6 +246,8 @@ which means you can modify it, redistribute it or use it however you like.
|
||||
for each command-line argument. If the URL
|
||||
refers to a playlist, dump the whole
|
||||
playlist information in a single line.
|
||||
--print-json Be quiet and print the video information as
|
||||
JSON (video is still being downloaded).
|
||||
--newline output progress bar as new lines
|
||||
--no-progress do not print progress bar
|
||||
--console-title display progress in console titlebar
|
||||
@ -229,6 +258,10 @@ which means you can modify it, redistribute it or use it however you like.
|
||||
files in the current directory to debug
|
||||
problems
|
||||
--print-traffic Display sent and read HTTP traffic
|
||||
-C, --call-home Contact the youtube-dl server for
|
||||
debugging.
|
||||
--no-call-home Do NOT contact the youtube-dl server for
|
||||
debugging.
|
||||
|
||||
## Workarounds:
|
||||
--encoding ENCODING Force the specified encoding (experimental)
|
||||
@ -245,14 +278,29 @@ which means you can modify it, redistribute it or use it however you like.
|
||||
--bidi-workaround Work around terminals that lack
|
||||
bidirectional text support. Requires bidiv
|
||||
or fribidi executable in PATH
|
||||
--sleep-interval SECONDS Number of seconds to sleep before each
|
||||
download.
|
||||
|
||||
## Video Format Options:
|
||||
-f, --format FORMAT video format code, specify the order of
|
||||
preference using slashes: -f 22/17/18 . -f
|
||||
mp4 , -f m4a and -f flv are also
|
||||
supported. You can also use the special
|
||||
names "best", "bestvideo", "bestaudio",
|
||||
"worst", "worstvideo" and "worstaudio". By
|
||||
preference using slashes, as in -f 22/17/18
|
||||
. Instead of format codes, you can select
|
||||
by extension for the extensions aac, m4a,
|
||||
mp3, mp4, ogg, wav, webm. You can also use
|
||||
the special names "best", "bestvideo",
|
||||
"bestaudio", "worst". You can filter the
|
||||
video results by putting a condition in
|
||||
brackets, as in -f "best[height=720]" (or
|
||||
-f "[filesize>10M]"). This works for
|
||||
filesize, height, width, tbr, abr, vbr, and
|
||||
fps and the comparisons <, <=, >, >=, =, !=
|
||||
. Formats for which the value is not known
|
||||
are excluded unless you put a question mark
|
||||
(?) after the operator. You can combine
|
||||
format filters, so -f "[height <=?
|
||||
720][tbr>500]" selects up to 720p videos
|
||||
(or videos where the height is not known)
|
||||
with a bitrate of at least 500 KBit/s. By
|
||||
default, youtube-dl will pick the best
|
||||
quality. Use commas to download multiple
|
||||
audio formats, such as -f
|
||||
@ -269,6 +317,10 @@ which means you can modify it, redistribute it or use it however you like.
|
||||
-F, --list-formats list all available formats
|
||||
--youtube-skip-dash-manifest Do not download the DASH manifest on
|
||||
YouTube videos
|
||||
--merge-output-format FORMAT If a merge is required (e.g.
|
||||
bestvideo+bestaudio), output to given
|
||||
container format. One of mkv, mp4, ogg,
|
||||
webm, flv.Ignored if no merge is required
|
||||
|
||||
## Subtitle Options:
|
||||
--write-sub write subtitle file
|
||||
@ -285,7 +337,8 @@ which means you can modify it, redistribute it or use it however you like.
|
||||
|
||||
## Authentication Options:
|
||||
-u, --username USERNAME login with this account ID
|
||||
-p, --password PASSWORD account password
|
||||
-p, --password PASSWORD account password. If this option is left
|
||||
out, youtube-dl will ask interactively.
|
||||
-2, --twofactor TWOFACTOR two-factor auth code
|
||||
-n, --netrc use .netrc authentication data
|
||||
--video-password PASSWORD video password (vimeo, smotri)
|
||||
@ -315,6 +368,11 @@ which means you can modify it, redistribute it or use it however you like.
|
||||
--add-metadata write metadata to the video file
|
||||
--xattrs write metadata to the video file's xattrs
|
||||
(using dublin core and xdg standards)
|
||||
--fixup POLICY Automatically correct known faults of the
|
||||
file. One of never (do nothing), warn (only
|
||||
emit a warning), detect_or_warn(the
|
||||
default; fix file if we can, warn
|
||||
otherwise)
|
||||
--prefer-avconv Prefer avconv over ffmpeg for running the
|
||||
postprocessors (default)
|
||||
--prefer-ffmpeg Prefer ffmpeg over avconv for running the
|
||||
@ -326,7 +384,7 @@ which means you can modify it, redistribute it or use it however you like.
|
||||
|
||||
# CONFIGURATION
|
||||
|
||||
You can configure youtube-dl by placing default arguments (such as `--extract-audio --no-mtime` to always extract the audio and not copy the mtime) into `/etc/youtube-dl.conf` and/or `~/.config/youtube-dl/config`. On Windows, the configuration file locations are `%APPDATA%\youtube-dl\config.txt` and `C:\Users\<Yourname>\youtube-dl.conf`.
|
||||
You can configure youtube-dl by placing default arguments (such as `--extract-audio --no-mtime` to always extract the audio and not copy the mtime) into `/etc/youtube-dl.conf` and/or `~/.config/youtube-dl/config`. On Windows, the configuration file locations are `%APPDATA%\youtube-dl\config.txt` and `C:\Users\<user name>\youtube-dl.conf`.
|
||||
|
||||
# OUTPUT TEMPLATE
|
||||
|
||||
@ -420,9 +478,15 @@ Apparently YouTube requires you to pass a CAPTCHA test if you download too much.
|
||||
|
||||
Once the video is fully downloaded, use any video player, such as [vlc](http://www.videolan.org) or [mplayer](http://www.mplayerhq.hu/).
|
||||
|
||||
### The links provided by youtube-dl -g are not working anymore
|
||||
### I extracted a video URL with -g, but it does not play on another machine / in my webbrowser.
|
||||
|
||||
The URLs youtube-dl outputs require the downloader to have the correct cookies. Use the `--cookies` option to write the required cookies into a file, and advise your downloader to read cookies from that file. Some sites also require a common user agent to be used, use `--dump-user-agent` to see the one in use by youtube-dl.
|
||||
It depends a lot on the service. In many cases, requests for the video (to download/play it) must come from the same IP address and with the same cookies. Use the `--cookies` option to write the required cookies into a file, and advise your downloader to read cookies from that file. Some sites also require a common user agent to be used, use `--dump-user-agent` to see the one in use by youtube-dl.
|
||||
|
||||
It may be beneficial to use IPv6; in some cases, the restrictions are only applied to IPv4. Some services (sometimes only for a subset of videos) do not restrict the video URL by IP address, cookie, or user-agent, but these are the exception rather than the rule.
|
||||
|
||||
Please bear in mind that some URL protocols are **not** supported by browsers out of the box, including RTMP. If you are using -g, your own downloader must support these as well.
|
||||
|
||||
If you want to play the video on a machine that is not running youtube-dl, you can relay the video content from the machine that runs youtube-dl. You can use `-o -` to let youtube-dl stream a video to stdout, or simply allow the player to download the files written by youtube-dl in turn.
|
||||
|
||||
### ERROR: no fmt_url_map or conn information found in video info
|
||||
|
||||
@ -449,9 +513,28 @@ Since June 2012 (#342) youtube-dl is packed as an executable zipfile, simply unz
|
||||
|
||||
To run the exe you need to install first the [Microsoft Visual C++ 2008 Redistributable Package](http://www.microsoft.com/en-us/download/details.aspx?id=29).
|
||||
|
||||
### On Windows, how should I set up ffmpeg and youtube-dl? Where should I put the exe files?
|
||||
|
||||
If you put youtube-dl and ffmpeg in the same directory that you're running the command from, it will work, but that's rather cumbersome.
|
||||
|
||||
To make a different directory work - either for ffmpeg, or for youtube-dl, or for both - simply create the directory (say, `C:\bin`, or `C:\Users\<User name>\bin`), put all the executables directly in there, and then [set your PATH environment variable](https://www.java.com/en/download/help/path.xml) to include that directory.
|
||||
|
||||
From then on, after restarting your shell, you will be able to access both youtube-dl and ffmpeg (and youtube-dl will be able to find ffmpeg) by simply typing `youtube-dl` or `ffmpeg`, no matter what directory you're in.
|
||||
|
||||
### How do I put downloads into a specific folder?
|
||||
|
||||
Use the `-o` to specify an [output template](#output-template), for example `-o "/home/user/videos/%(title)s-%(id)s.%(ext)s"`. If you want this for all of your downloads, put the option into your [configuration file](#configuration).
|
||||
|
||||
### How do I download a video starting with a `-` ?
|
||||
|
||||
Either prepend `http://www.youtube.com/watch?v=` or separate the ID from the options with `--`:
|
||||
|
||||
youtube-dl -- -wNyEUrxzFU
|
||||
youtube-dl "http://www.youtube.com/watch?v=-wNyEUrxzFU"
|
||||
|
||||
### How can I detect whether a given URL is supported by youtube-dl?
|
||||
|
||||
For one, have a look at the [list of supported sites](docs/supportedsites). Note that it can sometimes happen that the site changes its URL scheme (say, from http://example.com/v/1234567 to http://example.com/v/1234567 ) and youtube-dl reports an URL of a service in that list as unsupported. In that case, simply report a bug.
|
||||
For one, have a look at the [list of supported sites](docs/supportedsites.md). Note that it can sometimes happen that the site changes its URL scheme (say, from http://example.com/v/1234567 to http://example.com/v/1234567 ) and youtube-dl reports an URL of a service in that list as unsupported. In that case, simply report a bug.
|
||||
|
||||
It is *not* possible to detect whether a URL is supported or not. That's because youtube-dl contains a generic extractor which matches **all** URLs. You may be tempted to disable, exclude, or remove the generic extractor, but the generic extractor not only allows users to extract videos from lots of websites that embed a video from another service, but may also be used to extract video from a service that it's hosting itself. Therefore, we neither recommend nor support disabling, excluding, or removing the generic extractor.
|
||||
|
||||
@ -529,7 +612,7 @@ If you want to add support for a new site, you can follow this quick list (assum
|
||||
5. Add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.py).
|
||||
6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will be then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc.
|
||||
7. Have a look at [`youtube_dl/common/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L38). Add tests and code for as many as you want.
|
||||
8. If you can, check the code with [pyflakes](https://pypi.python.org/pypi/pyflakes) (a good idea) and [pep8](https://pypi.python.org/pypi/pep8) (optional, ignore E501).
|
||||
8. If you can, check the code with [flake8](https://pypi.python.org/pypi/flake8).
|
||||
9. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this:
|
||||
|
||||
$ git add youtube_dl/extractor/__init__.py
|
||||
@ -597,7 +680,9 @@ with youtube_dl.YoutubeDL(ydl_opts) as ydl:
|
||||
|
||||
Bugs and suggestions should be reported at: <https://github.com/rg3/youtube-dl/issues> . Unless you were prompted so or there is another pertinent reason (e.g. GitHub fails to accept the bug report), please do not send bug reports via personal email. For discussions, join us in the irc channel #youtube-dl on freenode.
|
||||
|
||||
Please include the full output of the command when run with `--verbose`. The output (including the first lines) contain important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever.
|
||||
**Please include the full output of youtube-dl when run with `-v`**.
|
||||
|
||||
The output (including the first lines) contain important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever.
|
||||
|
||||
Please re-read your issue once again to avoid a couple of common mistakes (you can and should use this as a checklist):
|
||||
|
||||
|
@ -16,7 +16,7 @@ def main():
|
||||
template = tmplf.read()
|
||||
|
||||
ie_htmls = []
|
||||
for ie in sorted(youtube_dl.gen_extractors(), key=lambda i: i.IE_NAME.lower()):
|
||||
for ie in youtube_dl.list_extractors(age_limit=None):
|
||||
ie_html = '<b>{}</b>'.format(ie.IE_NAME)
|
||||
ie_desc = getattr(ie, 'IE_DESC', None)
|
||||
if ie_desc is False:
|
||||
|
@ -23,12 +23,12 @@ def main():
|
||||
|
||||
def gen_ies_md(ies):
|
||||
for ie in ies:
|
||||
ie_md = '**{}**'.format(ie.IE_NAME)
|
||||
ie_md = '**{0}**'.format(ie.IE_NAME)
|
||||
ie_desc = getattr(ie, 'IE_DESC', None)
|
||||
if ie_desc is False:
|
||||
continue
|
||||
if ie_desc is not None:
|
||||
ie_md += ': {}'.format(ie.IE_DESC)
|
||||
ie_md += ': {0}'.format(ie.IE_DESC)
|
||||
if not ie.working():
|
||||
ie_md += ' (Currently broken)'
|
||||
yield ie_md
|
||||
|
@ -2,5 +2,5 @@
|
||||
universal = True
|
||||
|
||||
[flake8]
|
||||
exclude = youtube_dl/extractor/__init__.py,devscripts/buildserver.py,setup.py,build
|
||||
exclude = youtube_dl/extractor/__init__.py,devscripts/buildserver.py,setup.py,build,.git
|
||||
ignore = E501
|
||||
|
@ -82,18 +82,8 @@ class FakeYDL(YoutubeDL):
|
||||
|
||||
def gettestcases(include_onlymatching=False):
|
||||
for ie in youtube_dl.extractor.gen_extractors():
|
||||
t = getattr(ie, '_TEST', None)
|
||||
if t:
|
||||
assert not hasattr(ie, '_TESTS'), \
|
||||
'%s has _TEST and _TESTS' % type(ie).__name__
|
||||
tests = [t]
|
||||
else:
|
||||
tests = getattr(ie, '_TESTS', [])
|
||||
for t in tests:
|
||||
if not include_onlymatching and t.get('only_matching', False):
|
||||
continue
|
||||
t['name'] = type(ie).__name__[:-len('IE')]
|
||||
yield t
|
||||
for tc in ie.get_testcases(include_onlymatching):
|
||||
yield tc
|
||||
|
||||
|
||||
md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest()
|
||||
@ -120,6 +110,20 @@ def expect_info_dict(self, got_dict, expected_dict):
|
||||
else:
|
||||
if isinstance(expected, compat_str) and expected.startswith('md5:'):
|
||||
got = 'md5:' + md5(got_dict.get(info_field))
|
||||
elif isinstance(expected, compat_str) and expected.startswith('mincount:'):
|
||||
got = got_dict.get(info_field)
|
||||
self.assertTrue(
|
||||
isinstance(got, list),
|
||||
'Expected field %s to be a list, but it is of type %s' % (
|
||||
info_field, type(got).__name__))
|
||||
expected_num = int(expected.partition(':')[2])
|
||||
assertGreaterEqual(
|
||||
self, len(got), expected_num,
|
||||
'Expected %d items in field %s, but only got %d' % (
|
||||
expected_num, info_field, len(got)
|
||||
)
|
||||
)
|
||||
continue
|
||||
else:
|
||||
got = got_dict.get(info_field)
|
||||
self.assertEqual(expected, got,
|
||||
@ -136,7 +140,7 @@ def expect_info_dict(self, got_dict, expected_dict):
|
||||
# Are checkable fields missing from the test case definition?
|
||||
test_info_dict = dict((key, value if not isinstance(value, compat_str) or len(value) < 250 else 'md5:' + md5(value))
|
||||
for key, value in got_dict.items()
|
||||
if value and key in ('title', 'description', 'uploader', 'upload_date', 'timestamp', 'uploader_id', 'location'))
|
||||
if value and key in ('id', 'title', 'description', 'uploader', 'upload_date', 'timestamp', 'uploader_id', 'location'))
|
||||
missing_keys = set(test_info_dict.keys()) - set(expected_dict.keys())
|
||||
if missing_keys:
|
||||
def _repr(v):
|
||||
@ -144,9 +148,15 @@ def expect_info_dict(self, got_dict, expected_dict):
|
||||
return "'%s'" % v.replace('\\', '\\\\').replace("'", "\\'").replace('\n', '\\n')
|
||||
else:
|
||||
return repr(v)
|
||||
info_dict_str = ''.join(
|
||||
' %s: %s,\n' % (_repr(k), _repr(v))
|
||||
for k, v in test_info_dict.items())
|
||||
info_dict_str = ''
|
||||
if len(missing_keys) != len(expected_dict):
|
||||
info_dict_str += ''.join(
|
||||
' %s: %s,\n' % (_repr(k), _repr(v))
|
||||
for k, v in test_info_dict.items() if k not in missing_keys)
|
||||
info_dict_str += '\n'
|
||||
info_dict_str += ''.join(
|
||||
' %s: %s,\n' % (_repr(k), _repr(test_info_dict[k]))
|
||||
for k in missing_keys)
|
||||
write_string(
|
||||
'\n\'info_dict\': {\n' + info_dict_str + '}\n', out=sys.stderr)
|
||||
self.assertFalse(
|
||||
|
@ -40,5 +40,23 @@ class TestInfoExtractor(unittest.TestCase):
|
||||
self.assertEqual(ie._og_search_description(html), 'Some video\'s description ')
|
||||
self.assertEqual(ie._og_search_thumbnail(html), 'http://domain.com/pic.jpg?key1=val1&key2=val2')
|
||||
|
||||
def test_html_search_meta(self):
|
||||
ie = self.ie
|
||||
html = '''
|
||||
<meta name="a" content="1" />
|
||||
<meta name='b' content='2'>
|
||||
<meta name="c" content='3'>
|
||||
<meta name=d content='4'>
|
||||
<meta property="e" content='5' >
|
||||
<meta content="6" name="f">
|
||||
'''
|
||||
|
||||
self.assertEqual(ie._html_search_meta('a', html), '1')
|
||||
self.assertEqual(ie._html_search_meta('b', html), '2')
|
||||
self.assertEqual(ie._html_search_meta('c', html), '3')
|
||||
self.assertEqual(ie._html_search_meta('d', html), '4')
|
||||
self.assertEqual(ie._html_search_meta('e', html), '5')
|
||||
self.assertEqual(ie._html_search_meta('f', html), '6')
|
||||
|
||||
if __name__ == '__main__':
|
||||
unittest.main()
|
||||
|
@ -8,6 +8,8 @@ import sys
|
||||
import unittest
|
||||
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
|
||||
import copy
|
||||
|
||||
from test.helper import FakeYDL, assertRegexpMatches
|
||||
from youtube_dl import YoutubeDL
|
||||
from youtube_dl.extractor import YoutubeIE
|
||||
@ -192,6 +194,37 @@ class TestFormatSelection(unittest.TestCase):
|
||||
downloaded = ydl.downloaded_info_dicts[0]
|
||||
self.assertEqual(downloaded['format_id'], 'vid-high')
|
||||
|
||||
def test_format_selection_audio_exts(self):
|
||||
formats = [
|
||||
{'format_id': 'mp3-64', 'ext': 'mp3', 'abr': 64, 'url': 'http://_', 'vcodec': 'none'},
|
||||
{'format_id': 'ogg-64', 'ext': 'ogg', 'abr': 64, 'url': 'http://_', 'vcodec': 'none'},
|
||||
{'format_id': 'aac-64', 'ext': 'aac', 'abr': 64, 'url': 'http://_', 'vcodec': 'none'},
|
||||
{'format_id': 'mp3-32', 'ext': 'mp3', 'abr': 32, 'url': 'http://_', 'vcodec': 'none'},
|
||||
{'format_id': 'aac-32', 'ext': 'aac', 'abr': 32, 'url': 'http://_', 'vcodec': 'none'},
|
||||
]
|
||||
|
||||
info_dict = _make_result(formats)
|
||||
ydl = YDL({'format': 'best'})
|
||||
ie = YoutubeIE(ydl)
|
||||
ie._sort_formats(info_dict['formats'])
|
||||
ydl.process_ie_result(copy.deepcopy(info_dict))
|
||||
downloaded = ydl.downloaded_info_dicts[0]
|
||||
self.assertEqual(downloaded['format_id'], 'aac-64')
|
||||
|
||||
ydl = YDL({'format': 'mp3'})
|
||||
ie = YoutubeIE(ydl)
|
||||
ie._sort_formats(info_dict['formats'])
|
||||
ydl.process_ie_result(copy.deepcopy(info_dict))
|
||||
downloaded = ydl.downloaded_info_dicts[0]
|
||||
self.assertEqual(downloaded['format_id'], 'mp3-64')
|
||||
|
||||
ydl = YDL({'prefer_free_formats': True})
|
||||
ie = YoutubeIE(ydl)
|
||||
ie._sort_formats(info_dict['formats'])
|
||||
ydl.process_ie_result(copy.deepcopy(info_dict))
|
||||
downloaded = ydl.downloaded_info_dicts[0]
|
||||
self.assertEqual(downloaded['format_id'], 'ogg-64')
|
||||
|
||||
def test_format_selection_video(self):
|
||||
formats = [
|
||||
{'format_id': 'dash-video-low', 'ext': 'mp4', 'preference': 1, 'acodec': 'none', 'url': '_'},
|
||||
@ -218,7 +251,7 @@ class TestFormatSelection(unittest.TestCase):
|
||||
# 3D
|
||||
'85', '84', '102', '83', '101', '82', '100',
|
||||
# Dash video
|
||||
'138', '137', '248', '136', '247', '135', '246',
|
||||
'137', '248', '136', '247', '135', '246',
|
||||
'245', '244', '134', '243', '133', '242', '160',
|
||||
# Dash audio
|
||||
'141', '172', '140', '171', '139',
|
||||
@ -248,6 +281,61 @@ class TestFormatSelection(unittest.TestCase):
|
||||
downloaded = ydl.downloaded_info_dicts[0]
|
||||
self.assertEqual(downloaded['format_id'], f1id)
|
||||
|
||||
def test_format_filtering(self):
|
||||
formats = [
|
||||
{'format_id': 'A', 'filesize': 500, 'width': 1000},
|
||||
{'format_id': 'B', 'filesize': 1000, 'width': 500},
|
||||
{'format_id': 'C', 'filesize': 1000, 'width': 400},
|
||||
{'format_id': 'D', 'filesize': 2000, 'width': 600},
|
||||
{'format_id': 'E', 'filesize': 3000},
|
||||
{'format_id': 'F'},
|
||||
{'format_id': 'G', 'filesize': 1000000},
|
||||
]
|
||||
for f in formats:
|
||||
f['url'] = 'http://_/'
|
||||
f['ext'] = 'unknown'
|
||||
info_dict = _make_result(formats)
|
||||
|
||||
ydl = YDL({'format': 'best[filesize<3000]'})
|
||||
ydl.process_ie_result(info_dict)
|
||||
downloaded = ydl.downloaded_info_dicts[0]
|
||||
self.assertEqual(downloaded['format_id'], 'D')
|
||||
|
||||
ydl = YDL({'format': 'best[filesize<=3000]'})
|
||||
ydl.process_ie_result(info_dict)
|
||||
downloaded = ydl.downloaded_info_dicts[0]
|
||||
self.assertEqual(downloaded['format_id'], 'E')
|
||||
|
||||
ydl = YDL({'format': 'best[filesize <= ? 3000]'})
|
||||
ydl.process_ie_result(info_dict)
|
||||
downloaded = ydl.downloaded_info_dicts[0]
|
||||
self.assertEqual(downloaded['format_id'], 'F')
|
||||
|
||||
ydl = YDL({'format': 'best [filesize = 1000] [width>450]'})
|
||||
ydl.process_ie_result(info_dict)
|
||||
downloaded = ydl.downloaded_info_dicts[0]
|
||||
self.assertEqual(downloaded['format_id'], 'B')
|
||||
|
||||
ydl = YDL({'format': 'best [filesize = 1000] [width!=450]'})
|
||||
ydl.process_ie_result(info_dict)
|
||||
downloaded = ydl.downloaded_info_dicts[0]
|
||||
self.assertEqual(downloaded['format_id'], 'C')
|
||||
|
||||
ydl = YDL({'format': '[filesize>?1]'})
|
||||
ydl.process_ie_result(info_dict)
|
||||
downloaded = ydl.downloaded_info_dicts[0]
|
||||
self.assertEqual(downloaded['format_id'], 'G')
|
||||
|
||||
ydl = YDL({'format': '[filesize<1M]'})
|
||||
ydl.process_ie_result(info_dict)
|
||||
downloaded = ydl.downloaded_info_dicts[0]
|
||||
self.assertEqual(downloaded['format_id'], 'E')
|
||||
|
||||
ydl = YDL({'format': '[filesize<1MiB]'})
|
||||
ydl.process_ie_result(info_dict)
|
||||
downloaded = ydl.downloaded_info_dicts[0]
|
||||
self.assertEqual(downloaded['format_id'], 'G')
|
||||
|
||||
def test_add_extra_info(self):
|
||||
test_dict = {
|
||||
'extractor': 'Foo',
|
||||
|
@ -45,11 +45,6 @@ class TestAgeRestriction(unittest.TestCase):
|
||||
'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
|
||||
'505835.mp4', 2, old_age=25)
|
||||
|
||||
def test_pornotube(self):
|
||||
self._assert_restricted(
|
||||
'http://pornotube.com/c/173/m/1689755/Marilyn-Monroe-Bathing',
|
||||
'1689755.flv', 13)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
unittest.main()
|
||||
|
@ -14,7 +14,6 @@ from test.helper import gettestcases
|
||||
from youtube_dl.extractor import (
|
||||
FacebookIE,
|
||||
gen_extractors,
|
||||
TwitchIE,
|
||||
YoutubeIE,
|
||||
)
|
||||
|
||||
@ -72,18 +71,6 @@ class TestAllURLsMatching(unittest.TestCase):
|
||||
self.assertMatch('http://www.youtube.com/results?search_query=making+mustard', ['youtube:search_url'])
|
||||
self.assertMatch('https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', ['youtube:search_url'])
|
||||
|
||||
def test_twitch_channelid_matching(self):
|
||||
self.assertTrue(TwitchIE.suitable('twitch.tv/vanillatv'))
|
||||
self.assertTrue(TwitchIE.suitable('www.twitch.tv/vanillatv'))
|
||||
self.assertTrue(TwitchIE.suitable('http://www.twitch.tv/vanillatv'))
|
||||
self.assertTrue(TwitchIE.suitable('http://www.twitch.tv/vanillatv/'))
|
||||
|
||||
def test_twitch_videoid_matching(self):
|
||||
self.assertTrue(TwitchIE.suitable('http://www.twitch.tv/vanillatv/b/328087483'))
|
||||
|
||||
def test_twitch_chapterid_matching(self):
|
||||
self.assertTrue(TwitchIE.suitable('http://www.twitch.tv/tsm_theoddone/c/2349361'))
|
||||
|
||||
def test_youtube_extract(self):
|
||||
assertExtractId = lambda url, id: self.assertEqual(YoutubeIE.extract_id(url), id)
|
||||
assertExtractId('http://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
|
||||
@ -115,8 +102,6 @@ class TestAllURLsMatching(unittest.TestCase):
|
||||
self.assertMatch(':ythistory', ['youtube:history'])
|
||||
self.assertMatch(':thedailyshow', ['ComedyCentralShows'])
|
||||
self.assertMatch(':tds', ['ComedyCentralShows'])
|
||||
self.assertMatch(':colbertreport', ['ComedyCentralShows'])
|
||||
self.assertMatch(':cr', ['ComedyCentralShows'])
|
||||
|
||||
def test_vimeo_matching(self):
|
||||
self.assertMatch('http://vimeo.com/channels/tributes', ['vimeo:channel'])
|
||||
|
@ -89,7 +89,7 @@ def generator(test_case):
|
||||
|
||||
for tc in test_cases:
|
||||
info_dict = tc.get('info_dict', {})
|
||||
if not tc.get('file') and not (info_dict.get('id') and info_dict.get('ext')):
|
||||
if not (info_dict.get('id') and info_dict.get('ext')):
|
||||
raise Exception('Test definition incorrect. The output file cannot be known. Are both \'id\' and \'ext\' keys present?')
|
||||
|
||||
if 'skip' in test_case:
|
||||
@ -116,7 +116,7 @@ def generator(test_case):
|
||||
expect_warnings(ydl, test_case.get('expected_warnings', []))
|
||||
|
||||
def get_tc_filename(tc):
|
||||
return tc.get('file') or ydl.prepare_filename(tc.get('info_dict', {}))
|
||||
return ydl.prepare_filename(tc.get('info_dict', {}))
|
||||
|
||||
res_dict = None
|
||||
|
||||
|
72
test/test_http.py
Normal file
72
test/test_http.py
Normal file
@ -0,0 +1,72 @@
|
||||
#!/usr/bin/env python
|
||||
from __future__ import unicode_literals
|
||||
|
||||
# Allow direct execution
|
||||
import os
|
||||
import sys
|
||||
import unittest
|
||||
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
|
||||
from youtube_dl import YoutubeDL
|
||||
from youtube_dl.compat import compat_http_server
|
||||
import ssl
|
||||
import threading
|
||||
|
||||
TEST_DIR = os.path.dirname(os.path.abspath(__file__))
|
||||
|
||||
|
||||
class HTTPTestRequestHandler(compat_http_server.BaseHTTPRequestHandler):
|
||||
def log_message(self, format, *args):
|
||||
pass
|
||||
|
||||
def do_GET(self):
|
||||
if self.path == '/video.html':
|
||||
self.send_response(200)
|
||||
self.send_header('Content-Type', 'text/html; charset=utf-8')
|
||||
self.end_headers()
|
||||
self.wfile.write(b'<html><video src="/vid.mp4" /></html>')
|
||||
elif self.path == '/vid.mp4':
|
||||
self.send_response(200)
|
||||
self.send_header('Content-Type', 'video/mp4')
|
||||
self.end_headers()
|
||||
self.wfile.write(b'\x00\x00\x00\x00\x20\x66\x74[video]')
|
||||
else:
|
||||
assert False
|
||||
|
||||
|
||||
class FakeLogger(object):
|
||||
def debug(self, msg):
|
||||
pass
|
||||
|
||||
def warning(self, msg):
|
||||
pass
|
||||
|
||||
def error(self, msg):
|
||||
pass
|
||||
|
||||
|
||||
class TestHTTP(unittest.TestCase):
|
||||
def setUp(self):
|
||||
certfn = os.path.join(TEST_DIR, 'testcert.pem')
|
||||
self.httpd = compat_http_server.HTTPServer(
|
||||
('localhost', 0), HTTPTestRequestHandler)
|
||||
self.httpd.socket = ssl.wrap_socket(
|
||||
self.httpd.socket, certfile=certfn, server_side=True)
|
||||
self.port = self.httpd.socket.getsockname()[1]
|
||||
self.server_thread = threading.Thread(target=self.httpd.serve_forever)
|
||||
self.server_thread.daemon = True
|
||||
self.server_thread.start()
|
||||
|
||||
def test_nocheckcertificate(self):
|
||||
if sys.version_info >= (2, 7, 9): # No certificate checking anyways
|
||||
ydl = YoutubeDL({'logger': FakeLogger()})
|
||||
self.assertRaises(
|
||||
Exception,
|
||||
ydl.extract_info, 'https://localhost:%d/video.html' % self.port)
|
||||
|
||||
ydl = YoutubeDL({'logger': FakeLogger(), 'nocheckcertificate': True})
|
||||
r = ydl.extract_info('https://localhost:%d/video.html' % self.port)
|
||||
self.assertEqual(r['url'], 'https://localhost:%d/vid.mp4' % self.port)
|
||||
|
||||
if __name__ == '__main__':
|
||||
unittest.main()
|
95
test/test_jsinterp.py
Normal file
95
test/test_jsinterp.py
Normal file
@ -0,0 +1,95 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
from __future__ import unicode_literals
|
||||
|
||||
# Allow direct execution
|
||||
import os
|
||||
import sys
|
||||
import unittest
|
||||
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
|
||||
from youtube_dl.jsinterp import JSInterpreter
|
||||
|
||||
|
||||
class TestJSInterpreter(unittest.TestCase):
|
||||
def test_basic(self):
|
||||
jsi = JSInterpreter('function x(){;}')
|
||||
self.assertEqual(jsi.call_function('x'), None)
|
||||
|
||||
jsi = JSInterpreter('function x3(){return 42;}')
|
||||
self.assertEqual(jsi.call_function('x3'), 42)
|
||||
|
||||
def test_calc(self):
|
||||
jsi = JSInterpreter('function x4(a){return 2*a+1;}')
|
||||
self.assertEqual(jsi.call_function('x4', 3), 7)
|
||||
|
||||
def test_empty_return(self):
|
||||
jsi = JSInterpreter('function f(){return; y()}')
|
||||
self.assertEqual(jsi.call_function('f'), None)
|
||||
|
||||
def test_morespace(self):
|
||||
jsi = JSInterpreter('function x (a) { return 2 * a + 1 ; }')
|
||||
self.assertEqual(jsi.call_function('x', 3), 7)
|
||||
|
||||
jsi = JSInterpreter('function f () { x = 2 ; return x; }')
|
||||
self.assertEqual(jsi.call_function('f'), 2)
|
||||
|
||||
def test_strange_chars(self):
|
||||
jsi = JSInterpreter('function $_xY1 ($_axY1) { var $_axY2 = $_axY1 + 1; return $_axY2; }')
|
||||
self.assertEqual(jsi.call_function('$_xY1', 20), 21)
|
||||
|
||||
def test_operators(self):
|
||||
jsi = JSInterpreter('function f(){return 1 << 5;}')
|
||||
self.assertEqual(jsi.call_function('f'), 32)
|
||||
|
||||
jsi = JSInterpreter('function f(){return 19 & 21;}')
|
||||
self.assertEqual(jsi.call_function('f'), 17)
|
||||
|
||||
jsi = JSInterpreter('function f(){return 11 >> 2;}')
|
||||
self.assertEqual(jsi.call_function('f'), 2)
|
||||
|
||||
def test_array_access(self):
|
||||
jsi = JSInterpreter('function f(){var x = [1,2,3]; x[0] = 4; x[0] = 5; x[2] = 7; return x;}')
|
||||
self.assertEqual(jsi.call_function('f'), [5, 2, 7])
|
||||
|
||||
def test_parens(self):
|
||||
jsi = JSInterpreter('function f(){return (1) + (2) * ((( (( (((((3)))))) )) ));}')
|
||||
self.assertEqual(jsi.call_function('f'), 7)
|
||||
|
||||
jsi = JSInterpreter('function f(){return (1 + 2) * 3;}')
|
||||
self.assertEqual(jsi.call_function('f'), 9)
|
||||
|
||||
def test_assignments(self):
|
||||
jsi = JSInterpreter('function f(){var x = 20; x = 30 + 1; return x;}')
|
||||
self.assertEqual(jsi.call_function('f'), 31)
|
||||
|
||||
jsi = JSInterpreter('function f(){var x = 20; x += 30 + 1; return x;}')
|
||||
self.assertEqual(jsi.call_function('f'), 51)
|
||||
|
||||
jsi = JSInterpreter('function f(){var x = 20; x -= 30 + 1; return x;}')
|
||||
self.assertEqual(jsi.call_function('f'), -11)
|
||||
|
||||
def test_comments(self):
|
||||
jsi = JSInterpreter('''
|
||||
function x() {
|
||||
var x = /* 1 + */ 2;
|
||||
var y = /* 30
|
||||
* 40 */ 50;
|
||||
return x + y;
|
||||
}
|
||||
''')
|
||||
self.assertEqual(jsi.call_function('x'), 52)
|
||||
|
||||
def test_precedence(self):
|
||||
jsi = JSInterpreter('''
|
||||
function x() {
|
||||
var a = [10, 20, 30, 40, 50];
|
||||
var b = 6;
|
||||
a[0]=a[b%a.length];
|
||||
return a;
|
||||
}''')
|
||||
self.assertEqual(jsi.call_function('x'), [20, 20, 30, 40, 50])
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
unittest.main()
|
@ -17,6 +17,7 @@ from youtube_dl.extractor import (
|
||||
TEDIE,
|
||||
VimeoIE,
|
||||
WallaIE,
|
||||
CeskaTelevizeIE,
|
||||
)
|
||||
|
||||
|
||||
@ -317,5 +318,32 @@ class TestWallaSubtitles(BaseTestSubtitles):
|
||||
self.assertEqual(len(subtitles), 0)
|
||||
|
||||
|
||||
class TestCeskaTelevizeSubtitles(BaseTestSubtitles):
|
||||
url = 'http://www.ceskatelevize.cz/ivysilani/10600540290-u6-uzasny-svet-techniky'
|
||||
IE = CeskaTelevizeIE
|
||||
|
||||
def test_list_subtitles(self):
|
||||
self.DL.expect_warning('Automatic Captions not supported by this server')
|
||||
self.DL.params['listsubtitles'] = True
|
||||
info_dict = self.getInfoDict()
|
||||
self.assertEqual(info_dict, None)
|
||||
|
||||
def test_allsubtitles(self):
|
||||
self.DL.expect_warning('Automatic Captions not supported by this server')
|
||||
self.DL.params['writesubtitles'] = True
|
||||
self.DL.params['allsubtitles'] = True
|
||||
subtitles = self.getSubtitles()
|
||||
self.assertEqual(set(subtitles.keys()), set(['cs']))
|
||||
self.assertEqual(md5(subtitles['cs']), '9bf52d9549533c32c427e264bf0847d4')
|
||||
|
||||
def test_nosubtitles(self):
|
||||
self.DL.expect_warning('video doesn\'t have subtitles')
|
||||
self.url = 'http://www.ceskatelevize.cz/ivysilani/ivysilani/10441294653-hyde-park-civilizace/214411058091220'
|
||||
self.DL.params['writesubtitles'] = True
|
||||
self.DL.params['allsubtitles'] = True
|
||||
subtitles = self.getSubtitles()
|
||||
self.assertEqual(len(subtitles), 0)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
unittest.main()
|
||||
|
@ -16,6 +16,7 @@ import json
|
||||
import xml.etree.ElementTree
|
||||
|
||||
from youtube_dl.utils import (
|
||||
age_restricted,
|
||||
args_to_str,
|
||||
clean_html,
|
||||
DateRange,
|
||||
@ -27,6 +28,7 @@ from youtube_dl.utils import (
|
||||
fix_xml_ampersands,
|
||||
InAdvancePagedList,
|
||||
intlist_to_bytes,
|
||||
is_html,
|
||||
js_to_json,
|
||||
limit_length,
|
||||
OnDemandPagedList,
|
||||
@ -50,6 +52,7 @@ from youtube_dl.utils import (
|
||||
urlencode_postdata,
|
||||
version_tuple,
|
||||
xpath_with_ns,
|
||||
render_table,
|
||||
)
|
||||
|
||||
|
||||
@ -78,6 +81,10 @@ class TestUtil(unittest.TestCase):
|
||||
tests = '\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430'
|
||||
self.assertEqual(sanitize_filename(tests), tests)
|
||||
|
||||
self.assertEqual(
|
||||
sanitize_filename('New World record at 0:12:34'),
|
||||
'New World record at 0_12_34')
|
||||
|
||||
forbidden = '"\0\\/'
|
||||
for fc in forbidden:
|
||||
for fbc in forbidden:
|
||||
@ -143,6 +150,7 @@ class TestUtil(unittest.TestCase):
|
||||
self.assertEqual(unified_strdate('8/7/2009'), '20090708')
|
||||
self.assertEqual(unified_strdate('Dec 14, 2012'), '20121214')
|
||||
self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
|
||||
self.assertEqual(unified_strdate('1968 12 10'), '19681210')
|
||||
self.assertEqual(unified_strdate('1968-12-10'), '19681210')
|
||||
self.assertEqual(unified_strdate('28/01/2014 21:00:00 +0100'), '20140128')
|
||||
self.assertEqual(
|
||||
@ -207,6 +215,8 @@ class TestUtil(unittest.TestCase):
|
||||
|
||||
def test_parse_duration(self):
|
||||
self.assertEqual(parse_duration(None), None)
|
||||
self.assertEqual(parse_duration(False), None)
|
||||
self.assertEqual(parse_duration('invalid'), None)
|
||||
self.assertEqual(parse_duration('1'), 1)
|
||||
self.assertEqual(parse_duration('1337:12'), 80232)
|
||||
self.assertEqual(parse_duration('9:12:43'), 33163)
|
||||
@ -402,5 +412,38 @@ Trying to open render node...
|
||||
Success at /dev/dri/renderD128.
|
||||
ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')
|
||||
|
||||
def test_age_restricted(self):
|
||||
self.assertFalse(age_restricted(None, 10)) # unrestricted content
|
||||
self.assertFalse(age_restricted(1, None)) # unrestricted policy
|
||||
self.assertFalse(age_restricted(8, 10))
|
||||
self.assertTrue(age_restricted(18, 14))
|
||||
self.assertFalse(age_restricted(18, 18))
|
||||
|
||||
def test_is_html(self):
|
||||
self.assertFalse(is_html(b'\x49\x44\x43<html'))
|
||||
self.assertTrue(is_html(b'<!DOCTYPE foo>\xaaa'))
|
||||
self.assertTrue(is_html( # UTF-8 with BOM
|
||||
b'\xef\xbb\xbf<!DOCTYPE foo>\xaaa'))
|
||||
self.assertTrue(is_html( # UTF-16-LE
|
||||
b'\xff\xfe<\x00h\x00t\x00m\x00l\x00>\x00\xe4\x00'
|
||||
))
|
||||
self.assertTrue(is_html( # UTF-16-BE
|
||||
b'\xfe\xff\x00<\x00h\x00t\x00m\x00l\x00>\x00\xe4'
|
||||
))
|
||||
self.assertTrue(is_html( # UTF-32-BE
|
||||
b'\x00\x00\xFE\xFF\x00\x00\x00<\x00\x00\x00h\x00\x00\x00t\x00\x00\x00m\x00\x00\x00l\x00\x00\x00>\x00\x00\x00\xe4'))
|
||||
self.assertTrue(is_html( # UTF-32-LE
|
||||
b'\xFF\xFE\x00\x00<\x00\x00\x00h\x00\x00\x00t\x00\x00\x00m\x00\x00\x00l\x00\x00\x00>\x00\x00\x00\xe4\x00\x00\x00'))
|
||||
|
||||
def test_render_table(self):
|
||||
self.assertEqual(
|
||||
render_table(
|
||||
['a', 'bcd'],
|
||||
[[123, 4], [9999, 51]]),
|
||||
'a bcd\n'
|
||||
'123 4\n'
|
||||
'9999 51')
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
unittest.main()
|
||||
|
52
test/testcert.pem
Normal file
52
test/testcert.pem
Normal file
@ -0,0 +1,52 @@
|
||||
-----BEGIN PRIVATE KEY-----
|
||||
MIIEvQIBADANBgkqhkiG9w0BAQEFAASCBKcwggSjAgEAAoIBAQDMF0bAzaHAdIyB
|
||||
HRmnIp4vv40lGqEePmWqicCl0QZ0wsb5dNysSxSa7330M2QeQopGfdaUYF1uTcNp
|
||||
Qx6ECgBSfg+RrOBI7r/u4F+sKX8MUXVaf/5QoBUrGNGSn/pp7HMGOuQqO6BVg4+h
|
||||
A1ySSwUG8mZItLRry1ISyErmW8b9xlqfd97uLME/5tX+sMelRFjUbAx8A4CK58Ev
|
||||
mMguHVTlXzx5RMdYcf1VScYcjlV/qA45uzP8zwI5aigfcmUD+tbGuQRhKxUhmw0J
|
||||
aobtOR6+JSOAULW5gYa/egE4dWLwbyM6b6eFbdnjlQzEA1EW7ChMPAW/Mo83KyiP
|
||||
tKMCSQulAgMBAAECggEALCfBDAexPjU5DNoh6bIorUXxIJzxTNzNHCdvgbCGiA54
|
||||
BBKPh8s6qwazpnjT6WQWDIg/O5zZufqjE4wM9x4+0Zoqfib742ucJO9wY4way6x4
|
||||
Clt0xzbLPabB+MoZ4H7ip+9n2+dImhe7pGdYyOHoNYeOL57BBi1YFW42Hj6u/8pd
|
||||
63YCXisto3Rz1YvRQVjwsrS+cRKZlzAFQRviL30jav7Wh1aWEfcXxjj4zhm8pJdk
|
||||
ITGtq6howz57M0NtX6hZnfe8ywzTnDFIGKIMA2cYHuYJcBh9bc4tCGubTvTKK9UE
|
||||
8fM+f6UbfGqfpKCq1mcgs0XMoFDSzKS9+mSJn0+5JQKBgQD+OCKaeH3Yzw5zGnlw
|
||||
XuQfMJGNcgNr+ImjmvzUAC2fAZUJLAcQueE5kzMv5Fmd+EFE2CEX1Vit3tg0SXvA
|
||||
G+bq609doILHMA03JHnV1npO/YNIhG3AAtJlKYGxQNfWH9mflYj9mEui8ZFxG52o
|
||||
zWhHYuifOjjZszUR+/eio6NPzwKBgQDNhUBTrT8LIX4SE/EFUiTlYmWIvOMgXYvN
|
||||
8Cm3IRNQ/yyphZaXEU0eJzfX5uCDfSVOgd6YM/2pRah+t+1Hvey4H8e0GVTu5wMP
|
||||
gkkqwKPGIR1YOmlw6ippqwvoJD7LuYrm6Q4D6e1PvkjwCq6lEndrOPmPrrXNd0JJ
|
||||
XO60y3U2SwKBgQDLkyZarryQXxcCI6Q10Tc6pskYDMIit095PUbTeiUOXNT9GE28
|
||||
Hi32ziLCakk9kCysNasii81MxtQ54tJ/f5iGbNMMddnkKl2a19Hc5LjjAm4cJzg/
|
||||
98KGEhvyVqvAo5bBDZ06/rcrD+lZOzUglQS5jcIcqCIYa0LHWQ/wJLxFzwKBgFcZ
|
||||
1SRhdSmDfUmuF+S4ZpistflYjC3IV5rk4NkS9HvMWaJS0nqdw4A3AMzItXgkjq4S
|
||||
DkOVLTkTI5Do5HAWRv/VwC5M2hkR4NMu1VGAKSisGiKtRsirBWSZMEenLNHshbjN
|
||||
Jrpz5rZ4H7NT46ZkCCZyFBpX4gb9NyOedjA7Via3AoGARF8RxbYjnEGGFuhnbrJB
|
||||
FTPR0vaL4faY3lOgRZ8jOG9V2c9Hzi/y8a8TU4C11jnJSDqYCXBTd5XN28npYxtD
|
||||
pjRsCwy6ze+yvYXPO7C978eMG3YRyj366NXUxnXN59ibwe/lxi2OD9z8J1LEdF6z
|
||||
VJua1Wn8HKxnXMI61DhTCSo=
|
||||
-----END PRIVATE KEY-----
|
||||
-----BEGIN CERTIFICATE-----
|
||||
MIIEEzCCAvugAwIBAgIJAK1haYi6gmSKMA0GCSqGSIb3DQEBCwUAMIGeMQswCQYD
|
||||
VQQGEwJERTEMMAoGA1UECAwDTlJXMRQwEgYDVQQHDAtEdWVzc2VsZG9yZjEbMBkG
|
||||
A1UECgwSeW91dHViZS1kbCBwcm9qZWN0MRkwFwYDVQQLDBB5b3V0dWJlLWRsIHRl
|
||||
c3RzMRIwEAYDVQQDDAlsb2NhbGhvc3QxHzAdBgkqhkiG9w0BCQEWEHBoaWhhZ0Bw
|
||||
aGloYWcuZGUwIBcNMTUwMTMwMDExNTA4WhgPMjExNTAxMDYwMTE1MDhaMIGeMQsw
|
||||
CQYDVQQGEwJERTEMMAoGA1UECAwDTlJXMRQwEgYDVQQHDAtEdWVzc2VsZG9yZjEb
|
||||
MBkGA1UECgwSeW91dHViZS1kbCBwcm9qZWN0MRkwFwYDVQQLDBB5b3V0dWJlLWRs
|
||||
IHRlc3RzMRIwEAYDVQQDDAlsb2NhbGhvc3QxHzAdBgkqhkiG9w0BCQEWEHBoaWhh
|
||||
Z0BwaGloYWcuZGUwggEiMA0GCSqGSIb3DQEBAQUAA4IBDwAwggEKAoIBAQDMF0bA
|
||||
zaHAdIyBHRmnIp4vv40lGqEePmWqicCl0QZ0wsb5dNysSxSa7330M2QeQopGfdaU
|
||||
YF1uTcNpQx6ECgBSfg+RrOBI7r/u4F+sKX8MUXVaf/5QoBUrGNGSn/pp7HMGOuQq
|
||||
O6BVg4+hA1ySSwUG8mZItLRry1ISyErmW8b9xlqfd97uLME/5tX+sMelRFjUbAx8
|
||||
A4CK58EvmMguHVTlXzx5RMdYcf1VScYcjlV/qA45uzP8zwI5aigfcmUD+tbGuQRh
|
||||
KxUhmw0JaobtOR6+JSOAULW5gYa/egE4dWLwbyM6b6eFbdnjlQzEA1EW7ChMPAW/
|
||||
Mo83KyiPtKMCSQulAgMBAAGjUDBOMB0GA1UdDgQWBBTBUZoqhQkzHQ6xNgZfFxOd
|
||||
ZEVt8TAfBgNVHSMEGDAWgBTBUZoqhQkzHQ6xNgZfFxOdZEVt8TAMBgNVHRMEBTAD
|
||||
AQH/MA0GCSqGSIb3DQEBCwUAA4IBAQCUOCl3T/J9B08Z+ijfOJAtkbUaEHuVZb4x
|
||||
5EpZSy2ZbkLvtsftMFieHVNXn9dDswQc5qjYStCC4o60LKw4M6Y63FRsAZ/DNaqb
|
||||
PY3jyCyuugZ8/sNf50vHYkAcF7SQYqOQFQX4TQsNUk2xMJIt7H0ErQFmkf/u3dg6
|
||||
cy89zkT462IwxzSG7NNhIlRkL9o5qg+Y1mF9eZA1B0rcL6hO24PPTHOd90HDChBu
|
||||
SZ6XMi/LzYQSTf0Vg2R+uMIVlzSlkdcZ6sqVnnqeLL8dFyIa4e9sj/D4ZCYP8Mqe
|
||||
Z73H5/NNhmwCHRqVUTgm307xblQaWGhwAiDkaRvRW2aJQ0qGEdZK
|
||||
-----END CERTIFICATE-----
|
@ -10,6 +10,7 @@ import io
|
||||
import itertools
|
||||
import json
|
||||
import locale
|
||||
import operator
|
||||
import os
|
||||
import platform
|
||||
import re
|
||||
@ -24,6 +25,7 @@ if os.name == 'nt':
|
||||
import ctypes
|
||||
|
||||
from .compat import (
|
||||
compat_basestring,
|
||||
compat_cookiejar,
|
||||
compat_expanduser,
|
||||
compat_http_client,
|
||||
@ -49,26 +51,33 @@ from .utils import (
|
||||
make_HTTPS_handler,
|
||||
MaxDownloadsReached,
|
||||
PagedList,
|
||||
parse_filesize,
|
||||
PostProcessingError,
|
||||
platform_name,
|
||||
preferredencoding,
|
||||
render_table,
|
||||
SameFileError,
|
||||
sanitize_filename,
|
||||
std_headers,
|
||||
subtitles_filename,
|
||||
takewhile_inclusive,
|
||||
UnavailableVideoError,
|
||||
url_basename,
|
||||
version_tuple,
|
||||
write_json_file,
|
||||
write_string,
|
||||
YoutubeDLHandler,
|
||||
prepend_extension,
|
||||
args_to_str,
|
||||
age_restricted,
|
||||
)
|
||||
from .cache import Cache
|
||||
from .extractor import get_info_extractor, gen_extractors
|
||||
from .downloader import get_suitable_downloader
|
||||
from .downloader.rtmp import rtmpdump_version
|
||||
from .postprocessor import (
|
||||
FFmpegFixupM4aPP,
|
||||
FFmpegFixupStretchedPP,
|
||||
FFmpegMergerPP,
|
||||
FFmpegPostProcessor,
|
||||
get_postprocessor,
|
||||
@ -129,6 +138,7 @@ class YoutubeDL(object):
|
||||
nooverwrites: Prevent overwriting files.
|
||||
playliststart: Playlist item to start at.
|
||||
playlistend: Playlist item to end at.
|
||||
playlist_items: Specific indices of playlist to download.
|
||||
playlistreverse: Download playlist items in reverse order.
|
||||
matchtitle: Download only matching titles.
|
||||
rejecttitle: Reject downloads for matching titles.
|
||||
@ -138,6 +148,7 @@ class YoutubeDL(object):
|
||||
writeinfojson: Write the video description to a .info.json file
|
||||
writeannotations: Write the video annotations to a .annotations.xml file
|
||||
writethumbnail: Write the thumbnail image to a file
|
||||
write_all_thumbnails: Write all thumbnail formats to files
|
||||
writesubtitles: Write the video subtitles to a file
|
||||
writeautomaticsub: Write the automatic subtitles to a file
|
||||
allsubtitles: Downloads all the subtitles of the video
|
||||
@ -188,11 +199,12 @@ class YoutubeDL(object):
|
||||
postprocessor.
|
||||
progress_hooks: A list of functions that get called on download
|
||||
progress, with a dictionary with the entries
|
||||
* filename: The final filename
|
||||
* status: One of "downloading" and "finished"
|
||||
|
||||
The dict may also have some of the following entries:
|
||||
* status: One of "downloading" and "finished".
|
||||
Check this first and ignore unknown values.
|
||||
|
||||
If status is one of "downloading" or "finished", the
|
||||
following properties may also be present:
|
||||
* filename: The final filename (always present)
|
||||
* downloaded_bytes: Bytes on disk
|
||||
* total_bytes: Size of the whole file, None if unknown
|
||||
* tmpfilename: The filename we're currently writing to
|
||||
@ -202,12 +214,27 @@ class YoutubeDL(object):
|
||||
|
||||
Progress hooks are guaranteed to be called at least once
|
||||
(with status "finished") if the download is successful.
|
||||
merge_output_format: Extension to use when merging formats.
|
||||
fixup: Automatically correct known faults of the file.
|
||||
One of:
|
||||
- "never": do nothing
|
||||
- "warn": only emit a warning
|
||||
- "detect_or_warn": check whether we can do anything
|
||||
about it, warn otherwise (default)
|
||||
source_address: (Experimental) Client-side IP address to bind to.
|
||||
call_home: Boolean, true iff we are allowed to contact the
|
||||
youtube-dl servers for debugging.
|
||||
sleep_interval: Number of seconds to sleep before each download.
|
||||
external_downloader: Executable of the external downloader to call.
|
||||
listformats: Print an overview of available video formats and exit.
|
||||
list_thumbnails: Print a table of all thumbnails and exit.
|
||||
|
||||
|
||||
The following parameters are not used by YoutubeDL itself, they are used by
|
||||
the FileDownloader:
|
||||
nopart, updatetime, buffersize, ratelimit, min_filesize, max_filesize, test,
|
||||
noresizebuffer, retries, continuedl, noprogress, consoletitle
|
||||
noresizebuffer, retries, continuedl, noprogress, consoletitle,
|
||||
xattr_set_filesize.
|
||||
|
||||
The following options are used by the post processors:
|
||||
prefer_ffmpeg: If True, use ffmpeg instead of avconv if both are available,
|
||||
@ -517,6 +544,11 @@ class YoutubeDL(object):
|
||||
outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL)
|
||||
tmpl = compat_expanduser(outtmpl)
|
||||
filename = tmpl % template_dict
|
||||
# Temporary fix for #4787
|
||||
# 'Treat' all problem characters by passing filename through preferredencoding
|
||||
# to workaround encoding issues with subprocess on python2 @ Windows
|
||||
if sys.version_info < (3, 0) and sys.platform == 'win32':
|
||||
filename = encodeFilename(filename, True).decode(preferredencoding())
|
||||
return filename
|
||||
except ValueError as err:
|
||||
self.report_error('Error in output template: ' + str(err) + ' (encoding: ' + repr(preferredencoding()) + ')')
|
||||
@ -550,13 +582,8 @@ class YoutubeDL(object):
|
||||
max_views = self.params.get('max_views')
|
||||
if max_views is not None and view_count > max_views:
|
||||
return 'Skipping %s, because it has exceeded the maximum view count (%d/%d)' % (video_title, view_count, max_views)
|
||||
age_limit = self.params.get('age_limit')
|
||||
if age_limit is not None:
|
||||
actual_age_limit = info_dict.get('age_limit')
|
||||
if actual_age_limit is None:
|
||||
actual_age_limit = 0
|
||||
if age_limit < actual_age_limit:
|
||||
return 'Skipping "' + title + '" because it is age restricted'
|
||||
if age_restricted(info_dict.get('age_limit'), self.params.get('age_limit')):
|
||||
return 'Skipping "%s" because it is age restricted' % title
|
||||
if self.in_download_archive(info_dict):
|
||||
return '%s has already been recorded in archive' % video_title
|
||||
return None
|
||||
@ -685,24 +712,51 @@ class YoutubeDL(object):
|
||||
if playlistend == -1:
|
||||
playlistend = None
|
||||
|
||||
playlistitems_str = self.params.get('playlist_items', None)
|
||||
playlistitems = None
|
||||
if playlistitems_str is not None:
|
||||
def iter_playlistitems(format):
|
||||
for string_segment in format.split(','):
|
||||
if '-' in string_segment:
|
||||
start, end = string_segment.split('-')
|
||||
for item in range(int(start), int(end) + 1):
|
||||
yield int(item)
|
||||
else:
|
||||
yield int(string_segment)
|
||||
playlistitems = iter_playlistitems(playlistitems_str)
|
||||
|
||||
ie_entries = ie_result['entries']
|
||||
if isinstance(ie_entries, list):
|
||||
n_all_entries = len(ie_entries)
|
||||
entries = ie_entries[playliststart:playlistend]
|
||||
if playlistitems:
|
||||
entries = [ie_entries[i - 1] for i in playlistitems]
|
||||
else:
|
||||
entries = ie_entries[playliststart:playlistend]
|
||||
n_entries = len(entries)
|
||||
self.to_screen(
|
||||
"[%s] playlist %s: Collected %d video ids (downloading %d of them)" %
|
||||
(ie_result['extractor'], playlist, n_all_entries, n_entries))
|
||||
elif isinstance(ie_entries, PagedList):
|
||||
entries = ie_entries.getslice(
|
||||
playliststart, playlistend)
|
||||
if playlistitems:
|
||||
entries = []
|
||||
for item in playlistitems:
|
||||
entries.extend(ie_entries.getslice(
|
||||
item - 1, item
|
||||
))
|
||||
else:
|
||||
entries = ie_entries.getslice(
|
||||
playliststart, playlistend)
|
||||
n_entries = len(entries)
|
||||
self.to_screen(
|
||||
"[%s] playlist %s: Downloading %d videos" %
|
||||
(ie_result['extractor'], playlist, n_entries))
|
||||
else: # iterable
|
||||
entries = list(itertools.islice(
|
||||
ie_entries, playliststart, playlistend))
|
||||
if playlistitems:
|
||||
entry_list = list(ie_entries)
|
||||
entries = [entry_list[i - 1] for i in playlistitems]
|
||||
else:
|
||||
entries = list(itertools.islice(
|
||||
ie_entries, playliststart, playlistend))
|
||||
n_entries = len(entries)
|
||||
self.to_screen(
|
||||
"[%s] playlist %s: Downloading %d videos" %
|
||||
@ -760,7 +814,59 @@ class YoutubeDL(object):
|
||||
else:
|
||||
raise Exception('Invalid result type: %s' % result_type)
|
||||
|
||||
def _apply_format_filter(self, format_spec, available_formats):
|
||||
" Returns a tuple of the remaining format_spec and filtered formats "
|
||||
|
||||
OPERATORS = {
|
||||
'<': operator.lt,
|
||||
'<=': operator.le,
|
||||
'>': operator.gt,
|
||||
'>=': operator.ge,
|
||||
'=': operator.eq,
|
||||
'!=': operator.ne,
|
||||
}
|
||||
operator_rex = re.compile(r'''(?x)\s*\[
|
||||
(?P<key>width|height|tbr|abr|vbr|filesize|fps)
|
||||
\s*(?P<op>%s)(?P<none_inclusive>\s*\?)?\s*
|
||||
(?P<value>[0-9.]+(?:[kKmMgGtTpPeEzZyY]i?[Bb]?)?)
|
||||
\]$
|
||||
''' % '|'.join(map(re.escape, OPERATORS.keys())))
|
||||
m = operator_rex.search(format_spec)
|
||||
if not m:
|
||||
raise ValueError('Invalid format specification %r' % format_spec)
|
||||
|
||||
try:
|
||||
comparison_value = int(m.group('value'))
|
||||
except ValueError:
|
||||
comparison_value = parse_filesize(m.group('value'))
|
||||
if comparison_value is None:
|
||||
comparison_value = parse_filesize(m.group('value') + 'B')
|
||||
if comparison_value is None:
|
||||
raise ValueError(
|
||||
'Invalid value %r in format specification %r' % (
|
||||
m.group('value'), format_spec))
|
||||
op = OPERATORS[m.group('op')]
|
||||
|
||||
def _filter(f):
|
||||
actual_value = f.get(m.group('key'))
|
||||
if actual_value is None:
|
||||
return m.group('none_inclusive')
|
||||
return op(actual_value, comparison_value)
|
||||
new_formats = [f for f in available_formats if _filter(f)]
|
||||
|
||||
new_format_spec = format_spec[:-len(m.group(0))]
|
||||
if not new_format_spec:
|
||||
new_format_spec = 'best'
|
||||
|
||||
return (new_format_spec, new_formats)
|
||||
|
||||
def select_format(self, format_spec, available_formats):
|
||||
while format_spec.endswith(']'):
|
||||
format_spec, available_formats = self._apply_format_filter(
|
||||
format_spec, available_formats)
|
||||
if not available_formats:
|
||||
return None
|
||||
|
||||
if format_spec == 'best' or format_spec is None:
|
||||
return available_formats[-1]
|
||||
elif format_spec == 'worst':
|
||||
@ -790,7 +896,7 @@ class YoutubeDL(object):
|
||||
if video_formats:
|
||||
return video_formats[0]
|
||||
else:
|
||||
extensions = ['mp4', 'flv', 'webm', '3gp', 'm4a']
|
||||
extensions = ['mp4', 'flv', 'webm', '3gp', 'm4a', 'mp3', 'ogg', 'aac', 'wav']
|
||||
if format_spec in extensions:
|
||||
filter_f = lambda f: f['ext'] == format_spec
|
||||
else:
|
||||
@ -800,6 +906,42 @@ class YoutubeDL(object):
|
||||
return matches[-1]
|
||||
return None
|
||||
|
||||
def _calc_headers(self, info_dict):
|
||||
res = std_headers.copy()
|
||||
|
||||
add_headers = info_dict.get('http_headers')
|
||||
if add_headers:
|
||||
res.update(add_headers)
|
||||
|
||||
cookies = self._calc_cookies(info_dict)
|
||||
if cookies:
|
||||
res['Cookie'] = cookies
|
||||
|
||||
return res
|
||||
|
||||
def _calc_cookies(self, info_dict):
|
||||
class _PseudoRequest(object):
|
||||
def __init__(self, url):
|
||||
self.url = url
|
||||
self.headers = {}
|
||||
self.unverifiable = False
|
||||
|
||||
def add_unredirected_header(self, k, v):
|
||||
self.headers[k] = v
|
||||
|
||||
def get_full_url(self):
|
||||
return self.url
|
||||
|
||||
def is_unverifiable(self):
|
||||
return self.unverifiable
|
||||
|
||||
def has_header(self, h):
|
||||
return h in self.headers
|
||||
|
||||
pr = _PseudoRequest(info_dict['url'])
|
||||
self.cookiejar.add_cookie_header(pr)
|
||||
return pr.headers.get('Cookie')
|
||||
|
||||
def process_video_result(self, info_dict, download=True):
|
||||
assert info_dict.get('_type', 'video') == 'video'
|
||||
|
||||
@ -814,9 +956,14 @@ class YoutubeDL(object):
|
||||
info_dict['playlist_index'] = None
|
||||
|
||||
thumbnails = info_dict.get('thumbnails')
|
||||
if thumbnails is None:
|
||||
thumbnail = info_dict.get('thumbnail')
|
||||
if thumbnail:
|
||||
info_dict['thumbnails'] = thumbnails = [{'url': thumbnail}]
|
||||
if thumbnails:
|
||||
thumbnails.sort(key=lambda t: (
|
||||
t.get('width'), t.get('height'), t.get('url')))
|
||||
t.get('preference'), t.get('width'), t.get('height'),
|
||||
t.get('id'), t.get('url')))
|
||||
for t in thumbnails:
|
||||
if 'width' in t and 'height' in t:
|
||||
t['resolution'] = '%dx%d' % (t['width'], t['height'])
|
||||
@ -868,6 +1015,11 @@ class YoutubeDL(object):
|
||||
# Automatically determine file extension if missing
|
||||
if 'ext' not in format:
|
||||
format['ext'] = determine_ext(format['url']).lower()
|
||||
# Add HTTP headers, so that external programs can use them from the
|
||||
# json output
|
||||
full_format_info = info_dict.copy()
|
||||
full_format_info.update(format)
|
||||
format['http_headers'] = self._calc_headers(full_format_info)
|
||||
|
||||
format_limit = self.params.get('format_limit', None)
|
||||
if format_limit:
|
||||
@ -883,9 +1035,12 @@ class YoutubeDL(object):
|
||||
# element in the 'formats' field in info_dict is info_dict itself,
|
||||
# wich can't be exported to json
|
||||
info_dict['formats'] = formats
|
||||
if self.params.get('listformats', None):
|
||||
if self.params.get('listformats'):
|
||||
self.list_formats(info_dict)
|
||||
return
|
||||
if self.params.get('list_thumbnails'):
|
||||
self.list_thumbnails(info_dict)
|
||||
return
|
||||
|
||||
req_format = self.params.get('format')
|
||||
if req_format is None:
|
||||
@ -913,10 +1068,25 @@ class YoutubeDL(object):
|
||||
'contain the video, try using '
|
||||
'"-f %s+%s"' % (format_2, format_1))
|
||||
return
|
||||
output_ext = (
|
||||
formats_info[0]['ext']
|
||||
if self.params.get('merge_output_format') is None
|
||||
else self.params['merge_output_format'])
|
||||
selected_format = {
|
||||
'requested_formats': formats_info,
|
||||
'format': rf,
|
||||
'ext': formats_info[0]['ext'],
|
||||
'format_id': '%s+%s' % (formats_info[0].get('format_id'),
|
||||
formats_info[1].get('format_id')),
|
||||
'width': formats_info[0].get('width'),
|
||||
'height': formats_info[0].get('height'),
|
||||
'resolution': formats_info[0].get('resolution'),
|
||||
'fps': formats_info[0].get('fps'),
|
||||
'vcodec': formats_info[0].get('vcodec'),
|
||||
'vbr': formats_info[0].get('vbr'),
|
||||
'stretched_ratio': formats_info[0].get('stretched_ratio'),
|
||||
'acodec': formats_info[1].get('acodec'),
|
||||
'abr': formats_info[1].get('abr'),
|
||||
'ext': output_ext,
|
||||
}
|
||||
else:
|
||||
selected_format = None
|
||||
@ -967,7 +1137,7 @@ class YoutubeDL(object):
|
||||
|
||||
self._num_downloads += 1
|
||||
|
||||
filename = self.prepare_filename(info_dict)
|
||||
info_dict['_filename'] = filename = self.prepare_filename(info_dict)
|
||||
|
||||
# Forced printings
|
||||
if self.params.get('forcetitle', False):
|
||||
@ -992,10 +1162,7 @@ class YoutubeDL(object):
|
||||
if self.params.get('forceformat', False):
|
||||
self.to_stdout(info_dict['format'])
|
||||
if self.params.get('forcejson', False):
|
||||
info_dict['_filename'] = filename
|
||||
self.to_stdout(json.dumps(info_dict))
|
||||
if self.params.get('dump_single_json', False):
|
||||
info_dict['_filename'] = filename
|
||||
|
||||
# Do nothing else if in simulate mode
|
||||
if self.params.get('simulate', False):
|
||||
@ -1078,72 +1245,90 @@ class YoutubeDL(object):
|
||||
self.report_error('Cannot write metadata to JSON file ' + infofn)
|
||||
return
|
||||
|
||||
if self.params.get('writethumbnail', False):
|
||||
if info_dict.get('thumbnail') is not None:
|
||||
thumb_format = determine_ext(info_dict['thumbnail'], 'jpg')
|
||||
thumb_filename = os.path.splitext(filename)[0] + '.' + thumb_format
|
||||
if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(thumb_filename)):
|
||||
self.to_screen('[%s] %s: Thumbnail is already present' %
|
||||
(info_dict['extractor'], info_dict['id']))
|
||||
else:
|
||||
self.to_screen('[%s] %s: Downloading thumbnail ...' %
|
||||
(info_dict['extractor'], info_dict['id']))
|
||||
try:
|
||||
uf = self.urlopen(info_dict['thumbnail'])
|
||||
with open(thumb_filename, 'wb') as thumbf:
|
||||
shutil.copyfileobj(uf, thumbf)
|
||||
self.to_screen('[%s] %s: Writing thumbnail to: %s' %
|
||||
(info_dict['extractor'], info_dict['id'], thumb_filename))
|
||||
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
|
||||
self.report_warning('Unable to download thumbnail "%s": %s' %
|
||||
(info_dict['thumbnail'], compat_str(err)))
|
||||
self._write_thumbnails(info_dict, filename)
|
||||
|
||||
if not self.params.get('skip_download', False):
|
||||
if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(filename)):
|
||||
success = True
|
||||
else:
|
||||
try:
|
||||
def dl(name, info):
|
||||
fd = get_suitable_downloader(info)(self, self.params)
|
||||
for ph in self._progress_hooks:
|
||||
fd.add_progress_hook(ph)
|
||||
if self.params.get('verbose'):
|
||||
self.to_stdout('[debug] Invoking downloader on %r' % info.get('url'))
|
||||
return fd.download(name, info)
|
||||
if info_dict.get('requested_formats') is not None:
|
||||
downloaded = []
|
||||
success = True
|
||||
merger = FFmpegMergerPP(self, not self.params.get('keepvideo'))
|
||||
if not merger._executable:
|
||||
postprocessors = []
|
||||
self.report_warning('You have requested multiple '
|
||||
'formats but ffmpeg or avconv are not installed.'
|
||||
' The formats won\'t be merged')
|
||||
else:
|
||||
postprocessors = [merger]
|
||||
for f in info_dict['requested_formats']:
|
||||
new_info = dict(info_dict)
|
||||
new_info.update(f)
|
||||
fname = self.prepare_filename(new_info)
|
||||
fname = prepend_extension(fname, 'f%s' % f['format_id'])
|
||||
downloaded.append(fname)
|
||||
partial_success = dl(fname, new_info)
|
||||
success = success and partial_success
|
||||
info_dict['__postprocessors'] = postprocessors
|
||||
info_dict['__files_to_merge'] = downloaded
|
||||
try:
|
||||
def dl(name, info):
|
||||
fd = get_suitable_downloader(info, self.params)(self, self.params)
|
||||
for ph in self._progress_hooks:
|
||||
fd.add_progress_hook(ph)
|
||||
if self.params.get('verbose'):
|
||||
self.to_stdout('[debug] Invoking downloader on %r' % info.get('url'))
|
||||
return fd.download(name, info)
|
||||
|
||||
if info_dict.get('requested_formats') is not None:
|
||||
downloaded = []
|
||||
success = True
|
||||
merger = FFmpegMergerPP(self, not self.params.get('keepvideo'))
|
||||
if not merger._executable:
|
||||
postprocessors = []
|
||||
self.report_warning('You have requested multiple '
|
||||
'formats but ffmpeg or avconv are not installed.'
|
||||
' The formats won\'t be merged')
|
||||
else:
|
||||
# Just a single file
|
||||
success = dl(filename, info_dict)
|
||||
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
|
||||
self.report_error('unable to download video data: %s' % str(err))
|
||||
return
|
||||
except (OSError, IOError) as err:
|
||||
raise UnavailableVideoError(err)
|
||||
except (ContentTooShortError, ) as err:
|
||||
self.report_error('content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
|
||||
return
|
||||
postprocessors = [merger]
|
||||
for f in info_dict['requested_formats']:
|
||||
new_info = dict(info_dict)
|
||||
new_info.update(f)
|
||||
fname = self.prepare_filename(new_info)
|
||||
fname = prepend_extension(fname, 'f%s' % f['format_id'])
|
||||
downloaded.append(fname)
|
||||
partial_success = dl(fname, new_info)
|
||||
success = success and partial_success
|
||||
info_dict['__postprocessors'] = postprocessors
|
||||
info_dict['__files_to_merge'] = downloaded
|
||||
else:
|
||||
# Just a single file
|
||||
success = dl(filename, info_dict)
|
||||
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
|
||||
self.report_error('unable to download video data: %s' % str(err))
|
||||
return
|
||||
except (OSError, IOError) as err:
|
||||
raise UnavailableVideoError(err)
|
||||
except (ContentTooShortError, ) as err:
|
||||
self.report_error('content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
|
||||
return
|
||||
|
||||
if success:
|
||||
# Fixup content
|
||||
fixup_policy = self.params.get('fixup')
|
||||
if fixup_policy is None:
|
||||
fixup_policy = 'detect_or_warn'
|
||||
|
||||
stretched_ratio = info_dict.get('stretched_ratio')
|
||||
if stretched_ratio is not None and stretched_ratio != 1:
|
||||
if fixup_policy == 'warn':
|
||||
self.report_warning('%s: Non-uniform pixel ratio (%s)' % (
|
||||
info_dict['id'], stretched_ratio))
|
||||
elif fixup_policy == 'detect_or_warn':
|
||||
stretched_pp = FFmpegFixupStretchedPP(self)
|
||||
if stretched_pp.available:
|
||||
info_dict.setdefault('__postprocessors', [])
|
||||
info_dict['__postprocessors'].append(stretched_pp)
|
||||
else:
|
||||
self.report_warning(
|
||||
'%s: Non-uniform pixel ratio (%s). Install ffmpeg or avconv to fix this automatically.' % (
|
||||
info_dict['id'], stretched_ratio))
|
||||
else:
|
||||
assert fixup_policy in ('ignore', 'never')
|
||||
|
||||
if info_dict.get('requested_formats') is None and info_dict.get('container') == 'm4a_dash':
|
||||
if fixup_policy == 'warn':
|
||||
self.report_warning('%s: writing DASH m4a. Only some players support this container.' % (
|
||||
info_dict['id']))
|
||||
elif fixup_policy == 'detect_or_warn':
|
||||
fixup_pp = FFmpegFixupM4aPP(self)
|
||||
if fixup_pp.available:
|
||||
info_dict.setdefault('__postprocessors', [])
|
||||
info_dict['__postprocessors'].append(fixup_pp)
|
||||
else:
|
||||
self.report_warning(
|
||||
'%s: writing DASH m4a. Only some players support this container. Install ffmpeg or avconv to fix this automatically.' % (
|
||||
info_dict['id']))
|
||||
else:
|
||||
assert fixup_policy in ('ignore', 'never')
|
||||
|
||||
try:
|
||||
self.post_process(filename, info_dict)
|
||||
except (PostProcessingError) as err:
|
||||
@ -1192,14 +1377,15 @@ class YoutubeDL(object):
|
||||
"""Run all the postprocessors on the given file."""
|
||||
info = dict(ie_info)
|
||||
info['filepath'] = filename
|
||||
keep_video = None
|
||||
pps_chain = []
|
||||
if ie_info.get('__postprocessors') is not None:
|
||||
pps_chain.extend(ie_info['__postprocessors'])
|
||||
pps_chain.extend(self._pps)
|
||||
for pp in pps_chain:
|
||||
keep_video = None
|
||||
old_filename = info['filepath']
|
||||
try:
|
||||
keep_video_wish, new_info = pp.run(info)
|
||||
keep_video_wish, info = pp.run(info)
|
||||
if keep_video_wish is not None:
|
||||
if keep_video_wish:
|
||||
keep_video = keep_video_wish
|
||||
@ -1208,12 +1394,12 @@ class YoutubeDL(object):
|
||||
keep_video = keep_video_wish
|
||||
except PostProcessingError as e:
|
||||
self.report_error(e.msg)
|
||||
if keep_video is False and not self.params.get('keepvideo', False):
|
||||
try:
|
||||
self.to_screen('Deleting original file %s (pass -k to keep)' % filename)
|
||||
os.remove(encodeFilename(filename))
|
||||
except (IOError, OSError):
|
||||
self.report_warning('Unable to remove downloaded video file')
|
||||
if keep_video is False and not self.params.get('keepvideo', False):
|
||||
try:
|
||||
self.to_screen('Deleting original file %s (pass -k to keep)' % old_filename)
|
||||
os.remove(encodeFilename(old_filename))
|
||||
except (IOError, OSError):
|
||||
self.report_warning('Unable to remove downloaded video file')
|
||||
|
||||
def _make_archive_id(self, info_dict):
|
||||
# Future-proof against any change in case
|
||||
@ -1333,7 +1519,9 @@ class YoutubeDL(object):
|
||||
formats = info_dict.get('formats', [info_dict])
|
||||
idlen = max(len('format code'),
|
||||
max(len(f['format_id']) for f in formats))
|
||||
formats_s = [line(f, idlen) for f in formats]
|
||||
formats_s = [
|
||||
line(f, idlen) for f in formats
|
||||
if f.get('preference') is None or f['preference'] >= -1000]
|
||||
if len(formats) > 1:
|
||||
formats_s[0] += (' ' if self._format_note(formats[0]) else '') + '(worst)'
|
||||
formats_s[-1] += (' ' if self._format_note(formats[-1]) else '') + '(best)'
|
||||
@ -1341,8 +1529,26 @@ class YoutubeDL(object):
|
||||
header_line = line({
|
||||
'format_id': 'format code', 'ext': 'extension',
|
||||
'resolution': 'resolution', 'format_note': 'note'}, idlen=idlen)
|
||||
self.to_screen('[info] Available formats for %s:\n%s\n%s' %
|
||||
(info_dict['id'], header_line, '\n'.join(formats_s)))
|
||||
self.to_screen(
|
||||
'[info] Available formats for %s:\n%s\n%s' %
|
||||
(info_dict['id'], header_line, '\n'.join(formats_s)))
|
||||
|
||||
def list_thumbnails(self, info_dict):
|
||||
thumbnails = info_dict.get('thumbnails')
|
||||
if not thumbnails:
|
||||
tn_url = info_dict.get('thumbnail')
|
||||
if tn_url:
|
||||
thumbnails = [{'id': '0', 'url': tn_url}]
|
||||
else:
|
||||
self.to_screen(
|
||||
'[info] No thumbnails present for %s' % info_dict['id'])
|
||||
return
|
||||
|
||||
self.to_screen(
|
||||
'[info] Thumbnails for %s:' % info_dict['id'])
|
||||
self.to_screen(render_table(
|
||||
['ID', 'width', 'height', 'URL'],
|
||||
[[t['id'], t.get('width', 'unknown'), t.get('height', 'unknown'), t['url']] for t in thumbnails]))
|
||||
|
||||
def urlopen(self, req):
|
||||
""" Start an HTTP download """
|
||||
@ -1353,7 +1559,7 @@ class YoutubeDL(object):
|
||||
# urllib chokes on URLs with non-ASCII characters (see http://bugs.python.org/issue3991)
|
||||
# To work around aforementioned issue we will replace request's original URL with
|
||||
# percent-encoded one
|
||||
req_is_string = isinstance(req, basestring if sys.version_info < (3, 0) else compat_str)
|
||||
req_is_string = isinstance(req, compat_basestring)
|
||||
url = req if req_is_string else req.get_full_url()
|
||||
url_escaped = escape_url(url)
|
||||
|
||||
@ -1422,6 +1628,17 @@ class YoutubeDL(object):
|
||||
proxy_map.update(handler.proxies)
|
||||
self._write_string('[debug] Proxy map: ' + compat_str(proxy_map) + '\n')
|
||||
|
||||
if self.params.get('call_home', False):
|
||||
ipaddr = self.urlopen('https://yt-dl.org/ip').read().decode('utf-8')
|
||||
self._write_string('[debug] Public IP address: %s\n' % ipaddr)
|
||||
latest_version = self.urlopen(
|
||||
'https://yt-dl.org/latest/version').read().decode('utf-8')
|
||||
if version_tuple(latest_version) > version_tuple(__version__):
|
||||
self.report_warning(
|
||||
'You are using an outdated version (newest version: %s)! '
|
||||
'See https://yt-dl.org/update if you need help updating.' %
|
||||
latest_version)
|
||||
|
||||
def _setup_opener(self):
|
||||
timeout_val = self.params.get('socket_timeout')
|
||||
self._socket_timeout = 600 if timeout_val is None else float(timeout_val)
|
||||
@ -1452,9 +1669,8 @@ class YoutubeDL(object):
|
||||
proxy_handler = compat_urllib_request.ProxyHandler(proxies)
|
||||
|
||||
debuglevel = 1 if self.params.get('debug_printtraffic') else 0
|
||||
https_handler = make_HTTPS_handler(
|
||||
self.params.get('nocheckcertificate', False), debuglevel=debuglevel)
|
||||
ydlh = YoutubeDLHandler(debuglevel=debuglevel)
|
||||
https_handler = make_HTTPS_handler(self.params, debuglevel=debuglevel)
|
||||
ydlh = YoutubeDLHandler(self.params, debuglevel=debuglevel)
|
||||
opener = compat_urllib_request.build_opener(
|
||||
https_handler, proxy_handler, cookie_processor, ydlh)
|
||||
# Delete the default user-agent header, which would otherwise apply in
|
||||
@ -1478,3 +1694,39 @@ class YoutubeDL(object):
|
||||
if encoding is None:
|
||||
encoding = preferredencoding()
|
||||
return encoding
|
||||
|
||||
def _write_thumbnails(self, info_dict, filename):
|
||||
if self.params.get('writethumbnail', False):
|
||||
thumbnails = info_dict.get('thumbnails')
|
||||
if thumbnails:
|
||||
thumbnails = [thumbnails[-1]]
|
||||
elif self.params.get('write_all_thumbnails', False):
|
||||
thumbnails = info_dict.get('thumbnails')
|
||||
else:
|
||||
return
|
||||
|
||||
if not thumbnails:
|
||||
# No thumbnails present, so return immediately
|
||||
return
|
||||
|
||||
for t in thumbnails:
|
||||
thumb_ext = determine_ext(t['url'], 'jpg')
|
||||
suffix = '_%s' % t['id'] if len(thumbnails) > 1 else ''
|
||||
thumb_display_id = '%s ' % t['id'] if len(thumbnails) > 1 else ''
|
||||
thumb_filename = os.path.splitext(filename)[0] + suffix + '.' + thumb_ext
|
||||
|
||||
if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(thumb_filename)):
|
||||
self.to_screen('[%s] %s: Thumbnail %sis already present' %
|
||||
(info_dict['extractor'], info_dict['id'], thumb_display_id))
|
||||
else:
|
||||
self.to_screen('[%s] %s: Downloading thumbnail %s...' %
|
||||
(info_dict['extractor'], info_dict['id'], thumb_display_id))
|
||||
try:
|
||||
uf = self.urlopen(t['url'])
|
||||
with open(thumb_filename, 'wb') as thumbf:
|
||||
shutil.copyfileobj(uf, thumbf)
|
||||
self.to_screen('[%s] %s: Writing thumbnail %sto: %s' %
|
||||
(info_dict['extractor'], info_dict['id'], thumb_display_id, thumb_filename))
|
||||
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
|
||||
self.report_warning('Unable to download thumbnail "%s": %s' %
|
||||
(t['url'], compat_str(err)))
|
||||
|
@ -38,7 +38,7 @@ from .update import update_self
|
||||
from .downloader import (
|
||||
FileDownloader,
|
||||
)
|
||||
from .extractor import gen_extractors
|
||||
from .extractor import gen_extractors, list_extractors
|
||||
from .YoutubeDL import YoutubeDL
|
||||
|
||||
|
||||
@ -95,17 +95,15 @@ def _real_main(argv=None):
|
||||
_enc = preferredencoding()
|
||||
all_urls = [url.decode(_enc, 'ignore') if isinstance(url, bytes) else url for url in all_urls]
|
||||
|
||||
extractors = gen_extractors()
|
||||
|
||||
if opts.list_extractors:
|
||||
for ie in sorted(extractors, key=lambda ie: ie.IE_NAME.lower()):
|
||||
for ie in list_extractors(opts.age_limit):
|
||||
compat_print(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else ''))
|
||||
matchedUrls = [url for url in all_urls if ie.suitable(url)]
|
||||
for mu in matchedUrls:
|
||||
compat_print(' ' + mu)
|
||||
sys.exit(0)
|
||||
if opts.list_extractor_descriptions:
|
||||
for ie in sorted(extractors, key=lambda ie: ie.IE_NAME.lower()):
|
||||
for ie in list_extractors(opts.age_limit):
|
||||
if not ie._WORKING:
|
||||
continue
|
||||
desc = getattr(ie, 'IE_DESC', ie.IE_NAME)
|
||||
@ -145,10 +143,13 @@ def _real_main(argv=None):
|
||||
parser.error('invalid max_filesize specified')
|
||||
opts.max_filesize = numeric_limit
|
||||
if opts.retries is not None:
|
||||
try:
|
||||
opts.retries = int(opts.retries)
|
||||
except (TypeError, ValueError):
|
||||
parser.error('invalid retry count specified')
|
||||
if opts.retries in ('inf', 'infinite'):
|
||||
opts_retries = float('inf')
|
||||
else:
|
||||
try:
|
||||
opts_retries = int(opts.retries)
|
||||
except (TypeError, ValueError):
|
||||
parser.error('invalid retry count specified')
|
||||
if opts.buffersize is not None:
|
||||
numeric_buffersize = FileDownloader.parse_bytes(opts.buffersize)
|
||||
if numeric_buffersize is None:
|
||||
@ -168,6 +169,7 @@ def _real_main(argv=None):
|
||||
if opts.recodevideo is not None:
|
||||
if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv']:
|
||||
parser.error('invalid video recode format specified')
|
||||
|
||||
if opts.date is not None:
|
||||
date = DateRange.day(opts.date)
|
||||
else:
|
||||
@ -199,7 +201,8 @@ def _real_main(argv=None):
|
||||
' file! Use "{0}.%(ext)s" instead of "{0}" as the output'
|
||||
' template'.format(outtmpl))
|
||||
|
||||
any_printing = opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat or opts.getduration or opts.dumpjson or opts.dump_single_json
|
||||
any_getting = opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat or opts.getduration or opts.dumpjson or opts.dump_single_json
|
||||
any_printing = opts.print_json
|
||||
download_archive_fn = compat_expanduser(opts.download_archive) if opts.download_archive is not None else opts.download_archive
|
||||
|
||||
# PostProcessors
|
||||
@ -238,6 +241,12 @@ def _real_main(argv=None):
|
||||
'verboseOutput': opts.verbose,
|
||||
'exec_cmd': opts.exec_cmd,
|
||||
})
|
||||
if opts.xattr_set_filesize:
|
||||
try:
|
||||
import xattr
|
||||
xattr # Confuse flake8
|
||||
except ImportError:
|
||||
parser.error('setting filesize xattr requested but python-xattr is not available')
|
||||
|
||||
ydl_opts = {
|
||||
'usenetrc': opts.usenetrc,
|
||||
@ -245,7 +254,7 @@ def _real_main(argv=None):
|
||||
'password': opts.password,
|
||||
'twofactor': opts.twofactor,
|
||||
'videopassword': opts.videopassword,
|
||||
'quiet': (opts.quiet or any_printing),
|
||||
'quiet': (opts.quiet or any_getting or any_printing),
|
||||
'no_warnings': opts.no_warnings,
|
||||
'forceurl': opts.geturl,
|
||||
'forcetitle': opts.gettitle,
|
||||
@ -255,9 +264,9 @@ def _real_main(argv=None):
|
||||
'forceduration': opts.getduration,
|
||||
'forcefilename': opts.getfilename,
|
||||
'forceformat': opts.getformat,
|
||||
'forcejson': opts.dumpjson,
|
||||
'forcejson': opts.dumpjson or opts.print_json,
|
||||
'dump_single_json': opts.dump_single_json,
|
||||
'simulate': opts.simulate or any_printing,
|
||||
'simulate': opts.simulate or any_getting,
|
||||
'skip_download': opts.skip_download,
|
||||
'format': opts.format,
|
||||
'format_limit': opts.format_limit,
|
||||
@ -268,7 +277,7 @@ def _real_main(argv=None):
|
||||
'ignoreerrors': opts.ignoreerrors,
|
||||
'ratelimit': opts.ratelimit,
|
||||
'nooverwrites': opts.nooverwrites,
|
||||
'retries': opts.retries,
|
||||
'retries': opts_retries,
|
||||
'buffersize': opts.buffersize,
|
||||
'noresizebuffer': opts.noresizebuffer,
|
||||
'continuedl': opts.continue_dl,
|
||||
@ -286,6 +295,7 @@ def _real_main(argv=None):
|
||||
'writeannotations': opts.writeannotations,
|
||||
'writeinfojson': opts.writeinfojson,
|
||||
'writethumbnail': opts.writethumbnail,
|
||||
'write_all_thumbnails': opts.write_all_thumbnails,
|
||||
'writesubtitles': opts.writesubtitles,
|
||||
'writeautomaticsub': opts.writeautomaticsub,
|
||||
'allsubtitles': opts.allsubtitles,
|
||||
@ -324,7 +334,16 @@ def _real_main(argv=None):
|
||||
'encoding': opts.encoding,
|
||||
'exec_cmd': opts.exec_cmd,
|
||||
'extract_flat': opts.extract_flat,
|
||||
'merge_output_format': opts.merge_output_format,
|
||||
'postprocessors': postprocessors,
|
||||
'fixup': opts.fixup,
|
||||
'source_address': opts.source_address,
|
||||
'call_home': opts.call_home,
|
||||
'sleep_interval': opts.sleep_interval,
|
||||
'external_downloader': opts.external_downloader,
|
||||
'list_thumbnails': opts.list_thumbnails,
|
||||
'playlist_items': opts.playlist_items,
|
||||
'xattr_set_filesize': opts.xattr_set_filesize,
|
||||
}
|
||||
|
||||
with YoutubeDL(ydl_opts) as ydl:
|
||||
@ -342,7 +361,9 @@ def _real_main(argv=None):
|
||||
sys.exit()
|
||||
|
||||
ydl.warn_if_short_id(sys.argv[1:] if argv is None else argv)
|
||||
parser.error('you must provide at least one URL')
|
||||
parser.error(
|
||||
'You must provide at least one URL.\n'
|
||||
'Type youtube-dl --help to see a list of all options.')
|
||||
|
||||
try:
|
||||
if opts.load_info_filename is not None:
|
||||
@ -365,3 +386,5 @@ def main(argv=None):
|
||||
sys.exit('ERROR: fixed output name but more than one file to download')
|
||||
except KeyboardInterrupt:
|
||||
sys.exit('\nERROR: Interrupted by user')
|
||||
|
||||
__all__ = ['main', 'YoutubeDL', 'gen_extractors', 'list_extractors']
|
||||
|
@ -4,6 +4,7 @@ import getpass
|
||||
import optparse
|
||||
import os
|
||||
import re
|
||||
import socket
|
||||
import subprocess
|
||||
import sys
|
||||
|
||||
@ -70,6 +71,11 @@ try:
|
||||
except ImportError:
|
||||
compat_subprocess_get_DEVNULL = lambda: open(os.path.devnull, 'w')
|
||||
|
||||
try:
|
||||
import http.server as compat_http_server
|
||||
except ImportError:
|
||||
import BaseHTTPServer as compat_http_server
|
||||
|
||||
try:
|
||||
from urllib.parse import unquote as compat_urllib_parse_unquote
|
||||
except ImportError:
|
||||
@ -108,6 +114,26 @@ except ImportError:
|
||||
string += pct_sequence.decode(encoding, errors)
|
||||
return string
|
||||
|
||||
try:
|
||||
compat_str = unicode # Python 2
|
||||
except NameError:
|
||||
compat_str = str
|
||||
|
||||
try:
|
||||
compat_basestring = basestring # Python 2
|
||||
except NameError:
|
||||
compat_basestring = str
|
||||
|
||||
try:
|
||||
compat_chr = unichr # Python 2
|
||||
except NameError:
|
||||
compat_chr = chr
|
||||
|
||||
try:
|
||||
from xml.etree.ElementTree import ParseError as compat_xml_parse_error
|
||||
except ImportError: # Python 2.6
|
||||
from xml.parsers.expat import ExpatError as compat_xml_parse_error
|
||||
|
||||
|
||||
try:
|
||||
from urllib.parse import parse_qs as compat_parse_qs
|
||||
@ -117,7 +143,7 @@ except ImportError: # Python 2
|
||||
|
||||
def _parse_qsl(qs, keep_blank_values=False, strict_parsing=False,
|
||||
encoding='utf-8', errors='replace'):
|
||||
qs, _coerce_result = qs, unicode
|
||||
qs, _coerce_result = qs, compat_str
|
||||
pairs = [s2 for s1 in qs.split('&') for s2 in s1.split(';')]
|
||||
r = []
|
||||
for name_value in pairs:
|
||||
@ -156,21 +182,6 @@ except ImportError: # Python 2
|
||||
parsed_result[name] = [value]
|
||||
return parsed_result
|
||||
|
||||
try:
|
||||
compat_str = unicode # Python 2
|
||||
except NameError:
|
||||
compat_str = str
|
||||
|
||||
try:
|
||||
compat_chr = unichr # Python 2
|
||||
except NameError:
|
||||
compat_chr = chr
|
||||
|
||||
try:
|
||||
from xml.etree.ElementTree import ParseError as compat_xml_parse_error
|
||||
except ImportError: # Python 2.6
|
||||
from xml.parsers.expat import ExpatError as compat_xml_parse_error
|
||||
|
||||
try:
|
||||
from shlex import quote as shlex_quote
|
||||
except ImportError: # Python < 3.3
|
||||
@ -307,6 +318,32 @@ else:
|
||||
compat_kwargs = lambda kwargs: kwargs
|
||||
|
||||
|
||||
if sys.version_info < (2, 7):
|
||||
def compat_socket_create_connection(address, timeout, source_address=None):
|
||||
host, port = address
|
||||
err = None
|
||||
for res in socket.getaddrinfo(host, port, 0, socket.SOCK_STREAM):
|
||||
af, socktype, proto, canonname, sa = res
|
||||
sock = None
|
||||
try:
|
||||
sock = socket.socket(af, socktype, proto)
|
||||
sock.settimeout(timeout)
|
||||
if source_address:
|
||||
sock.bind(source_address)
|
||||
sock.connect(sa)
|
||||
return sock
|
||||
except socket.error as _:
|
||||
err = _
|
||||
if sock is not None:
|
||||
sock.close()
|
||||
if err is not None:
|
||||
raise err
|
||||
else:
|
||||
raise socket.error("getaddrinfo returns an empty list")
|
||||
else:
|
||||
compat_socket_create_connection = socket.create_connection
|
||||
|
||||
|
||||
# Fix https://github.com/rg3/youtube-dl/issues/4223
|
||||
# See http://bugs.python.org/issue9161 for what is broken
|
||||
def workaround_optparse_bug9161():
|
||||
@ -330,6 +367,7 @@ def workaround_optparse_bug9161():
|
||||
|
||||
__all__ = [
|
||||
'compat_HTTPError',
|
||||
'compat_basestring',
|
||||
'compat_chr',
|
||||
'compat_cookiejar',
|
||||
'compat_expanduser',
|
||||
@ -338,10 +376,12 @@ __all__ = [
|
||||
'compat_html_entities',
|
||||
'compat_html_parser',
|
||||
'compat_http_client',
|
||||
'compat_http_server',
|
||||
'compat_kwargs',
|
||||
'compat_ord',
|
||||
'compat_parse_qs',
|
||||
'compat_print',
|
||||
'compat_socket_create_connection',
|
||||
'compat_str',
|
||||
'compat_subprocess_get_DEVNULL',
|
||||
'compat_urllib_error',
|
||||
|
@ -1,35 +1,41 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import FileDownloader
|
||||
from .external import get_external_downloader
|
||||
from .f4m import F4mFD
|
||||
from .hls import HlsFD
|
||||
from .hls import NativeHlsFD
|
||||
from .http import HttpFD
|
||||
from .mplayer import MplayerFD
|
||||
from .rtmp import RtmpFD
|
||||
from .f4m import F4mFD
|
||||
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
determine_protocol,
|
||||
)
|
||||
|
||||
PROTOCOL_MAP = {
|
||||
'rtmp': RtmpFD,
|
||||
'm3u8_native': NativeHlsFD,
|
||||
'm3u8': HlsFD,
|
||||
'mms': MplayerFD,
|
||||
'rtsp': MplayerFD,
|
||||
'f4m': F4mFD,
|
||||
}
|
||||
|
||||
def get_suitable_downloader(info_dict):
|
||||
|
||||
def get_suitable_downloader(info_dict, params={}):
|
||||
"""Get the downloader class that can handle the info dict."""
|
||||
url = info_dict['url']
|
||||
protocol = info_dict.get('protocol')
|
||||
protocol = determine_protocol(info_dict)
|
||||
info_dict['protocol'] = protocol
|
||||
|
||||
external_downloader = params.get('external_downloader')
|
||||
if external_downloader is not None:
|
||||
ed = get_external_downloader(external_downloader)
|
||||
if ed.supports(info_dict):
|
||||
return ed
|
||||
|
||||
return PROTOCOL_MAP.get(protocol, HttpFD)
|
||||
|
||||
if url.startswith('rtmp'):
|
||||
return RtmpFD
|
||||
if protocol == 'm3u8_native':
|
||||
return NativeHlsFD
|
||||
if (protocol == 'm3u8') or (protocol is None and determine_ext(url) == 'm3u8'):
|
||||
return HlsFD
|
||||
if url.startswith('mms') or url.startswith('rtsp'):
|
||||
return MplayerFD
|
||||
if determine_ext(url) == 'f4m':
|
||||
return F4mFD
|
||||
else:
|
||||
return HttpFD
|
||||
|
||||
__all__ = [
|
||||
'get_suitable_downloader',
|
||||
|
@ -25,21 +25,23 @@ class FileDownloader(object):
|
||||
|
||||
Available options:
|
||||
|
||||
verbose: Print additional info to stdout.
|
||||
quiet: Do not print messages to stdout.
|
||||
ratelimit: Download speed limit, in bytes/sec.
|
||||
retries: Number of times to retry for HTTP error 5xx
|
||||
buffersize: Size of download buffer in bytes.
|
||||
noresizebuffer: Do not automatically resize the download buffer.
|
||||
continuedl: Try to continue downloads if possible.
|
||||
noprogress: Do not print the progress bar.
|
||||
logtostderr: Log messages to stderr instead of stdout.
|
||||
consoletitle: Display progress in console window's titlebar.
|
||||
nopart: Do not use temporary .part files.
|
||||
updatetime: Use the Last-modified header to set output file timestamps.
|
||||
test: Download only first bytes to test the downloader.
|
||||
min_filesize: Skip files smaller than this size
|
||||
max_filesize: Skip files larger than this size
|
||||
verbose: Print additional info to stdout.
|
||||
quiet: Do not print messages to stdout.
|
||||
ratelimit: Download speed limit, in bytes/sec.
|
||||
retries: Number of times to retry for HTTP error 5xx
|
||||
buffersize: Size of download buffer in bytes.
|
||||
noresizebuffer: Do not automatically resize the download buffer.
|
||||
continuedl: Try to continue downloads if possible.
|
||||
noprogress: Do not print the progress bar.
|
||||
logtostderr: Log messages to stderr instead of stdout.
|
||||
consoletitle: Display progress in console window's titlebar.
|
||||
nopart: Do not use temporary .part files.
|
||||
updatetime: Use the Last-modified header to set output file timestamps.
|
||||
test: Download only first bytes to test the downloader.
|
||||
min_filesize: Skip files smaller than this size
|
||||
max_filesize: Skip files larger than this size
|
||||
xattr_set_filesize: Set ytdl.filesize user xattribute with expected size.
|
||||
(experimenatal)
|
||||
|
||||
Subclasses of this one must re-define the real_download method.
|
||||
"""
|
||||
@ -284,8 +286,20 @@ class FileDownloader(object):
|
||||
"""Download to a filename using the info from info_dict
|
||||
Return True on success and False otherwise
|
||||
"""
|
||||
|
||||
nooverwrites_and_exists = (
|
||||
self.params.get('nooverwrites', False)
|
||||
and os.path.exists(encodeFilename(filename))
|
||||
)
|
||||
|
||||
continuedl_and_exists = (
|
||||
self.params.get('continuedl', False)
|
||||
and os.path.isfile(encodeFilename(filename))
|
||||
and not self.params.get('nopart', False)
|
||||
)
|
||||
|
||||
# Check file already present
|
||||
if filename != '-' and self.params.get('continuedl', False) and os.path.isfile(encodeFilename(filename)) and not self.params.get('nopart', False):
|
||||
if filename != '-' and nooverwrites_and_exists or continuedl_and_exists:
|
||||
self.report_file_already_downloaded(filename)
|
||||
self._hook_progress({
|
||||
'filename': filename,
|
||||
@ -294,6 +308,11 @@ class FileDownloader(object):
|
||||
})
|
||||
return True
|
||||
|
||||
sleep_interval = self.params.get('sleep_interval')
|
||||
if sleep_interval:
|
||||
self.to_screen('[download] Sleeping %s seconds...' % sleep_interval)
|
||||
time.sleep(sleep_interval)
|
||||
|
||||
return self.real_download(filename, info_dict)
|
||||
|
||||
def real_download(self, filename, info_dict):
|
||||
@ -308,3 +327,24 @@ class FileDownloader(object):
|
||||
# See YoutubeDl.py (search for progress_hooks) for a description of
|
||||
# this interface
|
||||
self._progress_hooks.append(ph)
|
||||
|
||||
def _debug_cmd(self, args, subprocess_encoding, exe=None):
|
||||
if not self.params.get('verbose', False):
|
||||
return
|
||||
|
||||
if exe is None:
|
||||
exe = os.path.basename(args[0])
|
||||
|
||||
if subprocess_encoding:
|
||||
str_args = [
|
||||
a.decode(subprocess_encoding) if isinstance(a, bytes) else a
|
||||
for a in args]
|
||||
else:
|
||||
str_args = args
|
||||
try:
|
||||
import pipes
|
||||
shell_quote = lambda args: ' '.join(map(pipes.quote, str_args))
|
||||
except ImportError:
|
||||
shell_quote = repr
|
||||
self.to_screen('[debug] %s command line: %s' % (
|
||||
exe, shell_quote(str_args)))
|
||||
|
126
youtube_dl/downloader/external.py
Normal file
126
youtube_dl/downloader/external.py
Normal file
@ -0,0 +1,126 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import os.path
|
||||
import subprocess
|
||||
import sys
|
||||
|
||||
from .common import FileDownloader
|
||||
from ..utils import (
|
||||
encodeFilename,
|
||||
)
|
||||
|
||||
|
||||
class ExternalFD(FileDownloader):
|
||||
def real_download(self, filename, info_dict):
|
||||
self.report_destination(filename)
|
||||
tmpfilename = self.temp_name(filename)
|
||||
|
||||
retval = self._call_downloader(tmpfilename, info_dict)
|
||||
if retval == 0:
|
||||
fsize = os.path.getsize(encodeFilename(tmpfilename))
|
||||
self.to_screen('\r[%s] Downloaded %s bytes' % (self.get_basename(), fsize))
|
||||
self.try_rename(tmpfilename, filename)
|
||||
self._hook_progress({
|
||||
'downloaded_bytes': fsize,
|
||||
'total_bytes': fsize,
|
||||
'filename': filename,
|
||||
'status': 'finished',
|
||||
})
|
||||
return True
|
||||
else:
|
||||
self.to_stderr('\n')
|
||||
self.report_error('%s exited with code %d' % (
|
||||
self.get_basename(), retval))
|
||||
return False
|
||||
|
||||
@classmethod
|
||||
def get_basename(cls):
|
||||
return cls.__name__[:-2].lower()
|
||||
|
||||
@property
|
||||
def exe(self):
|
||||
return self.params.get('external_downloader')
|
||||
|
||||
@classmethod
|
||||
def supports(cls, info_dict):
|
||||
return info_dict['protocol'] in ('http', 'https', 'ftp', 'ftps')
|
||||
|
||||
def _source_address(self, command_option):
|
||||
source_address = self.params.get('source_address')
|
||||
if source_address is None:
|
||||
return []
|
||||
return [command_option, source_address]
|
||||
|
||||
def _call_downloader(self, tmpfilename, info_dict):
|
||||
""" Either overwrite this or implement _make_cmd """
|
||||
cmd = self._make_cmd(tmpfilename, info_dict)
|
||||
|
||||
if sys.platform == 'win32' and sys.version_info < (3, 0):
|
||||
# Windows subprocess module does not actually support Unicode
|
||||
# on Python 2.x
|
||||
# See http://stackoverflow.com/a/9951851/35070
|
||||
subprocess_encoding = sys.getfilesystemencoding()
|
||||
cmd = [a.encode(subprocess_encoding, 'ignore') for a in cmd]
|
||||
else:
|
||||
subprocess_encoding = None
|
||||
self._debug_cmd(cmd, subprocess_encoding)
|
||||
|
||||
p = subprocess.Popen(
|
||||
cmd, stderr=subprocess.PIPE)
|
||||
_, stderr = p.communicate()
|
||||
if p.returncode != 0:
|
||||
self.to_stderr(stderr)
|
||||
return p.returncode
|
||||
|
||||
|
||||
class CurlFD(ExternalFD):
|
||||
def _make_cmd(self, tmpfilename, info_dict):
|
||||
cmd = [self.exe, '-o', tmpfilename]
|
||||
for key, val in info_dict['http_headers'].items():
|
||||
cmd += ['--header', '%s: %s' % (key, val)]
|
||||
cmd += self._source_address('--interface')
|
||||
cmd += ['--', info_dict['url']]
|
||||
return cmd
|
||||
|
||||
|
||||
class WgetFD(ExternalFD):
|
||||
def _make_cmd(self, tmpfilename, info_dict):
|
||||
cmd = [self.exe, '-O', tmpfilename, '-nv', '--no-cookies']
|
||||
for key, val in info_dict['http_headers'].items():
|
||||
cmd += ['--header', '%s: %s' % (key, val)]
|
||||
cmd += self._source_address('--bind-address')
|
||||
cmd += ['--', info_dict['url']]
|
||||
return cmd
|
||||
|
||||
|
||||
class Aria2cFD(ExternalFD):
|
||||
def _make_cmd(self, tmpfilename, info_dict):
|
||||
cmd = [
|
||||
self.exe, '-c',
|
||||
'--min-split-size', '1M', '--max-connection-per-server', '4']
|
||||
dn = os.path.dirname(tmpfilename)
|
||||
if dn:
|
||||
cmd += ['--dir', dn]
|
||||
cmd += ['--out', os.path.basename(tmpfilename)]
|
||||
for key, val in info_dict['http_headers'].items():
|
||||
cmd += ['--header', '%s: %s' % (key, val)]
|
||||
cmd += self._source_address('--interface')
|
||||
cmd += ['--', info_dict['url']]
|
||||
return cmd
|
||||
|
||||
_BY_NAME = dict(
|
||||
(klass.get_basename(), klass)
|
||||
for name, klass in globals().items()
|
||||
if name.endswith('FD') and name != 'ExternalFD'
|
||||
)
|
||||
|
||||
|
||||
def list_external_downloaders():
|
||||
return sorted(_BY_NAME.keys())
|
||||
|
||||
|
||||
def get_external_downloader(external_downloader):
|
||||
""" Given the name of the executable, see whether we support the given
|
||||
downloader . """
|
||||
bn = os.path.basename(external_downloader)
|
||||
return _BY_NAME[bn]
|
@ -177,34 +177,43 @@ def build_fragments_list(boot_info):
|
||||
""" Return a list of (segment, fragment) for each fragment in the video """
|
||||
res = []
|
||||
segment_run_table = boot_info['segments'][0]
|
||||
# I've only found videos with one segment
|
||||
segment_run_entry = segment_run_table['segment_run'][0]
|
||||
n_frags = segment_run_entry[1]
|
||||
fragment_run_entry_table = boot_info['fragments'][0]['fragments']
|
||||
first_frag_number = fragment_run_entry_table[0]['first']
|
||||
for (i, frag_number) in zip(range(1, n_frags + 1), itertools.count(first_frag_number)):
|
||||
res.append((1, frag_number))
|
||||
fragments_counter = itertools.count(first_frag_number)
|
||||
for segment, fragments_count in segment_run_table['segment_run']:
|
||||
for _ in range(fragments_count):
|
||||
res.append((segment, next(fragments_counter)))
|
||||
return res
|
||||
|
||||
|
||||
def write_flv_header(stream, metadata):
|
||||
"""Writes the FLV header and the metadata to stream"""
|
||||
def write_unsigned_int(stream, val):
|
||||
stream.write(struct_pack('!I', val))
|
||||
|
||||
|
||||
def write_unsigned_int_24(stream, val):
|
||||
stream.write(struct_pack('!I', val)[1:])
|
||||
|
||||
|
||||
def write_flv_header(stream):
|
||||
"""Writes the FLV header to stream"""
|
||||
# FLV header
|
||||
stream.write(b'FLV\x01')
|
||||
stream.write(b'\x05')
|
||||
stream.write(b'\x00\x00\x00\x09')
|
||||
# FLV File body
|
||||
stream.write(b'\x00\x00\x00\x00')
|
||||
# FLVTAG
|
||||
# Script data
|
||||
stream.write(b'\x12')
|
||||
# Size of the metadata with 3 bytes
|
||||
stream.write(struct_pack('!L', len(metadata))[1:])
|
||||
stream.write(b'\x00\x00\x00\x00\x00\x00\x00')
|
||||
stream.write(metadata)
|
||||
# Magic numbers extracted from the output files produced by AdobeHDS.php
|
||||
# (https://github.com/K-S-V/Scripts)
|
||||
stream.write(b'\x00\x00\x01\x73')
|
||||
|
||||
|
||||
def write_metadata_tag(stream, metadata):
|
||||
"""Writes optional metadata tag to stream"""
|
||||
SCRIPT_TAG = b'\x12'
|
||||
FLV_TAG_HEADER_LEN = 11
|
||||
|
||||
if metadata:
|
||||
stream.write(SCRIPT_TAG)
|
||||
write_unsigned_int_24(stream, len(metadata))
|
||||
stream.write(b'\x00\x00\x00\x00\x00\x00\x00')
|
||||
stream.write(metadata)
|
||||
write_unsigned_int(stream, FLV_TAG_HEADER_LEN + len(metadata))
|
||||
|
||||
|
||||
def _add_ns(prop):
|
||||
@ -221,6 +230,23 @@ class F4mFD(FileDownloader):
|
||||
A downloader for f4m manifests or AdobeHDS.
|
||||
"""
|
||||
|
||||
def _get_unencrypted_media(self, doc):
|
||||
media = doc.findall(_add_ns('media'))
|
||||
if not media:
|
||||
self.report_error('No media found')
|
||||
for e in (doc.findall(_add_ns('drmAdditionalHeader')) +
|
||||
doc.findall(_add_ns('drmAdditionalHeaderSet'))):
|
||||
# If id attribute is missing it's valid for all media nodes
|
||||
# without drmAdditionalHeaderId or drmAdditionalHeaderSetId attribute
|
||||
if 'id' not in e.attrib:
|
||||
self.report_error('Missing ID in f4m DRM')
|
||||
media = list(filter(lambda e: 'drmAdditionalHeaderId' not in e.attrib and
|
||||
'drmAdditionalHeaderSetId' not in e.attrib,
|
||||
media))
|
||||
if not media:
|
||||
self.report_error('Unsupported DRM')
|
||||
return media
|
||||
|
||||
def real_download(self, filename, info_dict):
|
||||
man_url = info_dict['url']
|
||||
requested_bitrate = info_dict.get('tbr')
|
||||
@ -239,7 +265,8 @@ class F4mFD(FileDownloader):
|
||||
)
|
||||
|
||||
doc = etree.fromstring(manifest)
|
||||
formats = [(int(f.attrib.get('bitrate', -1)), f) for f in doc.findall(_add_ns('media'))]
|
||||
formats = [(int(f.attrib.get('bitrate', -1)), f)
|
||||
for f in self._get_unencrypted_media(doc)]
|
||||
if requested_bitrate is None:
|
||||
# get the best format
|
||||
formats = sorted(formats, key=lambda f: f[0])
|
||||
@ -256,7 +283,11 @@ class F4mFD(FileDownloader):
|
||||
bootstrap = self.ydl.urlopen(bootstrap_url).read()
|
||||
else:
|
||||
bootstrap = base64.b64decode(bootstrap_node.text)
|
||||
metadata = base64.b64decode(media.find(_add_ns('metadata')).text)
|
||||
metadata_node = media.find(_add_ns('metadata'))
|
||||
if metadata_node is not None:
|
||||
metadata = base64.b64decode(metadata_node.text)
|
||||
else:
|
||||
metadata = None
|
||||
boot_info = read_bootstrap_info(bootstrap)
|
||||
|
||||
fragments_list = build_fragments_list(boot_info)
|
||||
@ -269,7 +300,8 @@ class F4mFD(FileDownloader):
|
||||
|
||||
tmpfilename = self.temp_name(filename)
|
||||
(dest_stream, tmpfilename) = sanitize_open(tmpfilename, 'wb')
|
||||
write_flv_header(dest_stream, metadata)
|
||||
write_flv_header(dest_stream)
|
||||
write_metadata_tag(dest_stream, metadata)
|
||||
|
||||
# This dict stores the download progress, it's updated by the progress
|
||||
# hook
|
||||
|
@ -11,7 +11,7 @@ from ..compat import (
|
||||
compat_urllib_request,
|
||||
)
|
||||
from ..utils import (
|
||||
check_executable,
|
||||
encodeArgument,
|
||||
encodeFilename,
|
||||
)
|
||||
|
||||
@ -22,26 +22,22 @@ class HlsFD(FileDownloader):
|
||||
self.report_destination(filename)
|
||||
tmpfilename = self.temp_name(filename)
|
||||
|
||||
args = [
|
||||
'-y', '-i', url, '-f', 'mp4', '-c', 'copy',
|
||||
'-bsf:a', 'aac_adtstoasc',
|
||||
encodeFilename(tmpfilename, for_subprocess=True)]
|
||||
|
||||
for program in ['avconv', 'ffmpeg']:
|
||||
if check_executable(program, ['-version']):
|
||||
break
|
||||
else:
|
||||
ffpp = FFmpegPostProcessor(downloader=self)
|
||||
program = ffpp._executable
|
||||
if program is None:
|
||||
self.report_error('m3u8 download detected but ffmpeg or avconv could not be found. Please install one.')
|
||||
return False
|
||||
cmd = [program] + args
|
||||
|
||||
ffpp = FFmpegPostProcessor(downloader=self)
|
||||
ffpp.check_version()
|
||||
|
||||
retval = subprocess.call(cmd)
|
||||
args = [
|
||||
encodeArgument(opt)
|
||||
for opt in (program, '-y', '-i', url, '-f', 'mp4', '-c', 'copy', '-bsf:a', 'aac_adtstoasc')]
|
||||
args.append(encodeFilename(tmpfilename, True))
|
||||
|
||||
retval = subprocess.call(args)
|
||||
if retval == 0:
|
||||
fsize = os.path.getsize(encodeFilename(tmpfilename))
|
||||
self.to_screen('\r[%s] %s bytes' % (cmd[0], fsize))
|
||||
self.to_screen('\r[%s] %s bytes' % (args[0], fsize))
|
||||
self.try_rename(tmpfilename, filename)
|
||||
self._hook_progress({
|
||||
'downloaded_bytes': fsize,
|
||||
|
@ -3,6 +3,9 @@ from __future__ import unicode_literals
|
||||
import os
|
||||
import time
|
||||
|
||||
from socket import error as SocketError
|
||||
import errno
|
||||
|
||||
from .common import FileDownloader
|
||||
from ..compat import (
|
||||
compat_urllib_request,
|
||||
@ -24,10 +27,6 @@ class HttpFD(FileDownloader):
|
||||
|
||||
# Do not include the Accept-Encoding header
|
||||
headers = {'Youtubedl-no-compression': 'True'}
|
||||
if 'user_agent' in info_dict:
|
||||
headers['Youtubedl-user-agent'] = info_dict['user_agent']
|
||||
if 'http_referer' in info_dict:
|
||||
headers['Referer'] = info_dict['http_referer']
|
||||
add_headers = info_dict.get('http_headers')
|
||||
if add_headers:
|
||||
headers.update(add_headers)
|
||||
@ -103,6 +102,11 @@ class HttpFD(FileDownloader):
|
||||
resume_len = 0
|
||||
open_mode = 'wb'
|
||||
break
|
||||
except SocketError as e:
|
||||
if e.errno != errno.ECONNRESET:
|
||||
# Connection reset is no problem, just retry
|
||||
raise
|
||||
|
||||
# Retry
|
||||
count += 1
|
||||
if count <= retries:
|
||||
@ -161,6 +165,14 @@ class HttpFD(FileDownloader):
|
||||
except (OSError, IOError) as err:
|
||||
self.report_error('unable to open for writing: %s' % str(err))
|
||||
return False
|
||||
|
||||
if self.params.get('xattr_set_filesize', False) and data_len is not None:
|
||||
try:
|
||||
import xattr
|
||||
xattr.setxattr(tmpfilename, 'user.ytdl.filesize', str(data_len))
|
||||
except(OSError, IOError, ImportError) as err:
|
||||
self.report_error('unable to set filesize xattr: %s' % str(err))
|
||||
|
||||
try:
|
||||
stream.write(data_block)
|
||||
except (IOError, OSError) as err:
|
||||
|
@ -4,8 +4,8 @@ import os
|
||||
import subprocess
|
||||
|
||||
from .common import FileDownloader
|
||||
from ..compat import compat_subprocess_get_DEVNULL
|
||||
from ..utils import (
|
||||
check_executable,
|
||||
encodeFilename,
|
||||
)
|
||||
|
||||
@ -20,11 +20,7 @@ class MplayerFD(FileDownloader):
|
||||
'mplayer', '-really-quiet', '-vo', 'null', '-vc', 'dummy',
|
||||
'-dumpstream', '-dumpfile', tmpfilename, url]
|
||||
# Check for mplayer first
|
||||
try:
|
||||
subprocess.call(
|
||||
['mplayer', '-h'],
|
||||
stdout=compat_subprocess_get_DEVNULL(), stderr=subprocess.STDOUT)
|
||||
except (OSError, IOError):
|
||||
if not check_executable('mplayer', ['-h']):
|
||||
self.report_error('MMS or RTSP download detected but "%s" could not be run' % args[0])
|
||||
return False
|
||||
|
||||
|
@ -104,6 +104,9 @@ class RtmpFD(FileDownloader):
|
||||
live = info_dict.get('rtmp_live', False)
|
||||
conn = info_dict.get('rtmp_conn', None)
|
||||
protocol = info_dict.get('rtmp_protocol', None)
|
||||
real_time = info_dict.get('rtmp_real_time', False)
|
||||
no_resume = info_dict.get('no_resume', False)
|
||||
continue_dl = info_dict.get('continuedl', False)
|
||||
|
||||
self.report_destination(filename)
|
||||
tmpfilename = self.temp_name(filename)
|
||||
@ -141,7 +144,14 @@ class RtmpFD(FileDownloader):
|
||||
basic_args += ['--conn', conn]
|
||||
if protocol is not None:
|
||||
basic_args += ['--protocol', protocol]
|
||||
args = basic_args + [[], ['--resume', '--skip', '1']][not live and self.params.get('continuedl', False)]
|
||||
if real_time:
|
||||
basic_args += ['--realtime']
|
||||
|
||||
args = basic_args
|
||||
if not no_resume and continue_dl and not live:
|
||||
args += ['--resume']
|
||||
if not live and continue_dl:
|
||||
args += ['--skip', '1']
|
||||
|
||||
if sys.platform == 'win32' and sys.version_info < (3, 0):
|
||||
# Windows subprocess module does not actually support Unicode
|
||||
@ -152,19 +162,7 @@ class RtmpFD(FileDownloader):
|
||||
else:
|
||||
subprocess_encoding = None
|
||||
|
||||
if self.params.get('verbose', False):
|
||||
if subprocess_encoding:
|
||||
str_args = [
|
||||
a.decode(subprocess_encoding) if isinstance(a, bytes) else a
|
||||
for a in args]
|
||||
else:
|
||||
str_args = args
|
||||
try:
|
||||
import pipes
|
||||
shell_quote = lambda args: ' '.join(map(pipes.quote, str_args))
|
||||
except ImportError:
|
||||
shell_quote = repr
|
||||
self.to_screen('[debug] rtmpdump command line: ' + shell_quote(str_args))
|
||||
self._debug_cmd(args, subprocess_encoding, exe='rtmpdump')
|
||||
|
||||
RD_SUCCESS = 0
|
||||
RD_FAILED = 1
|
||||
|
@ -1,6 +1,7 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .abc import ABCIE
|
||||
from .abc7news import Abc7NewsIE
|
||||
from .academicearth import AcademicEarthCourseIE
|
||||
from .addanime import AddAnimeIE
|
||||
from .adobetv import AdobeTVIE
|
||||
@ -26,8 +27,8 @@ from .arte import (
|
||||
ArteTVEmbedIE,
|
||||
)
|
||||
from .atresplayer import AtresPlayerIE
|
||||
from .audiomack import AudiomackIE
|
||||
from .auengine import AUEngineIE
|
||||
from .atttechchannel import ATTTechChannelIE
|
||||
from .audiomack import AudiomackIE, AudiomackAlbumIE
|
||||
from .azubu import AzubuIE
|
||||
from .bambuser import BambuserIE, BambuserChannelIE
|
||||
from .bandcamp import BandcampIE, BandcampAlbumIE
|
||||
@ -69,6 +70,7 @@ from .cnn import (
|
||||
CNNArticleIE,
|
||||
)
|
||||
from .collegehumor import CollegeHumorIE
|
||||
from .collegerama import CollegeRamaIE
|
||||
from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE
|
||||
from .comcarcoff import ComCarCoffIE
|
||||
from .commonmistakes import CommonMistakesIE
|
||||
@ -80,6 +82,7 @@ from .crunchyroll import (
|
||||
CrunchyrollShowPlaylistIE
|
||||
)
|
||||
from .cspan import CSpanIE
|
||||
from .ctsnews import CtsNewsIE
|
||||
from .dailymotion import (
|
||||
DailymotionIE,
|
||||
DailymotionPlaylistIE,
|
||||
@ -87,10 +90,12 @@ from .dailymotion import (
|
||||
)
|
||||
from .daum import DaumIE
|
||||
from .dbtv import DBTVIE
|
||||
from .dctp import DctpTvIE
|
||||
from .deezer import DeezerPlaylistIE
|
||||
from .dfb import DFBIE
|
||||
from .dotsub import DotsubIE
|
||||
from .dreisat import DreiSatIE
|
||||
from .drbonanza import DRBonanzaIE
|
||||
from .drtuber import DrTuberIE
|
||||
from .drtv import DRTVIE
|
||||
from .dvtv import DVTVIE
|
||||
@ -159,6 +164,7 @@ from .gametrailers import GametrailersIE
|
||||
from .gdcvault import GDCVaultIE
|
||||
from .generic import GenericIE
|
||||
from .giantbomb import GiantBombIE
|
||||
from .giga import GigaIE
|
||||
from .glide import GlideIE
|
||||
from .globo import GloboIE
|
||||
from .godtube import GodTubeIE
|
||||
@ -171,10 +177,12 @@ from .goshgay import GoshgayIE
|
||||
from .grooveshark import GroovesharkIE
|
||||
from .groupon import GrouponIE
|
||||
from .hark import HarkIE
|
||||
from .hearthisat import HearThisAtIE
|
||||
from .heise import HeiseIE
|
||||
from .hellporno import HellPornoIE
|
||||
from .helsinki import HelsinkiIE
|
||||
from .hentaistigma import HentaiStigmaIE
|
||||
from .historicfilms import HistoricFilmsIE
|
||||
from .hitbox import HitboxIE, HitboxLiveIE
|
||||
from .hornbunny import HornBunnyIE
|
||||
from .hostingbulk import HostingBulkIE
|
||||
@ -205,6 +213,7 @@ from .jove import JoveIE
|
||||
from .jukebox import JukeboxIE
|
||||
from .jpopsukitv import JpopsukiIE
|
||||
from .kankan import KankanIE
|
||||
from .karaoketv import KaraoketvIE
|
||||
from .keezmovies import KeezMoviesIE
|
||||
from .khanacademy import KhanAcademyIE
|
||||
from .kickstarter import KickStarterIE
|
||||
@ -221,6 +230,7 @@ from .livestream import (
|
||||
LivestreamOriginalIE,
|
||||
LivestreamShortenerIE,
|
||||
)
|
||||
from .lnkgo import LnkGoIE
|
||||
from .lrt import LRTIE
|
||||
from .lynda import (
|
||||
LyndaIE,
|
||||
@ -273,12 +283,23 @@ from .nbc import (
|
||||
)
|
||||
from .ndr import NDRIE
|
||||
from .ndtv import NDTVIE
|
||||
from .netzkino import NetzkinoIE
|
||||
from .nerdcubed import NerdCubedFeedIE
|
||||
from .newgrounds import NewgroundsIE
|
||||
from .newstube import NewstubeIE
|
||||
from .nextmedia import (
|
||||
NextMediaIE,
|
||||
NextMediaActionNewsIE,
|
||||
AppleDailyRealtimeNewsIE,
|
||||
AppleDailyAnimationNewsIE
|
||||
)
|
||||
from .nfb import NFBIE
|
||||
from .nfl import NFLIE
|
||||
from .nhl import NHLIE, NHLVideocenterIE
|
||||
from .nhl import (
|
||||
NHLIE,
|
||||
NHLNewsIE,
|
||||
NHLVideocenterIE,
|
||||
)
|
||||
from .niconico import NiconicoIE, NiconicoPlaylistIE
|
||||
from .ninegag import NineGagIE
|
||||
from .noco import NocoIE
|
||||
@ -289,6 +310,7 @@ from .nowness import NownessIE
|
||||
from .nowvideo import NowVideoIE
|
||||
from .npo import (
|
||||
NPOIE,
|
||||
NPOLiveIE,
|
||||
TegenlichtVproIE,
|
||||
)
|
||||
from .nrk import (
|
||||
@ -325,6 +347,7 @@ from .prosiebensat1 import ProSiebenSat1IE
|
||||
from .pyvideo import PyvideoIE
|
||||
from .quickvid import QuickVidIE
|
||||
from .radiode import RadioDeIE
|
||||
from .radiobremen import RadioBremenIE
|
||||
from .radiofrance import RadioFranceIE
|
||||
from .rai import RaiIE
|
||||
from .rbmaradio import RBMARadioIE
|
||||
@ -336,8 +359,10 @@ from .ro220 import Ro220IE
|
||||
from .rottentomatoes import RottenTomatoesIE
|
||||
from .roxwel import RoxwelIE
|
||||
from .rtbf import RTBFIE
|
||||
from .rte import RteIE
|
||||
from .rtlnl import RtlXlIE
|
||||
from .rtlnow import RTLnowIE
|
||||
from .rtl2 import RTL2IE
|
||||
from .rtp import RTPIE
|
||||
from .rts import RTSIE
|
||||
from .rtve import RTVEALaCartaIE, RTVELiveIE
|
||||
@ -345,6 +370,7 @@ from .ruhd import RUHDIE
|
||||
from .rutube import (
|
||||
RutubeIE,
|
||||
RutubeChannelIE,
|
||||
RutubeEmbedIE,
|
||||
RutubeMovieIE,
|
||||
RutubePersonIE,
|
||||
)
|
||||
@ -397,6 +423,7 @@ from .stanfordoc import StanfordOpenClassroomIE
|
||||
from .steam import SteamIE
|
||||
from .streamcloud import StreamcloudIE
|
||||
from .streamcz import StreamCZIE
|
||||
from .streetvoice import StreetVoiceIE
|
||||
from .sunporno import SunPornoIE
|
||||
from .swrmediathek import SWRMediathekIE
|
||||
from .syfy import SyfyIE
|
||||
@ -418,6 +445,7 @@ from .telemb import TeleMBIE
|
||||
from .teletask import TeleTaskIE
|
||||
from .tenplay import TenPlayIE
|
||||
from .testurl import TestURLIE
|
||||
from .testtube import TestTubeIE
|
||||
from .tf1 import TF1IE
|
||||
from .theonion import TheOnionIE
|
||||
from .theplatform import ThePlatformIE
|
||||
@ -443,10 +471,18 @@ from .tunein import TuneInIE
|
||||
from .turbo import TurboIE
|
||||
from .tutv import TutvIE
|
||||
from .tvigle import TvigleIE
|
||||
from .tvp import TvpIE
|
||||
from .tvp import TvpIE, TvpSeriesIE
|
||||
from .tvplay import TVPlayIE
|
||||
from .twentyfourvideo import TwentyFourVideoIE
|
||||
from .twitch import TwitchIE
|
||||
from .twitch import (
|
||||
TwitchVideoIE,
|
||||
TwitchChapterIE,
|
||||
TwitchVodIE,
|
||||
TwitchProfileIE,
|
||||
TwitchPastBroadcastsIE,
|
||||
TwitchBookmarksIE,
|
||||
TwitchStreamIE,
|
||||
)
|
||||
from .ubu import UbuIE
|
||||
from .udemy import (
|
||||
UdemyIE,
|
||||
@ -510,6 +546,7 @@ from .wdr import (
|
||||
WDRMobileIE,
|
||||
WDRMausIE,
|
||||
)
|
||||
from .webofstories import WebOfStoriesIE
|
||||
from .weibo import WeiboIE
|
||||
from .wimp import WimpIE
|
||||
from .wistia import WistiaIE
|
||||
@ -522,6 +559,7 @@ from .xminus import XMinusIE
|
||||
from .xnxx import XNXXIE
|
||||
from .xvideos import XVideosIE
|
||||
from .xtube import XTubeUserIE, XTubeIE
|
||||
from .xuite import XuiteIE
|
||||
from .xxxymovies import XXXYMoviesIE
|
||||
from .yahoo import (
|
||||
YahooIE,
|
||||
@ -545,7 +583,6 @@ from .youtube import (
|
||||
YoutubeSearchURLIE,
|
||||
YoutubeShowIE,
|
||||
YoutubeSubscriptionsIE,
|
||||
YoutubeTopListIE,
|
||||
YoutubeTruncatedIDIE,
|
||||
YoutubeTruncatedURLIE,
|
||||
YoutubeUserIE,
|
||||
@ -572,6 +609,17 @@ def gen_extractors():
|
||||
return [klass() for klass in _ALL_CLASSES]
|
||||
|
||||
|
||||
def list_extractors(age_limit):
|
||||
"""
|
||||
Return a list of extractors that are suitable for the given age,
|
||||
sorted by extractor ID.
|
||||
"""
|
||||
|
||||
return sorted(
|
||||
filter(lambda ie: ie.is_suitable(age_limit), gen_extractors()),
|
||||
key=lambda ie: ie.IE_NAME.lower())
|
||||
|
||||
|
||||
def get_info_extractor(ie_name):
|
||||
"""Returns the info extractor class with the given ie_name"""
|
||||
return globals()[ie_name + 'IE']
|
||||
|
68
youtube_dl/extractor/abc7news.py
Normal file
68
youtube_dl/extractor/abc7news.py
Normal file
@ -0,0 +1,68 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import parse_iso8601
|
||||
|
||||
|
||||
class Abc7NewsIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://abc7news\.com(?:/[^/]+/(?P<display_id>[^/]+))?/(?P<id>\d+)'
|
||||
_TESTS = [
|
||||
{
|
||||
'url': 'http://abc7news.com/entertainment/east-bay-museum-celebrates-vintage-synthesizers/472581/',
|
||||
'info_dict': {
|
||||
'id': '472581',
|
||||
'display_id': 'east-bay-museum-celebrates-vintage-synthesizers',
|
||||
'ext': 'mp4',
|
||||
'title': 'East Bay museum celebrates history of synthesized music',
|
||||
'description': 'md5:a4f10fb2f2a02565c1749d4adbab4b10',
|
||||
'thumbnail': 're:^https?://.*\.jpg$',
|
||||
'timestamp': 1421123075,
|
||||
'upload_date': '20150113',
|
||||
'uploader': 'Jonathan Bloom',
|
||||
},
|
||||
'params': {
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
},
|
||||
},
|
||||
{
|
||||
'url': 'http://abc7news.com/472581',
|
||||
'only_matching': True,
|
||||
},
|
||||
]
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
display_id = mobj.group('display_id') or video_id
|
||||
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
m3u8 = self._html_search_meta(
|
||||
'contentURL', webpage, 'm3u8 url', fatal=True)
|
||||
|
||||
formats = self._extract_m3u8_formats(m3u8, display_id, 'mp4')
|
||||
self._sort_formats(formats)
|
||||
|
||||
title = self._og_search_title(webpage).strip()
|
||||
description = self._og_search_description(webpage).strip()
|
||||
thumbnail = self._og_search_thumbnail(webpage)
|
||||
timestamp = parse_iso8601(self._search_regex(
|
||||
r'<div class="meta">\s*<time class="timeago" datetime="([^"]+)">',
|
||||
webpage, 'upload date', fatal=False))
|
||||
uploader = self._search_regex(
|
||||
r'rel="author">([^<]+)</a>',
|
||||
webpage, 'uploader', default=None)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'display_id': display_id,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
'timestamp': timestamp,
|
||||
'uploader': uploader,
|
||||
'formats': formats,
|
||||
}
|
@ -122,14 +122,15 @@ class AppleTrailersIE(InfoExtractor):
|
||||
playlist.append({
|
||||
'_type': 'video',
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'formats': formats,
|
||||
'title': title,
|
||||
'duration': duration,
|
||||
'thumbnail': thumbnail,
|
||||
'upload_date': upload_date,
|
||||
'uploader_id': uploader_id,
|
||||
'user_agent': 'QuickTime compatible (youtube-dl)',
|
||||
'http_headers': {
|
||||
'User-Agent': 'QuickTime compatible (youtube-dl)',
|
||||
},
|
||||
})
|
||||
|
||||
return {
|
||||
|
@ -23,13 +23,7 @@ class ARDMediathekIE(InfoExtractor):
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://mediathek.daserste.de/sendungen_a-z/328454_anne-will/22429276_vertrauen-ist-gut-spionieren-ist-besser-geht',
|
||||
'file': '22429276.mp4',
|
||||
'md5': '469751912f1de0816a9fc9df8336476c',
|
||||
'info_dict': {
|
||||
'title': 'Vertrauen ist gut, Spionieren ist besser - Geht so deutsch-amerikanische Freundschaft?',
|
||||
'description': 'Das Erste Mediathek [ARD]: Vertrauen ist gut, Spionieren ist besser - Geht so deutsch-amerikanische Freundschaft?, Anne Will, Über die Spionage-Affäre diskutieren Clemens Binninger, Katrin Göring-Eckardt, Georg Mascolo, Andrew B. Denison und Constanze Kurz.. Das Video zur Sendung Anne Will am Mittwoch, 16.07.2014',
|
||||
},
|
||||
'skip': 'Blocked outside of Germany',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.ardmediathek.de/tv/Tatort/Das-Wunder-von-Wolbeck-Video-tgl-ab-20/Das-Erste/Video?documentId=22490580&bcastId=602916',
|
||||
'info_dict': {
|
||||
|
@ -3,10 +3,13 @@ from __future__ import unicode_literals
|
||||
import time
|
||||
import hmac
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
from .subtitles import SubtitlesInfoExtractor
|
||||
from ..compat import (
|
||||
compat_str,
|
||||
compat_urllib_parse,
|
||||
compat_urllib_request,
|
||||
)
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
float_or_none,
|
||||
xpath_text,
|
||||
@ -14,7 +17,7 @@ from ..utils import (
|
||||
)
|
||||
|
||||
|
||||
class AtresPlayerIE(InfoExtractor):
|
||||
class AtresPlayerIE(SubtitlesInfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?atresplayer\.com/television/[^/]+/[^/]+/[^/]+/(?P<id>.+?)_\d+\.html'
|
||||
_TESTS = [
|
||||
{
|
||||
@ -44,6 +47,33 @@ class AtresPlayerIE(InfoExtractor):
|
||||
_PLAYER_URL_TEMPLATE = 'https://servicios.atresplayer.com/episode/getplayer.json?episodePk=%s'
|
||||
_EPISODE_URL_TEMPLATE = 'http://www.atresplayer.com/episodexml/%s'
|
||||
|
||||
_LOGIN_URL = 'https://servicios.atresplayer.com/j_spring_security_check'
|
||||
|
||||
def _real_initialize(self):
|
||||
self._login()
|
||||
|
||||
def _login(self):
|
||||
(username, password) = self._get_login_info()
|
||||
if username is None:
|
||||
return
|
||||
|
||||
login_form = {
|
||||
'j_username': username,
|
||||
'j_password': password,
|
||||
}
|
||||
|
||||
request = compat_urllib_request.Request(
|
||||
self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
|
||||
request.add_header('Content-Type', 'application/x-www-form-urlencoded')
|
||||
response = self._download_webpage(
|
||||
request, None, 'Logging in as %s' % username)
|
||||
|
||||
error = self._html_search_regex(
|
||||
r'(?s)<ul class="list_error">(.+?)</ul>', response, 'error', default=None)
|
||||
if error:
|
||||
raise ExtractorError(
|
||||
'Unable to login: %s' % error, expected=True)
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
@ -65,7 +95,7 @@ class AtresPlayerIE(InfoExtractor):
|
||||
for fmt in ['windows', 'android_tablet']:
|
||||
request = compat_urllib_request.Request(
|
||||
self._URL_VIDEO_TEMPLATE.format(fmt, episode_id, timestamp_shifted, token))
|
||||
request.add_header('Youtubedl-user-agent', self._USER_AGENT)
|
||||
request.add_header('User-Agent', self._USER_AGENT)
|
||||
|
||||
fmt_json = self._download_json(
|
||||
request, video_id, 'Downloading %s video JSON' % fmt)
|
||||
@ -75,13 +105,22 @@ class AtresPlayerIE(InfoExtractor):
|
||||
raise ExtractorError(
|
||||
'%s returned error: %s' % (self.IE_NAME, result), expected=True)
|
||||
|
||||
for _, video_url in fmt_json['resultObject'].items():
|
||||
for format_id, video_url in fmt_json['resultObject'].items():
|
||||
if format_id == 'token' or not video_url.startswith('http'):
|
||||
continue
|
||||
if video_url.endswith('/Manifest'):
|
||||
formats.extend(self._extract_f4m_formats(video_url[:-9] + '/manifest.f4m', video_id))
|
||||
if 'geodeswowsmpra3player' in video_url:
|
||||
f4m_path = video_url.split('smil:', 1)[-1].split('free_', 1)[0]
|
||||
f4m_url = 'http://drg.antena3.com/{0}hds/es/sd.f4m'.format(f4m_path)
|
||||
# this videos are protected by DRM, the f4m downloader doesn't support them
|
||||
continue
|
||||
else:
|
||||
f4m_url = video_url[:-9] + '/manifest.f4m'
|
||||
formats.extend(self._extract_f4m_formats(f4m_url, video_id))
|
||||
else:
|
||||
formats.append({
|
||||
'url': video_url,
|
||||
'format_id': 'android',
|
||||
'format_id': 'android-%s' % format_id,
|
||||
'preference': 1,
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
@ -104,6 +143,15 @@ class AtresPlayerIE(InfoExtractor):
|
||||
description = xpath_text(art, './description', 'description')
|
||||
thumbnail = xpath_text(episode, './media/asset/files/background', 'thumbnail')
|
||||
|
||||
subtitles = {}
|
||||
subtitle = xpath_text(episode, './media/asset/files/subtitle', 'subtitle')
|
||||
if subtitle:
|
||||
subtitles['es'] = subtitle
|
||||
|
||||
if self._downloader.params.get('listsubtitles', False):
|
||||
self._list_available_subtitles(video_id, subtitles)
|
||||
return
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
@ -111,4 +159,5 @@ class AtresPlayerIE(InfoExtractor):
|
||||
'thumbnail': thumbnail,
|
||||
'duration': duration,
|
||||
'formats': formats,
|
||||
'subtitles': self.extract_subtitles(video_id, subtitles),
|
||||
}
|
||||
|
55
youtube_dl/extractor/atttechchannel.py
Normal file
55
youtube_dl/extractor/atttechchannel.py
Normal file
@ -0,0 +1,55 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import unified_strdate
|
||||
|
||||
|
||||
class ATTTechChannelIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://techchannel\.att\.com/play-video\.cfm/([^/]+/)*(?P<id>.+)'
|
||||
_TEST = {
|
||||
'url': 'http://techchannel.att.com/play-video.cfm/2014/1/27/ATT-Archives-The-UNIX-System-Making-Computers-Easier-to-Use',
|
||||
'info_dict': {
|
||||
'id': '11316',
|
||||
'display_id': 'ATT-Archives-The-UNIX-System-Making-Computers-Easier-to-Use',
|
||||
'ext': 'flv',
|
||||
'title': 'AT&T Archives : The UNIX System: Making Computers Easier to Use',
|
||||
'description': 'A 1982 film about UNIX is the foundation for software in use around Bell Labs and AT&T.',
|
||||
'thumbnail': 're:^https?://.*\.jpg$',
|
||||
'upload_date': '20140127',
|
||||
},
|
||||
'params': {
|
||||
# rtmp download
|
||||
'skip_download': True,
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
video_url = self._search_regex(
|
||||
r"url\s*:\s*'(rtmp://[^']+)'",
|
||||
webpage, 'video URL')
|
||||
|
||||
video_id = self._search_regex(
|
||||
r'mediaid\s*=\s*(\d+)',
|
||||
webpage, 'video id', fatal=False)
|
||||
|
||||
title = self._og_search_title(webpage)
|
||||
description = self._og_search_description(webpage)
|
||||
thumbnail = self._og_search_thumbnail(webpage)
|
||||
upload_date = unified_strdate(self._search_regex(
|
||||
r'[Rr]elease\s+date:\s*(\d{1,2}/\d{1,2}/\d{4})',
|
||||
webpage, 'upload date', fatal=False), False)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'display_id': display_id,
|
||||
'url': video_url,
|
||||
'ext': 'flv',
|
||||
'title': title,
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
'upload_date': upload_date,
|
||||
}
|
@ -1,11 +1,15 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import itertools
|
||||
import time
|
||||
|
||||
from .common import InfoExtractor
|
||||
from .soundcloud import SoundcloudIE
|
||||
from ..utils import ExtractorError
|
||||
|
||||
import time
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
url_basename,
|
||||
)
|
||||
|
||||
|
||||
class AudiomackIE(InfoExtractor):
|
||||
@ -17,12 +21,13 @@ class AudiomackIE(InfoExtractor):
|
||||
'url': 'http://www.audiomack.com/song/roosh-williams/extraordinary',
|
||||
'info_dict':
|
||||
{
|
||||
'id': 'roosh-williams/extraordinary',
|
||||
'id': '310086',
|
||||
'ext': 'mp3',
|
||||
'title': 'Roosh Williams - Extraordinary'
|
||||
'uploader': 'Roosh Williams',
|
||||
'title': 'Extraordinary'
|
||||
}
|
||||
},
|
||||
# hosted on soundcloud via audiomack
|
||||
# audiomack wrapper around soundcloud song
|
||||
{
|
||||
'add_ie': ['Soundcloud'],
|
||||
'url': 'http://www.audiomack.com/song/xclusiveszone/take-kare',
|
||||
@ -38,32 +43,102 @@ class AudiomackIE(InfoExtractor):
|
||||
]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
# URLs end with [uploader name]/[uploader title]
|
||||
# this title is whatever the user types in, and is rarely
|
||||
# the proper song title. Real metadata is in the api response
|
||||
album_url_tag = self._match_id(url)
|
||||
|
||||
# Request the extended version of the api for extra fields like artist and title
|
||||
api_response = self._download_json(
|
||||
"http://www.audiomack.com/api/music/url/song/%s?_=%d" % (
|
||||
video_id, time.time()),
|
||||
video_id)
|
||||
'http://www.audiomack.com/api/music/url/song/%s?extended=1&_=%d' % (
|
||||
album_url_tag, time.time()),
|
||||
album_url_tag)
|
||||
|
||||
if "url" not in api_response:
|
||||
raise ExtractorError("Unable to deduce api url of song")
|
||||
realurl = api_response["url"]
|
||||
# API is inconsistent with errors
|
||||
if 'url' not in api_response or not api_response['url'] or 'error' in api_response:
|
||||
raise ExtractorError('Invalid url %s', url)
|
||||
|
||||
# Audiomack wraps a lot of soundcloud tracks in their branded wrapper
|
||||
# - if so, pass the work off to the soundcloud extractor
|
||||
if SoundcloudIE.suitable(realurl):
|
||||
return {'_type': 'url', 'url': realurl, 'ie_key': 'Soundcloud'}
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
artist = self._html_search_regex(
|
||||
r'<span class="artist">(.*?)</span>', webpage, "artist")
|
||||
songtitle = self._html_search_regex(
|
||||
r'<h1 class="profile-title song-title"><span class="artist">.*?</span>(.*?)</h1>',
|
||||
webpage, "title")
|
||||
title = artist + " - " + songtitle
|
||||
# if so, pass the work off to the soundcloud extractor
|
||||
if SoundcloudIE.suitable(api_response['url']):
|
||||
return {'_type': 'url', 'url': api_response['url'], 'ie_key': 'Soundcloud'}
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'url': realurl,
|
||||
'id': api_response.get('id', album_url_tag),
|
||||
'uploader': api_response.get('artist'),
|
||||
'title': api_response.get('title'),
|
||||
'url': api_response['url'],
|
||||
}
|
||||
|
||||
|
||||
class AudiomackAlbumIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?audiomack\.com/album/(?P<id>[\w/-]+)'
|
||||
IE_NAME = 'audiomack:album'
|
||||
_TESTS = [
|
||||
# Standard album playlist
|
||||
{
|
||||
'url': 'http://www.audiomack.com/album/flytunezcom/tha-tour-part-2-mixtape',
|
||||
'playlist_count': 15,
|
||||
'info_dict':
|
||||
{
|
||||
'id': '812251',
|
||||
'title': 'Tha Tour: Part 2 (Official Mixtape)'
|
||||
}
|
||||
},
|
||||
# Album playlist ripped from fakeshoredrive with no metadata
|
||||
{
|
||||
'url': 'http://www.audiomack.com/album/fakeshoredrive/ppp-pistol-p-project',
|
||||
'info_dict': {
|
||||
'title': 'PPP (Pistol P Project)',
|
||||
'id': '837572',
|
||||
},
|
||||
'playlist': [{
|
||||
'info_dict': {
|
||||
'title': 'PPP (Pistol P Project) - 9. Heaven or Hell (CHIMACA) ft Zuse (prod by DJ FU)',
|
||||
'id': '837577',
|
||||
'ext': 'mp3',
|
||||
'uploader': 'Lil Herb a.k.a. G Herbo',
|
||||
}
|
||||
}],
|
||||
'params': {
|
||||
'playliststart': 9,
|
||||
'playlistend': 9,
|
||||
}
|
||||
}
|
||||
]
|
||||
|
||||
def _real_extract(self, url):
|
||||
# URLs end with [uploader name]/[uploader title]
|
||||
# this title is whatever the user types in, and is rarely
|
||||
# the proper song title. Real metadata is in the api response
|
||||
album_url_tag = self._match_id(url)
|
||||
result = {'_type': 'playlist', 'entries': []}
|
||||
# There is no one endpoint for album metadata - instead it is included/repeated in each song's metadata
|
||||
# Therefore we don't know how many songs the album has and must infi-loop until failure
|
||||
for track_no in itertools.count():
|
||||
# Get song's metadata
|
||||
api_response = self._download_json(
|
||||
'http://www.audiomack.com/api/music/url/album/%s/%d?extended=1&_=%d'
|
||||
% (album_url_tag, track_no, time.time()), album_url_tag,
|
||||
note='Querying song information (%d)' % (track_no + 1))
|
||||
|
||||
# Total failure, only occurs when url is totally wrong
|
||||
# Won't happen in middle of valid playlist (next case)
|
||||
if 'url' not in api_response or 'error' in api_response:
|
||||
raise ExtractorError('Invalid url for track %d of album url %s' % (track_no, url))
|
||||
# URL is good but song id doesn't exist - usually means end of playlist
|
||||
elif not api_response['url']:
|
||||
break
|
||||
else:
|
||||
# Pull out the album metadata and add to result (if it exists)
|
||||
for resultkey, apikey in [('id', 'album_id'), ('title', 'album_title')]:
|
||||
if apikey in api_response and resultkey not in result:
|
||||
result[resultkey] = api_response[apikey]
|
||||
song_id = url_basename(api_response['url']).rpartition('.')[0]
|
||||
result['entries'].append({
|
||||
'id': api_response.get('id', song_id),
|
||||
'uploader': api_response.get('artist'),
|
||||
'title': api_response.get('title', song_id),
|
||||
'url': api_response['url'],
|
||||
})
|
||||
return result
|
||||
|
@ -1,54 +0,0 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_urllib_parse
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
ExtractorError,
|
||||
)
|
||||
|
||||
|
||||
class AUEngineIE(InfoExtractor):
|
||||
_VALID_URL = r'http://(?:www\.)?auengine\.com/embed\.php\?.*?file=(?P<id>[^&]+).*?'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://auengine.com/embed.php?file=lfvlytY6&w=650&h=370',
|
||||
'md5': '48972bdbcf1a3a2f5533e62425b41d4f',
|
||||
'info_dict': {
|
||||
'id': 'lfvlytY6',
|
||||
'ext': 'mp4',
|
||||
'title': '[Commie]The Legend of the Legendary Heroes - 03 - Replication Eye (Alpha Stigma)[F9410F5A]'
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
title = self._html_search_regex(r'<title>(?P<title>.+?)</title>', webpage, 'title')
|
||||
title = title.strip()
|
||||
links = re.findall(r'\s(?:file|url):\s*["\']([^\'"]+)["\']', webpage)
|
||||
links = map(compat_urllib_parse.unquote, links)
|
||||
|
||||
thumbnail = None
|
||||
video_url = None
|
||||
for link in links:
|
||||
if link.endswith('.png'):
|
||||
thumbnail = link
|
||||
elif '/videos/' in link:
|
||||
video_url = link
|
||||
if not video_url:
|
||||
raise ExtractorError('Could not find video URL')
|
||||
ext = '.' + determine_ext(video_url)
|
||||
if ext == title[-len(ext):]:
|
||||
title = title[:-len(ext)]
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'url': video_url,
|
||||
'title': title,
|
||||
'thumbnail': thumbnail,
|
||||
'http_referer': 'http://www.auengine.com/flowplayer/flowplayer.commercial-3.2.14.swf',
|
||||
}
|
@ -161,7 +161,8 @@ class BandcampAlbumIE(InfoExtractor):
|
||||
entries = [
|
||||
self.url_result(compat_urlparse.urljoin(url, t_path), ie=BandcampIE.ie_key())
|
||||
for t_path in tracks_paths]
|
||||
title = self._search_regex(r'album_title : "(.*?)"', webpage, 'title')
|
||||
title = self._search_regex(
|
||||
r'album_title\s*:\s*"(.*?)"', webpage, 'title', fatal=False)
|
||||
return {
|
||||
'_type': 'playlist',
|
||||
'id': playlist_id,
|
||||
|
@ -10,7 +10,7 @@ from ..compat import compat_HTTPError
|
||||
class BBCCoUkIE(SubtitlesInfoExtractor):
|
||||
IE_NAME = 'bbc.co.uk'
|
||||
IE_DESC = 'BBC iPlayer'
|
||||
_VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:programmes|iplayer/(?:episode|playlist))/(?P<id>[\da-z]{8})'
|
||||
_VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:(?:programmes|iplayer(?:/[^/]+)?/(?:episode|playlist))/)|music/clips[/#])(?P<id>[\da-z]{8})'
|
||||
|
||||
_TESTS = [
|
||||
{
|
||||
@ -18,8 +18,8 @@ class BBCCoUkIE(SubtitlesInfoExtractor):
|
||||
'info_dict': {
|
||||
'id': 'b039d07m',
|
||||
'ext': 'flv',
|
||||
'title': 'Kaleidoscope: Leonard Cohen',
|
||||
'description': 'md5:db4755d7a665ae72343779f7dacb402c',
|
||||
'title': 'Kaleidoscope, Leonard Cohen',
|
||||
'description': 'The Canadian poet and songwriter reflects on his musical career.',
|
||||
'duration': 1740,
|
||||
},
|
||||
'params': {
|
||||
@ -84,9 +84,43 @@ class BBCCoUkIE(SubtitlesInfoExtractor):
|
||||
# rtmp download
|
||||
'skip_download': True,
|
||||
}
|
||||
}, {
|
||||
'url': 'http://www.bbc.co.uk/music/clips/p02frcc3',
|
||||
'note': 'Audio',
|
||||
'info_dict': {
|
||||
'id': 'p02frcch',
|
||||
'ext': 'flv',
|
||||
'title': 'Pete Tong, Past, Present and Future Special, Madeon - After Hours mix',
|
||||
'description': 'French house superstar Madeon takes us out of the club and onto the after party.',
|
||||
'duration': 3507,
|
||||
},
|
||||
'params': {
|
||||
# rtmp download
|
||||
'skip_download': True,
|
||||
}
|
||||
}, {
|
||||
'url': 'http://www.bbc.co.uk/music/clips/p025c0zz',
|
||||
'note': 'Video',
|
||||
'info_dict': {
|
||||
'id': 'p025c103',
|
||||
'ext': 'flv',
|
||||
'title': 'Reading and Leeds Festival, 2014, Rae Morris - Closer (Live on BBC Three)',
|
||||
'description': 'Rae Morris performs Closer for BBC Three at Reading 2014',
|
||||
'duration': 226,
|
||||
},
|
||||
'params': {
|
||||
# rtmp download
|
||||
'skip_download': True,
|
||||
}
|
||||
}, {
|
||||
'url': 'http://www.bbc.co.uk/iplayer/playlist/p01dvks4',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.bbc.co.uk/music/clips#p02frcc3',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.bbc.co.uk/iplayer/cbeebies/episode/b0480276/bing-14-atchoo',
|
||||
'only_matching': True,
|
||||
}
|
||||
]
|
||||
|
||||
|
@ -16,7 +16,7 @@ class BetIE(InfoExtractor):
|
||||
{
|
||||
'url': 'http://www.bet.com/news/politics/2014/12/08/in-bet-exclusive-obama-talks-race-and-racism.html',
|
||||
'info_dict': {
|
||||
'id': '417cd61c-c793-4e8e-b006-e445ecc45add',
|
||||
'id': '740ab250-bb94-4a8a-8787-fe0de7c74471',
|
||||
'display_id': 'in-bet-exclusive-obama-talks-race-and-racism',
|
||||
'ext': 'flv',
|
||||
'title': 'BET News Presents: A Conversation With President Obama',
|
||||
@ -35,7 +35,7 @@ class BetIE(InfoExtractor):
|
||||
{
|
||||
'url': 'http://www.bet.com/video/news/national/2014/justice-for-ferguson-a-community-reacts.html',
|
||||
'info_dict': {
|
||||
'id': '4160e53b-ad41-43b1-980f-8d85f63121f4',
|
||||
'id': 'bcd1b1df-673a-42cf-8d01-b282db608f2d',
|
||||
'display_id': 'justice-for-ferguson-a-community-reacts',
|
||||
'ext': 'flv',
|
||||
'title': 'Justice for Ferguson: A Community Reacts',
|
||||
@ -55,7 +55,6 @@ class BetIE(InfoExtractor):
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
media_url = compat_urllib_parse.unquote(self._search_regex(
|
||||
|
@ -4,9 +4,7 @@ from __future__ import unicode_literals
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_parse_qs
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
int_or_none,
|
||||
unified_strdate,
|
||||
)
|
||||
@ -54,45 +52,38 @@ class BiliBiliIE(InfoExtractor):
|
||||
thumbnail = self._html_search_meta(
|
||||
'thumbnailUrl', video_code, 'thumbnail', fatal=False)
|
||||
|
||||
player_params = compat_parse_qs(self._html_search_regex(
|
||||
r'<iframe .*?class="player" src="https://secure\.bilibili\.(?:tv|com)/secure,([^"]+)"',
|
||||
webpage, 'player params'))
|
||||
cid = self._search_regex(r'cid=(\d+)', webpage, 'cid')
|
||||
|
||||
if 'cid' in player_params:
|
||||
cid = player_params['cid'][0]
|
||||
lq_doc = self._download_xml(
|
||||
'http://interface.bilibili.com/v_cdn_play?appkey=1&cid=%s' % cid,
|
||||
video_id,
|
||||
note='Downloading LQ video info'
|
||||
)
|
||||
lq_durl = lq_doc.find('./durl')
|
||||
formats = [{
|
||||
'format_id': 'lq',
|
||||
'quality': 1,
|
||||
'url': lq_durl.find('./url').text,
|
||||
'filesize': int_or_none(
|
||||
lq_durl.find('./size'), get_attr='text'),
|
||||
}]
|
||||
|
||||
lq_doc = self._download_xml(
|
||||
'http://interface.bilibili.cn/v_cdn_play?cid=%s' % cid,
|
||||
video_id,
|
||||
note='Downloading LQ video info'
|
||||
)
|
||||
lq_durl = lq_doc.find('.//durl')
|
||||
formats = [{
|
||||
'format_id': 'lq',
|
||||
'quality': 1,
|
||||
'url': lq_durl.find('./url').text,
|
||||
hq_doc = self._download_xml(
|
||||
'http://interface.bilibili.com/playurl?appkey=1&cid=%s' % cid,
|
||||
video_id,
|
||||
note='Downloading HQ video info',
|
||||
fatal=False,
|
||||
)
|
||||
if hq_doc is not False:
|
||||
hq_durl = hq_doc.find('./durl')
|
||||
formats.append({
|
||||
'format_id': 'hq',
|
||||
'quality': 2,
|
||||
'ext': 'flv',
|
||||
'url': hq_durl.find('./url').text,
|
||||
'filesize': int_or_none(
|
||||
lq_durl.find('./size'), get_attr='text'),
|
||||
}]
|
||||
|
||||
hq_doc = self._download_xml(
|
||||
'http://interface.bilibili.cn/playurl?cid=%s' % cid,
|
||||
video_id,
|
||||
note='Downloading HQ video info',
|
||||
fatal=False,
|
||||
)
|
||||
if hq_doc is not False:
|
||||
hq_durl = hq_doc.find('.//durl')
|
||||
formats.append({
|
||||
'format_id': 'hq',
|
||||
'quality': 2,
|
||||
'ext': 'flv',
|
||||
'url': hq_durl.find('./url').text,
|
||||
'filesize': int_or_none(
|
||||
hq_durl.find('./size'), get_attr='text'),
|
||||
})
|
||||
else:
|
||||
raise ExtractorError('Unsupported player parameters: %r' % (player_params,))
|
||||
hq_durl.find('./size'), get_attr='text'),
|
||||
})
|
||||
|
||||
self._sort_formats(formats)
|
||||
return {
|
||||
|
@ -199,7 +199,7 @@ class BlipTVIE(SubtitlesInfoExtractor):
|
||||
# For some weird reason, blip.tv serves a video instead of subtitles
|
||||
# when we request with a common UA
|
||||
req = compat_urllib_request.Request(url)
|
||||
req.add_header('Youtubedl-user-agent', 'youtube-dl')
|
||||
req.add_header('User-Agent', 'youtube-dl')
|
||||
return self._download_webpage(req, None, note=False)
|
||||
|
||||
|
||||
|
@ -33,7 +33,7 @@ class BuzzFeedIE(InfoExtractor):
|
||||
'skip_download': True, # Got enough YouTube download tests
|
||||
},
|
||||
'info_dict': {
|
||||
'description': 'Munchkin the Teddy Bear is back !',
|
||||
'description': 're:Munchkin the Teddy Bear is back ?!',
|
||||
'title': 'You Need To Stop What You\'re Doing And Watching This Dog Walk On A Treadmill',
|
||||
},
|
||||
'playlist': [{
|
||||
@ -42,9 +42,9 @@ class BuzzFeedIE(InfoExtractor):
|
||||
'ext': 'mp4',
|
||||
'upload_date': '20141124',
|
||||
'uploader_id': 'CindysMunchkin',
|
||||
'description': '© 2014 Munchkin the Shih Tzu\nAll rights reserved\nFacebook: http://facebook.com/MunchkintheShihTzu',
|
||||
'description': 're:© 2014 Munchkin the Shih Tzu',
|
||||
'uploader': 'Munchkin the Shih Tzu',
|
||||
'title': 'Munchkin the Teddy Bear gets her exercise',
|
||||
'title': 're:Munchkin the Teddy Bear gets her exercise',
|
||||
},
|
||||
}]
|
||||
}]
|
||||
|
@ -5,6 +5,8 @@ import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
HEADRequest,
|
||||
unified_strdate,
|
||||
url_basename,
|
||||
qualities,
|
||||
@ -76,6 +78,16 @@ class CanalplusIE(InfoExtractor):
|
||||
|
||||
preference = qualities(['MOBILE', 'BAS_DEBIT', 'HAUT_DEBIT', 'HD', 'HLS', 'HDS'])
|
||||
|
||||
fmt_url = next(iter(media.find('VIDEOS'))).text
|
||||
if '/geo' in fmt_url.lower():
|
||||
response = self._request_webpage(
|
||||
HEADRequest(fmt_url), video_id,
|
||||
'Checking if the video is georestricted')
|
||||
if '/blocage' in response.geturl():
|
||||
raise ExtractorError(
|
||||
'The video is not available in your country',
|
||||
expected=True)
|
||||
|
||||
formats = []
|
||||
for fmt in media.find('VIDEOS'):
|
||||
format_url = fmt.text
|
||||
|
@ -3,7 +3,7 @@ from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from .subtitles import SubtitlesInfoExtractor
|
||||
from ..compat import (
|
||||
compat_urllib_request,
|
||||
compat_urllib_parse,
|
||||
@ -15,7 +15,7 @@ from ..utils import (
|
||||
)
|
||||
|
||||
|
||||
class CeskaTelevizeIE(InfoExtractor):
|
||||
class CeskaTelevizeIE(SubtitlesInfoExtractor):
|
||||
_VALID_URL = r'https?://www\.ceskatelevize\.cz/(porady|ivysilani)/(.+/)?(?P<id>[^?#]+)'
|
||||
|
||||
_TESTS = [
|
||||
@ -104,6 +104,17 @@ class CeskaTelevizeIE(InfoExtractor):
|
||||
duration = float_or_none(item.get('duration'))
|
||||
thumbnail = item.get('previewImageUrl')
|
||||
|
||||
subtitles = {}
|
||||
subs = item.get('subtitles')
|
||||
if subs:
|
||||
subtitles['cs'] = subs[0]['url']
|
||||
|
||||
if self._downloader.params.get('listsubtitles', False):
|
||||
self._list_available_subtitles(video_id, subtitles)
|
||||
return
|
||||
|
||||
subtitles = self._fix_subtitles(self.extract_subtitles(video_id, subtitles))
|
||||
|
||||
return {
|
||||
'id': episode_id,
|
||||
'title': title,
|
||||
@ -111,4 +122,34 @@ class CeskaTelevizeIE(InfoExtractor):
|
||||
'thumbnail': thumbnail,
|
||||
'duration': duration,
|
||||
'formats': formats,
|
||||
'subtitles': subtitles,
|
||||
}
|
||||
|
||||
@staticmethod
|
||||
def _fix_subtitles(subtitles):
|
||||
""" Convert millisecond-based subtitles to SRT """
|
||||
if subtitles is None:
|
||||
return subtitles # subtitles not requested
|
||||
|
||||
def _msectotimecode(msec):
|
||||
""" Helper utility to convert milliseconds to timecode """
|
||||
components = []
|
||||
for divider in [1000, 60, 60, 100]:
|
||||
components.append(msec % divider)
|
||||
msec //= divider
|
||||
return "{3:02}:{2:02}:{1:02},{0:03}".format(*components)
|
||||
|
||||
def _fix_subtitle(subtitle):
|
||||
for line in subtitle.splitlines():
|
||||
m = re.match(r"^\s*([0-9]+);\s*([0-9]+)\s+([0-9]+)\s*$", line)
|
||||
if m:
|
||||
yield m.group(1)
|
||||
start, stop = (_msectotimecode(int(t)) for t in m.groups()[1:])
|
||||
yield "{0} --> {1}".format(start, stop)
|
||||
else:
|
||||
yield line
|
||||
|
||||
fixed_subtitles = {}
|
||||
for k, v in subtitles.items():
|
||||
fixed_subtitles[k] = "\r\n".join(_fix_subtitle(v))
|
||||
return fixed_subtitles
|
||||
|
@ -28,12 +28,10 @@ class CinchcastIE(InfoExtractor):
|
||||
item, './{http://developer.longtailvideo.com/trac/}date')
|
||||
upload_date = unified_strdate(date_str, day_first=False)
|
||||
# duration is present but wrong
|
||||
formats = []
|
||||
formats.append({
|
||||
formats = [{
|
||||
'format_id': 'main',
|
||||
'url': item.find(
|
||||
'./{http://search.yahoo.com/mrss/}content').attrib['url'],
|
||||
})
|
||||
'url': item.find('./{http://search.yahoo.com/mrss/}content').attrib['url'],
|
||||
}]
|
||||
backup_url = xpath_text(
|
||||
item, './{http://developer.longtailvideo.com/trac/}backupContent')
|
||||
if backup_url:
|
||||
|
@ -1,9 +1,7 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import json
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import determine_ext
|
||||
|
||||
|
||||
_translation_table = {
|
||||
@ -27,10 +25,10 @@ class CliphunterIE(InfoExtractor):
|
||||
'''
|
||||
_TEST = {
|
||||
'url': 'http://www.cliphunter.com/w/1012420/Fun_Jynx_Maze_solo',
|
||||
'md5': 'a2ba71eebf523859fe527a61018f723e',
|
||||
'md5': 'b7c9bbd4eb3a226ab91093714dcaa480',
|
||||
'info_dict': {
|
||||
'id': '1012420',
|
||||
'ext': 'mp4',
|
||||
'ext': 'flv',
|
||||
'title': 'Fun Jynx Maze solo',
|
||||
'thumbnail': 're:^https?://.*\.jpg$',
|
||||
'age_limit': 18,
|
||||
@ -44,39 +42,31 @@ class CliphunterIE(InfoExtractor):
|
||||
video_title = self._search_regex(
|
||||
r'mediaTitle = "([^"]+)"', webpage, 'title')
|
||||
|
||||
pl_fiji = self._search_regex(
|
||||
r'pl_fiji = \'([^\']+)\'', webpage, 'video data')
|
||||
pl_c_qual = self._search_regex(
|
||||
r'pl_c_qual = "(.)"', webpage, 'video quality')
|
||||
video_url = _decode(pl_fiji)
|
||||
formats = [{
|
||||
'url': video_url,
|
||||
'format_id': 'default-%s' % pl_c_qual,
|
||||
}]
|
||||
fmts = {}
|
||||
for fmt in ('mp4', 'flv'):
|
||||
fmt_list = self._parse_json(self._search_regex(
|
||||
r'var %sjson\s*=\s*(\[.*?\]);' % fmt, webpage, '%s formats' % fmt), video_id)
|
||||
for f in fmt_list:
|
||||
fmts[f['fname']] = _decode(f['sUrl'])
|
||||
|
||||
qualities_json = self._search_regex(
|
||||
r'var pl_qualities\s*=\s*(.*?);\n', webpage, 'quality info')
|
||||
qualities_data = json.loads(qualities_json)
|
||||
qualities = self._parse_json(self._search_regex(
|
||||
r'var player_btns\s*=\s*(.*?);\n', webpage, 'quality info'), video_id)
|
||||
|
||||
for i, t in enumerate(
|
||||
re.findall(r"pl_fiji_([a-z0-9]+)\s*=\s*'([^']+')", webpage)):
|
||||
quality_id, crypted_url = t
|
||||
video_url = _decode(crypted_url)
|
||||
formats = []
|
||||
for fname, url in fmts.items():
|
||||
f = {
|
||||
'format_id': quality_id,
|
||||
'url': video_url,
|
||||
'quality': i,
|
||||
'url': url,
|
||||
}
|
||||
if quality_id in qualities_data:
|
||||
qd = qualities_data[quality_id]
|
||||
m = re.match(
|
||||
r'''(?x)<b>(?P<width>[0-9]+)x(?P<height>[0-9]+)<\\/b>
|
||||
\s*\(\s*(?P<tbr>[0-9]+)\s*kb\\/s''', qd)
|
||||
if m:
|
||||
f['width'] = int(m.group('width'))
|
||||
f['height'] = int(m.group('height'))
|
||||
f['tbr'] = int(m.group('tbr'))
|
||||
if fname in qualities:
|
||||
qual = qualities[fname]
|
||||
f.update({
|
||||
'format_id': '%s_%sp' % (determine_ext(url), qual['h']),
|
||||
'width': qual['w'],
|
||||
'height': qual['h'],
|
||||
'tbr': qual['br'],
|
||||
})
|
||||
formats.append(f)
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
thumbnail = self._search_regex(
|
||||
|
@ -51,7 +51,7 @@ class CNNIE(InfoExtractor):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
path = mobj.group('path')
|
||||
page_title = mobj.group('title')
|
||||
info_url = 'http://cnn.com/video/data/3.0/%s/index.xml' % path
|
||||
info_url = 'http://edition.cnn.com/video/data/3.0/%s/index.xml' % path
|
||||
info = self._download_xml(info_url, page_title)
|
||||
|
||||
formats = []
|
||||
@ -143,13 +143,13 @@ class CNNArticleIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:(?:edition|www)\.)?cnn\.com/(?!video/)'
|
||||
_TEST = {
|
||||
'url': 'http://www.cnn.com/2014/12/21/politics/obama-north-koreas-hack-not-war-but-cyber-vandalism/',
|
||||
'md5': '275b326f85d80dff7592a9820f5dc887',
|
||||
'md5': '689034c2a3d9c6dc4aa72d65a81efd01',
|
||||
'info_dict': {
|
||||
'id': 'bestoftv/2014/12/21/sotu-crowley-president-obama-north-korea-not-going-to-be-intimidated.cnn',
|
||||
'id': 'bestoftv/2014/12/21/ip-north-korea-obama.cnn',
|
||||
'ext': 'mp4',
|
||||
'title': 'Obama: We\'re not going to be intimidated',
|
||||
'description': 'md5:e735586f3dc936075fa654a4d91b21f9',
|
||||
'upload_date': '20141220',
|
||||
'title': 'Obama: Cyberattack not an act of war',
|
||||
'description': 'md5:51ce6750450603795cad0cdfbd7d05c5',
|
||||
'upload_date': '20141221',
|
||||
},
|
||||
'add_ie': ['CNN'],
|
||||
}
|
||||
|
92
youtube_dl/extractor/collegerama.py
Normal file
92
youtube_dl/extractor/collegerama.py
Normal file
@ -0,0 +1,92 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import json
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_urllib_request
|
||||
from ..utils import (
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
)
|
||||
|
||||
|
||||
class CollegeRamaIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://collegerama\.tudelft\.nl/Mediasite/Play/(?P<id>[\da-f]+)'
|
||||
_TESTS = [
|
||||
{
|
||||
'url': 'https://collegerama.tudelft.nl/Mediasite/Play/585a43626e544bdd97aeb71a0ec907a01d',
|
||||
'md5': '481fda1c11f67588c0d9d8fbdced4e39',
|
||||
'info_dict': {
|
||||
'id': '585a43626e544bdd97aeb71a0ec907a01d',
|
||||
'ext': 'mp4',
|
||||
'title': 'Een nieuwe wereld: waarden, bewustzijn en techniek van de mensheid 2.0.',
|
||||
'description': '',
|
||||
'thumbnail': 're:^https?://.*\.jpg$',
|
||||
'duration': 7713.088,
|
||||
'timestamp': 1413309600,
|
||||
'upload_date': '20141014',
|
||||
},
|
||||
},
|
||||
{
|
||||
'url': 'https://collegerama.tudelft.nl/Mediasite/Play/86a9ea9f53e149079fbdb4202b521ed21d?catalog=fd32fd35-6c99-466c-89d4-cd3c431bc8a4',
|
||||
'md5': 'ef1fdded95bdf19b12c5999949419c92',
|
||||
'info_dict': {
|
||||
'id': '86a9ea9f53e149079fbdb4202b521ed21d',
|
||||
'ext': 'wmv',
|
||||
'title': '64ste Vakantiecursus: Afvalwater',
|
||||
'description': 'md5:7fd774865cc69d972f542b157c328305',
|
||||
'duration': 10853,
|
||||
'timestamp': 1326446400,
|
||||
'upload_date': '20120113',
|
||||
},
|
||||
},
|
||||
]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
player_options_request = {
|
||||
"getPlayerOptionsRequest": {
|
||||
"ResourceId": video_id,
|
||||
"QueryString": "",
|
||||
}
|
||||
}
|
||||
|
||||
request = compat_urllib_request.Request(
|
||||
'http://collegerama.tudelft.nl/Mediasite/PlayerService/PlayerService.svc/json/GetPlayerOptions',
|
||||
json.dumps(player_options_request))
|
||||
request.add_header('Content-Type', 'application/json')
|
||||
|
||||
player_options = self._download_json(request, video_id)
|
||||
|
||||
presentation = player_options['d']['Presentation']
|
||||
title = presentation['Title']
|
||||
description = presentation.get('Description')
|
||||
thumbnail = None
|
||||
duration = float_or_none(presentation.get('Duration'), 1000)
|
||||
timestamp = int_or_none(presentation.get('UnixTime'), 1000)
|
||||
|
||||
formats = []
|
||||
for stream in presentation['Streams']:
|
||||
for video in stream['VideoUrls']:
|
||||
thumbnail_url = stream.get('ThumbnailUrl')
|
||||
if thumbnail_url:
|
||||
thumbnail = 'http://collegerama.tudelft.nl' + thumbnail_url
|
||||
format_id = video['MediaType']
|
||||
if format_id == 'SS':
|
||||
continue
|
||||
formats.append({
|
||||
'url': video['Location'],
|
||||
'format_id': format_id,
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
'duration': duration,
|
||||
'timestamp': timestamp,
|
||||
'formats': formats,
|
||||
}
|
@ -34,12 +34,12 @@ class ComedyCentralIE(MTVServicesInfoExtractor):
|
||||
|
||||
class ComedyCentralShowsIE(MTVServicesInfoExtractor):
|
||||
IE_DESC = 'The Daily Show / The Colbert Report'
|
||||
# urls can be abbreviations like :thedailyshow or :colbert
|
||||
# urls can be abbreviations like :thedailyshow
|
||||
# urls for episodes like:
|
||||
# or urls for clips like: http://www.thedailyshow.com/watch/mon-december-10-2012/any-given-gun-day
|
||||
# or: http://www.colbertnation.com/the-colbert-report-videos/421667/november-29-2012/moon-shattering-news
|
||||
# or: http://www.colbertnation.com/the-colbert-report-collections/422008/festival-of-lights/79524
|
||||
_VALID_URL = r'''(?x)^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport)
|
||||
_VALID_URL = r'''(?x)^(:(?P<shortname>tds|thedailyshow)
|
||||
|https?://(:www\.)?
|
||||
(?P<showname>thedailyshow|thecolbertreport)\.(?:cc\.)?com/
|
||||
((?:full-)?episodes/(?:[0-9a-z]{6}/)?(?P<episode>.*)|
|
||||
@ -49,7 +49,9 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor):
|
||||
|(watch/(?P<date>[^/]*)/(?P<tdstitle>.*))
|
||||
)|
|
||||
(?P<interview>
|
||||
extended-interviews/(?P<interID>[0-9a-z]+)/(?:playlist_tds_extended_)?(?P<interview_title>.*?)(/.*?)?)))
|
||||
extended-interviews/(?P<interID>[0-9a-z]+)/
|
||||
(?:playlist_tds_extended_)?(?P<interview_title>[^/?#]*?)
|
||||
(?:/[^/?#]?|[?#]|$))))
|
||||
'''
|
||||
_TESTS = [{
|
||||
'url': 'http://thedailyshow.cc.com/watch/thu-december-13-2012/kristen-stewart',
|
||||
@ -62,6 +64,38 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor):
|
||||
'uploader': 'thedailyshow',
|
||||
'title': 'thedailyshow kristen-stewart part 1',
|
||||
}
|
||||
}, {
|
||||
'url': 'http://thedailyshow.cc.com/extended-interviews/b6364d/sarah-chayes-extended-interview',
|
||||
'info_dict': {
|
||||
'id': 'sarah-chayes-extended-interview',
|
||||
'description': 'Carnegie Endowment Senior Associate Sarah Chayes discusses how corrupt institutions function throughout the world in her book "Thieves of State: Why Corruption Threatens Global Security."',
|
||||
'title': 'thedailyshow Sarah Chayes Extended Interview',
|
||||
},
|
||||
'playlist': [
|
||||
{
|
||||
'info_dict': {
|
||||
'id': '0baad492-cbec-4ec1-9e50-ad91c291127f',
|
||||
'ext': 'mp4',
|
||||
'upload_date': '20150129',
|
||||
'description': 'Carnegie Endowment Senior Associate Sarah Chayes discusses how corrupt institutions function throughout the world in her book "Thieves of State: Why Corruption Threatens Global Security."',
|
||||
'uploader': 'thedailyshow',
|
||||
'title': 'thedailyshow sarah-chayes-extended-interview part 1',
|
||||
},
|
||||
},
|
||||
{
|
||||
'info_dict': {
|
||||
'id': '1e4fb91b-8ce7-4277-bd7c-98c9f1bbd283',
|
||||
'ext': 'mp4',
|
||||
'upload_date': '20150129',
|
||||
'description': 'Carnegie Endowment Senior Associate Sarah Chayes discusses how corrupt institutions function throughout the world in her book "Thieves of State: Why Corruption Threatens Global Security."',
|
||||
'uploader': 'thedailyshow',
|
||||
'title': 'thedailyshow sarah-chayes-extended-interview part 2',
|
||||
},
|
||||
},
|
||||
],
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
'url': 'http://thedailyshow.cc.com/extended-interviews/xm3fnq/andrew-napolitano-extended-interview',
|
||||
'only_matching': True,
|
||||
@ -230,6 +264,7 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor):
|
||||
|
||||
return {
|
||||
'_type': 'playlist',
|
||||
'id': epTitle,
|
||||
'entries': entries,
|
||||
'title': show_name + ' ' + title,
|
||||
'description': description,
|
||||
|
@ -14,6 +14,7 @@ import xml.etree.ElementTree
|
||||
|
||||
from ..compat import (
|
||||
compat_cookiejar,
|
||||
compat_HTTPError,
|
||||
compat_http_client,
|
||||
compat_urllib_error,
|
||||
compat_urllib_parse_urlparse,
|
||||
@ -21,10 +22,12 @@ from ..compat import (
|
||||
compat_str,
|
||||
)
|
||||
from ..utils import (
|
||||
age_restricted,
|
||||
clean_html,
|
||||
compiled_regex_type,
|
||||
ExtractorError,
|
||||
float_or_none,
|
||||
HEADRequest,
|
||||
int_or_none,
|
||||
RegexNotFoundError,
|
||||
sanitize_filename,
|
||||
@ -86,12 +89,15 @@ class InfoExtractor(object):
|
||||
* player_url SWF Player URL (used for rtmpdump).
|
||||
* protocol The protocol that will be used for the actual
|
||||
download, lower-case.
|
||||
"http", "https", "rtsp", "rtmp", "m3u8" or so.
|
||||
"http", "https", "rtsp", "rtmp", "rtmpe",
|
||||
"m3u8", or "m3u8_native".
|
||||
* preference Order number of this format. If this field is
|
||||
present and not None, the formats get sorted
|
||||
by this field, regardless of all other values.
|
||||
-1 for default (order by other properties),
|
||||
-2 or smaller for less than default.
|
||||
< -1000 to hide the format (if there is
|
||||
another one which is strictly better)
|
||||
* language_preference Is this in the correct requested
|
||||
language?
|
||||
10 if it's what the URL is about,
|
||||
@ -105,12 +111,17 @@ class InfoExtractor(object):
|
||||
(quality takes higher priority)
|
||||
-1 for default (order by other properties),
|
||||
-2 or smaller for less than default.
|
||||
* http_referer HTTP Referer header value to set.
|
||||
* http_method HTTP method to use for the download.
|
||||
* http_headers A dictionary of additional HTTP headers
|
||||
to add to the request.
|
||||
* http_post_data Additional data to send with a POST
|
||||
request.
|
||||
* stretched_ratio If given and not 1, indicates that the
|
||||
video's pixels are not square.
|
||||
width : height ratio as float.
|
||||
* no_resume The server does not support resuming the
|
||||
(HTTP or RTMP) download. Boolean.
|
||||
|
||||
url: Final video URL.
|
||||
ext: Video filename extension.
|
||||
format: The video format, defaults to ext (used for --get-format)
|
||||
@ -124,7 +135,9 @@ class InfoExtractor(object):
|
||||
something like "4234987", title "Dancing naked mole rats",
|
||||
and display_id "dancing-naked-mole-rats"
|
||||
thumbnails: A list of dictionaries, with the following entries:
|
||||
* "id" (optional, string) - Thumbnail format ID
|
||||
* "url"
|
||||
* "preference" (optional, int) - quality of the image
|
||||
* "width" (optional, int)
|
||||
* "height" (optional, int)
|
||||
* "resolution" (optional, string "{width}x{height"},
|
||||
@ -144,6 +157,17 @@ class InfoExtractor(object):
|
||||
like_count: Number of positive ratings of the video
|
||||
dislike_count: Number of negative ratings of the video
|
||||
comment_count: Number of comments on the video
|
||||
comments: A list of comments, each with one or more of the following
|
||||
properties (all but one of text or html optional):
|
||||
* "author" - human-readable name of the comment author
|
||||
* "author_id" - user ID of the comment author
|
||||
* "id" - Comment ID
|
||||
* "html" - Comment as HTML
|
||||
* "text" - Plain text of the comment
|
||||
* "timestamp" - UNIX timestamp of comment
|
||||
* "parent" - ID of the comment this one is replying to.
|
||||
Set to "root" to indicate that this is a
|
||||
comment to the original video.
|
||||
age_limit: Age restriction for the video, as an integer (years)
|
||||
webpage_url: The url to the video webpage, if given to youtube-dl it
|
||||
should allow to get the same result again. (It will be set
|
||||
@ -362,9 +386,19 @@ class InfoExtractor(object):
|
||||
|
||||
return content
|
||||
|
||||
def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True):
|
||||
def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5):
|
||||
""" Returns the data of the page as a string """
|
||||
res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal)
|
||||
success = False
|
||||
try_count = 0
|
||||
while success is False:
|
||||
try:
|
||||
res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal)
|
||||
success = True
|
||||
except compat_http_client.IncompleteRead as e:
|
||||
try_count += 1
|
||||
if try_count >= tries:
|
||||
raise e
|
||||
self._sleep(timeout, video_id)
|
||||
if res is False:
|
||||
return res
|
||||
else:
|
||||
@ -591,7 +625,7 @@ class InfoExtractor(object):
|
||||
return self._html_search_regex(
|
||||
r'''(?isx)<meta
|
||||
(?=[^>]+(?:itemprop|name|property)=(["\']?)%s\1)
|
||||
[^>]+content=(["\'])(?P<content>.*?)\1''' % re.escape(name),
|
||||
[^>]+?content=(["\'])(?P<content>.*?)\2''' % re.escape(name),
|
||||
html, display_name, fatal=fatal, group='content', **kwargs)
|
||||
|
||||
def _dc_search_uploader(self, html):
|
||||
@ -685,6 +719,27 @@ class InfoExtractor(object):
|
||||
)
|
||||
formats.sort(key=_formats_key)
|
||||
|
||||
def _check_formats(self, formats, video_id):
|
||||
if formats:
|
||||
formats[:] = filter(
|
||||
lambda f: self._is_valid_url(
|
||||
f['url'], video_id,
|
||||
item='%s video format' % f.get('format_id') if f.get('format_id') else 'video'),
|
||||
formats)
|
||||
|
||||
def _is_valid_url(self, url, video_id, item='video'):
|
||||
try:
|
||||
self._request_webpage(
|
||||
HEADRequest(url), video_id,
|
||||
'Checking %s URL' % item)
|
||||
return True
|
||||
except ExtractorError as e:
|
||||
if isinstance(e.cause, compat_HTTPError):
|
||||
self.report_warning(
|
||||
'%s URL is invalid, skipping' % item, video_id)
|
||||
return False
|
||||
raise
|
||||
|
||||
def http_scheme(self):
|
||||
""" Either "http:" or "https:", depending on the user's preferences """
|
||||
return (
|
||||
@ -715,8 +770,14 @@ class InfoExtractor(object):
|
||||
'Unable to download f4m manifest')
|
||||
|
||||
formats = []
|
||||
manifest_version = '1.0'
|
||||
media_nodes = manifest.findall('{http://ns.adobe.com/f4m/1.0}media')
|
||||
if not media_nodes:
|
||||
manifest_version = '2.0'
|
||||
media_nodes = manifest.findall('{http://ns.adobe.com/f4m/2.0}media')
|
||||
for i, media_el in enumerate(media_nodes):
|
||||
if manifest_version == '2.0':
|
||||
manifest_url = '/'.join(manifest_url.split('/')[:-1]) + '/' + media_el.attrib.get('href')
|
||||
tbr = int_or_none(media_el.attrib.get('bitrate'))
|
||||
format_id = 'f4m-%d' % (i if tbr is None else tbr)
|
||||
formats.append({
|
||||
@ -875,6 +936,35 @@ class InfoExtractor(object):
|
||||
None, '/', True, False, expire_time, '', None, None, None)
|
||||
self._downloader.cookiejar.set_cookie(cookie)
|
||||
|
||||
def get_testcases(self, include_onlymatching=False):
|
||||
t = getattr(self, '_TEST', None)
|
||||
if t:
|
||||
assert not hasattr(self, '_TESTS'), \
|
||||
'%s has _TEST and _TESTS' % type(self).__name__
|
||||
tests = [t]
|
||||
else:
|
||||
tests = getattr(self, '_TESTS', [])
|
||||
for t in tests:
|
||||
if not include_onlymatching and t.get('only_matching', False):
|
||||
continue
|
||||
t['name'] = type(self).__name__[:-len('IE')]
|
||||
yield t
|
||||
|
||||
def is_suitable(self, age_limit):
|
||||
""" Test whether the extractor is generally suitable for the given
|
||||
age limit (i.e. pornographic sites are not, all others usually are) """
|
||||
|
||||
any_restricted = False
|
||||
for tc in self.get_testcases(include_onlymatching=False):
|
||||
if 'playlist' in tc:
|
||||
tc = tc['playlist'][0]
|
||||
is_restricted = age_restricted(
|
||||
tc.get('info_dict', {}).get('age_limit'), age_limit)
|
||||
if not is_restricted:
|
||||
return True
|
||||
any_restricted = any_restricted or is_restricted
|
||||
return not any_restricted
|
||||
|
||||
|
||||
class SearchInfoExtractor(InfoExtractor):
|
||||
"""
|
||||
|
@ -228,7 +228,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
|
||||
video_thumbnail = self._search_regex(r'<episode_image_url>([^<]+)', playerdata, 'thumbnail', fatal=False)
|
||||
|
||||
formats = []
|
||||
for fmt in re.findall(r'\?p([0-9]{3,4})=1', webpage):
|
||||
for fmt in re.findall(r'showmedia\.([0-9]{3,4})p', webpage):
|
||||
stream_quality, stream_format = self._FORMAT_IDS[fmt]
|
||||
video_format = fmt + 'p'
|
||||
streamdata_req = compat_urllib_request.Request('http://www.crunchyroll.com/xml/')
|
||||
|
93
youtube_dl/extractor/ctsnews.py
Normal file
93
youtube_dl/extractor/ctsnews.py
Normal file
@ -0,0 +1,93 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import parse_iso8601, ExtractorError
|
||||
|
||||
|
||||
class CtsNewsIE(InfoExtractor):
|
||||
# https connection failed (Connection reset)
|
||||
_VALID_URL = r'http://news\.cts\.com\.tw/[a-z]+/[a-z]+/\d+/(?P<id>\d+)\.html'
|
||||
_TESTS = [{
|
||||
'url': 'http://news.cts.com.tw/cts/international/201501/201501291578109.html',
|
||||
'md5': 'a9875cb790252b08431186d741beaabe',
|
||||
'info_dict': {
|
||||
'id': '201501291578109',
|
||||
'ext': 'mp4',
|
||||
'title': '以色列.真主黨交火 3人死亡',
|
||||
'description': 'md5:95e9b295c898b7ff294f09d450178d7d',
|
||||
'timestamp': 1422528540,
|
||||
'upload_date': '20150129',
|
||||
}
|
||||
}, {
|
||||
# News count not appear on page but still available in database
|
||||
'url': 'http://news.cts.com.tw/cts/international/201309/201309031304098.html',
|
||||
'md5': '3aee7e0df7cdff94e43581f54c22619e',
|
||||
'info_dict': {
|
||||
'id': '201309031304098',
|
||||
'ext': 'mp4',
|
||||
'title': '韓國31歲童顏男 貌如十多歲小孩',
|
||||
'description': 'md5:f183feeba3752b683827aab71adad584',
|
||||
'thumbnail': 're:^https?://.*\.jpg$',
|
||||
'timestamp': 1378205880,
|
||||
'upload_date': '20130903',
|
||||
}
|
||||
}, {
|
||||
# With Youtube embedded video
|
||||
'url': 'http://news.cts.com.tw/cts/money/201501/201501291578003.html',
|
||||
'md5': '1d842c771dc94c8c3bca5af2cc1db9c5',
|
||||
'add_ie': ['Youtube'],
|
||||
'info_dict': {
|
||||
'id': 'OVbfO7d0_hQ',
|
||||
'ext': 'mp4',
|
||||
'title': 'iPhone6熱銷 蘋果財報亮眼',
|
||||
'description': 'md5:f395d4f485487bb0f992ed2c4b07aa7d',
|
||||
'thumbnail': 're:^https?://.*\.jpg$',
|
||||
'upload_date': '20150128',
|
||||
'uploader_id': 'TBSCTS',
|
||||
'uploader': '中華電視公司',
|
||||
}
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
news_id = self._match_id(url)
|
||||
page = self._download_webpage(url, news_id)
|
||||
|
||||
if self._search_regex(r'(CTSPlayer2)', page, 'CTSPlayer2 identifier', default=None):
|
||||
feed_url = self._html_search_regex(
|
||||
r'(http://news\.cts\.com\.tw/action/mp4feed\.php\?news_id=\d+)',
|
||||
page, 'feed url')
|
||||
video_url = self._download_webpage(
|
||||
feed_url, news_id, note='Fetching feed')
|
||||
else:
|
||||
self.to_screen('Not CTSPlayer video, trying Youtube...')
|
||||
youtube_url = self._search_regex(
|
||||
r'src="(//www\.youtube\.com/embed/[^"]+)"', page, 'youtube url',
|
||||
default=None)
|
||||
if not youtube_url:
|
||||
raise ExtractorError('The news includes no videos!', expected=True)
|
||||
|
||||
return {
|
||||
'_type': 'url',
|
||||
'url': youtube_url,
|
||||
'ie_key': 'Youtube',
|
||||
}
|
||||
|
||||
description = self._html_search_meta('description', page)
|
||||
title = self._html_search_meta('title', page)
|
||||
thumbnail = self._html_search_meta('image', page)
|
||||
|
||||
datetime_str = self._html_search_regex(
|
||||
r'(\d{4}/\d{2}/\d{2} \d{2}:\d{2})', page, 'date and time')
|
||||
# Transform into ISO 8601 format with timezone info
|
||||
datetime_str = datetime_str.replace('/', '-') + ':00+0800'
|
||||
timestamp = parse_iso8601(datetime_str, delimiter=' ')
|
||||
|
||||
return {
|
||||
'id': news_id,
|
||||
'url': video_url,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
'timestamp': timestamp,
|
||||
}
|
57
youtube_dl/extractor/dctp.py
Normal file
57
youtube_dl/extractor/dctp.py
Normal file
@ -0,0 +1,57 @@
|
||||
# encoding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_str
|
||||
|
||||
|
||||
class DctpTvIE(InfoExtractor):
|
||||
_VALID_URL = r'http://www.dctp.tv/(#/)?filme/(?P<id>.+?)/$'
|
||||
_TEST = {
|
||||
'url': 'http://www.dctp.tv/filme/videoinstallation-fuer-eine-kaufhausfassade/',
|
||||
'info_dict': {
|
||||
'id': '1324',
|
||||
'display_id': 'videoinstallation-fuer-eine-kaufhausfassade',
|
||||
'ext': 'flv',
|
||||
'title': 'Videoinstallation für eine Kaufhausfassade'
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
base_url = 'http://dctp-ivms2-restapi.s3.amazonaws.com/'
|
||||
version_json = self._download_json(
|
||||
base_url + 'version.json',
|
||||
video_id, note='Determining file version')
|
||||
version = version_json['version_name']
|
||||
info_json = self._download_json(
|
||||
'{0}{1}/restapi/slugs/{2}.json'.format(base_url, version, video_id),
|
||||
video_id, note='Fetching object ID')
|
||||
object_id = compat_str(info_json['object_id'])
|
||||
meta_json = self._download_json(
|
||||
'{0}{1}/restapi/media/{2}.json'.format(base_url, version, object_id),
|
||||
video_id, note='Downloading metadata')
|
||||
uuid = meta_json['uuid']
|
||||
title = meta_json['title']
|
||||
wide = meta_json['is_wide']
|
||||
if wide:
|
||||
ratio = '16x9'
|
||||
else:
|
||||
ratio = '4x3'
|
||||
play_path = 'mp4:{0}_dctp_0500_{1}.m4v'.format(uuid, ratio)
|
||||
|
||||
servers_json = self._download_json(
|
||||
'http://www.dctp.tv/streaming_servers/',
|
||||
video_id, note='Downloading server list')
|
||||
url = servers_json[0]['endpoint']
|
||||
|
||||
return {
|
||||
'id': object_id,
|
||||
'title': title,
|
||||
'format': 'rtmp',
|
||||
'url': url,
|
||||
'play_path': play_path,
|
||||
'rtmp_real_time': True,
|
||||
'ext': 'flv',
|
||||
'display_id': video_id
|
||||
}
|
@ -1,40 +1,38 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
import json
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
||||
|
||||
class DefenseGouvFrIE(InfoExtractor):
|
||||
IE_NAME = 'defense.gouv.fr'
|
||||
_VALID_URL = (r'http://.*?\.defense\.gouv\.fr/layout/set/'
|
||||
r'ligthboxvideo/base-de-medias/webtv/(.*)')
|
||||
_VALID_URL = r'http://.*?\.defense\.gouv\.fr/layout/set/ligthboxvideo/base-de-medias/webtv/(?P<id>[^/?#]*)'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://www.defense.gouv.fr/layout/set/ligthboxvideo/base-de-medias/webtv/attaque-chimique-syrienne-du-21-aout-2013-1',
|
||||
'file': '11213.mp4',
|
||||
'md5': '75bba6124da7e63d2d60b5244ec9430c',
|
||||
"info_dict": {
|
||||
"title": "attaque-chimique-syrienne-du-21-aout-2013-1"
|
||||
'info_dict': {
|
||||
'id': '11213',
|
||||
'ext': 'mp4',
|
||||
'title': 'attaque-chimique-syrienne-du-21-aout-2013-1'
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
title = re.match(self._VALID_URL, url).group(1)
|
||||
title = self._match_id(url)
|
||||
webpage = self._download_webpage(url, title)
|
||||
|
||||
video_id = self._search_regex(
|
||||
r"flashvars.pvg_id=\"(\d+)\";",
|
||||
webpage, 'ID')
|
||||
|
||||
json_url = ('http://static.videos.gouv.fr/brightcovehub/export/json/'
|
||||
+ video_id)
|
||||
info = self._download_webpage(json_url, title,
|
||||
'Downloading JSON config')
|
||||
video_url = json.loads(info)['renditions'][0]['url']
|
||||
info = self._download_json(json_url, title, 'Downloading JSON config')
|
||||
video_url = info['renditions'][0]['url']
|
||||
|
||||
return {'id': video_id,
|
||||
'ext': 'mp4',
|
||||
'url': video_url,
|
||||
'title': title,
|
||||
}
|
||||
return {
|
||||
'id': video_id,
|
||||
'ext': 'mp4',
|
||||
'url': video_url,
|
||||
'title': title,
|
||||
}
|
||||
|
@ -1,47 +1,45 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
import json
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
parse_iso8601,
|
||||
int_or_none,
|
||||
)
|
||||
|
||||
|
||||
class DiscoveryIE(InfoExtractor):
|
||||
_VALID_URL = r'http://www\.discovery\.com\/[a-zA-Z0-9\-]*/[a-zA-Z0-9\-]*/videos/(?P<id>[a-zA-Z0-9\-]*)(.htm)?'
|
||||
_VALID_URL = r'http://www\.discovery\.com\/[a-zA-Z0-9\-]*/[a-zA-Z0-9\-]*/videos/(?P<id>[a-zA-Z0-9_\-]*)(?:\.htm)?'
|
||||
_TEST = {
|
||||
'url': 'http://www.discovery.com/tv-shows/mythbusters/videos/mission-impossible-outtakes.htm',
|
||||
'md5': 'e12614f9ee303a6ccef415cb0793eba2',
|
||||
'md5': '3c69d77d9b0d82bfd5e5932a60f26504',
|
||||
'info_dict': {
|
||||
'id': '614784',
|
||||
'ext': 'mp4',
|
||||
'title': 'MythBusters: Mission Impossible Outtakes',
|
||||
'id': 'mission-impossible-outtakes',
|
||||
'ext': 'flv',
|
||||
'title': 'Mission Impossible Outtakes',
|
||||
'description': ('Watch Jamie Hyneman and Adam Savage practice being'
|
||||
' each other -- to the point of confusing Jamie\'s dog -- and '
|
||||
'don\'t miss Adam moon-walking as Jamie ... behind Jamie\'s'
|
||||
' back.'),
|
||||
'duration': 156,
|
||||
'timestamp': 1303099200,
|
||||
'upload_date': '20110418',
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
video_list_json = self._search_regex(r'var videoListJSON = ({.*?});',
|
||||
webpage, 'video list', flags=re.DOTALL)
|
||||
video_list = json.loads(video_list_json)
|
||||
info = video_list['clips'][0]
|
||||
formats = []
|
||||
for f in info['mp4']:
|
||||
formats.append(
|
||||
{'url': f['src'], 'ext': 'mp4', 'tbr': int(f['bitrate'][:-1])})
|
||||
info = self._parse_json(self._search_regex(
|
||||
r'(?s)<script type="application/ld\+json">(.*?)</script>',
|
||||
webpage, 'video info'), video_id)
|
||||
|
||||
return {
|
||||
'id': info['contentId'],
|
||||
'title': video_list['name'],
|
||||
'formats': formats,
|
||||
'description': info['videoCaption'],
|
||||
'thumbnail': info.get('videoStillURL') or info.get('thumbnailURL'),
|
||||
'duration': info['duration'],
|
||||
'id': video_id,
|
||||
'title': info['name'],
|
||||
'url': info['contentURL'],
|
||||
'description': info.get('description'),
|
||||
'thumbnail': info.get('thumbnailUrl'),
|
||||
'timestamp': parse_iso8601(info.get('uploadDate')),
|
||||
'duration': int_or_none(info.get('duration')),
|
||||
}
|
||||
|
131
youtube_dl/extractor/drbonanza.py
Normal file
131
youtube_dl/extractor/drbonanza.py
Normal file
@ -0,0 +1,131 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import json
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
parse_iso8601,
|
||||
)
|
||||
|
||||
|
||||
class DRBonanzaIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?dr\.dk/bonanza/(?:[^/]+/)+(?:[^/])+?(?:assetId=(?P<id>\d+))?(?:[#&]|$)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://www.dr.dk/bonanza/serie/portraetter/Talkshowet.htm?assetId=65517',
|
||||
'md5': 'fe330252ddea607635cf2eb2c99a0af3',
|
||||
'info_dict': {
|
||||
'id': '65517',
|
||||
'ext': 'mp4',
|
||||
'title': 'Talkshowet - Leonard Cohen',
|
||||
'description': 'md5:8f34194fb30cd8c8a30ad8b27b70c0ca',
|
||||
'thumbnail': 're:^https?://.*\.(?:gif|jpg)$',
|
||||
'timestamp': 1295537932,
|
||||
'upload_date': '20110120',
|
||||
'duration': 3664,
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.dr.dk/bonanza/radio/serie/sport/fodbold.htm?assetId=59410',
|
||||
'md5': '6dfe039417e76795fb783c52da3de11d',
|
||||
'info_dict': {
|
||||
'id': '59410',
|
||||
'ext': 'mp3',
|
||||
'title': 'EM fodbold 1992 Danmark - Tyskland finale Transmission',
|
||||
'description': 'md5:501e5a195749480552e214fbbed16c4e',
|
||||
'thumbnail': 're:^https?://.*\.(?:gif|jpg)$',
|
||||
'timestamp': 1223274900,
|
||||
'upload_date': '20081006',
|
||||
'duration': 7369,
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
url_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, url_id)
|
||||
|
||||
if url_id:
|
||||
info = json.loads(self._html_search_regex(r'({.*?%s.*})' % url_id, webpage, 'json'))
|
||||
else:
|
||||
# Just fetch the first video on that page
|
||||
info = json.loads(self._html_search_regex(r'bonanzaFunctions.newPlaylist\(({.*})\)', webpage, 'json'))
|
||||
|
||||
asset_id = str(info['AssetId'])
|
||||
title = info['Title'].rstrip(' \'\"-,.:;!?')
|
||||
duration = int_or_none(info.get('Duration'), scale=1000)
|
||||
# First published online. "FirstPublished" contains the date for original airing.
|
||||
timestamp = parse_iso8601(
|
||||
re.sub(r'\.\d+$', '', info['Created']))
|
||||
|
||||
def parse_filename_info(url):
|
||||
match = re.search(r'/\d+_(?P<width>\d+)x(?P<height>\d+)x(?P<bitrate>\d+)K\.(?P<ext>\w+)$', url)
|
||||
if match:
|
||||
return {
|
||||
'width': int(match.group('width')),
|
||||
'height': int(match.group('height')),
|
||||
'vbr': int(match.group('bitrate')),
|
||||
'ext': match.group('ext')
|
||||
}
|
||||
match = re.search(r'/\d+_(?P<bitrate>\d+)K\.(?P<ext>\w+)$', url)
|
||||
if match:
|
||||
return {
|
||||
'vbr': int(match.group('bitrate')),
|
||||
'ext': match.group(2)
|
||||
}
|
||||
return {}
|
||||
|
||||
video_types = ['VideoHigh', 'VideoMid', 'VideoLow']
|
||||
preferencemap = {
|
||||
'VideoHigh': -1,
|
||||
'VideoMid': -2,
|
||||
'VideoLow': -3,
|
||||
'Audio': -4,
|
||||
}
|
||||
|
||||
formats = []
|
||||
for file in info['Files']:
|
||||
if info['Type'] == "Video":
|
||||
if file['Type'] in video_types:
|
||||
format = parse_filename_info(file['Location'])
|
||||
format.update({
|
||||
'url': file['Location'],
|
||||
'format_id': file['Type'].replace('Video', ''),
|
||||
'preference': preferencemap.get(file['Type'], -10),
|
||||
})
|
||||
formats.append(format)
|
||||
elif file['Type'] == "Thumb":
|
||||
thumbnail = file['Location']
|
||||
elif info['Type'] == "Audio":
|
||||
if file['Type'] == "Audio":
|
||||
format = parse_filename_info(file['Location'])
|
||||
format.update({
|
||||
'url': file['Location'],
|
||||
'format_id': file['Type'],
|
||||
'vcodec': 'none',
|
||||
})
|
||||
formats.append(format)
|
||||
elif file['Type'] == "Thumb":
|
||||
thumbnail = file['Location']
|
||||
|
||||
description = '%s\n%s\n%s\n' % (
|
||||
info['Description'], info['Actors'], info['Colophon'])
|
||||
|
||||
for f in formats:
|
||||
f['url'] = f['url'].replace('rtmp://vod-bonanza.gss.dr.dk/bonanza/', 'http://vodfiles.dr.dk/')
|
||||
f['url'] = f['url'].replace('mp4:bonanza', 'bonanza')
|
||||
self._sort_formats(formats)
|
||||
|
||||
display_id = re.sub(r'[^\w\d-]', '', re.sub(r' ', '-', title.lower())) + '-' + asset_id
|
||||
display_id = re.sub(r'-+', '-', display_id)
|
||||
|
||||
return {
|
||||
'id': asset_id,
|
||||
'display_id': display_id,
|
||||
'title': title,
|
||||
'formats': formats,
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
'timestamp': timestamp,
|
||||
'duration': duration,
|
||||
}
|
@ -6,7 +6,7 @@ from ..utils import parse_iso8601
|
||||
|
||||
|
||||
class DRTVIE(SubtitlesInfoExtractor):
|
||||
_VALID_URL = r'http://(?:www\.)?dr\.dk/tv/se/(?:[^/]+/)+(?P<id>[\da-z-]+)(?:[/#?]|$)'
|
||||
_VALID_URL = r'https?://(?:www\.)?dr\.dk/tv/se/(?:[^/]+/)*(?P<id>[\da-z-]+)(?:[/#?]|$)'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://www.dr.dk/tv/se/partiets-mand/partiets-mand-7-8',
|
||||
@ -25,9 +25,15 @@ class DRTVIE(SubtitlesInfoExtractor):
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
programcard = self._download_json(
|
||||
'http://www.dr.dk/mu/programcard/expanded/%s' % video_id, video_id, 'Downloading video JSON')
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
video_id = self._search_regex(
|
||||
r'data-(?:material-identifier|episode-slug)="([^"]+)"',
|
||||
webpage, 'video id')
|
||||
|
||||
programcard = self._download_json(
|
||||
'http://www.dr.dk/mu/programcard/expanded/%s' % video_id,
|
||||
video_id, 'Downloading video JSON')
|
||||
data = programcard['Data'][0]
|
||||
|
||||
title = data['Title']
|
||||
@ -48,14 +54,20 @@ class DRTVIE(SubtitlesInfoExtractor):
|
||||
elif asset['Kind'] == 'VideoResource':
|
||||
duration = asset['DurationInMilliseconds'] / 1000.0
|
||||
restricted_to_denmark = asset['RestrictedToDenmark']
|
||||
spoken_subtitles = asset['Target'] == 'SpokenSubtitles'
|
||||
for link in asset['Links']:
|
||||
target = link['Target']
|
||||
uri = link['Uri']
|
||||
format_id = target
|
||||
preference = -1 if target == 'HDS' else -2
|
||||
if spoken_subtitles:
|
||||
preference -= 2
|
||||
format_id += '-spoken-subtitles'
|
||||
formats.append({
|
||||
'url': uri + '?hdcore=3.3.0&plugin=aasp-3.3.0.99.43' if target == 'HDS' else uri,
|
||||
'format_id': target,
|
||||
'format_id': format_id,
|
||||
'ext': link['FileFormat'],
|
||||
'preference': -1 if target == 'HDS' else -2,
|
||||
'preference': preference,
|
||||
})
|
||||
subtitles_list = asset.get('SubtitlesList')
|
||||
if isinstance(subtitles_list, list):
|
||||
|
@ -9,6 +9,9 @@ from .common import InfoExtractor
|
||||
from ..compat import (
|
||||
compat_str,
|
||||
)
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
)
|
||||
|
||||
|
||||
class EightTracksIE(InfoExtractor):
|
||||
@ -112,14 +115,29 @@ class EightTracksIE(InfoExtractor):
|
||||
session = str(random.randint(0, 1000000000))
|
||||
mix_id = data['id']
|
||||
track_count = data['tracks_count']
|
||||
duration = data['duration']
|
||||
avg_song_duration = float(duration) / track_count
|
||||
first_url = 'http://8tracks.com/sets/%s/play?player=sm&mix_id=%s&format=jsonh' % (session, mix_id)
|
||||
next_url = first_url
|
||||
entries = []
|
||||
|
||||
for i in range(track_count):
|
||||
api_json = self._download_webpage(
|
||||
next_url, playlist_id,
|
||||
note='Downloading song information %d/%d' % (i + 1, track_count),
|
||||
errnote='Failed to download song information')
|
||||
api_json = None
|
||||
download_tries = 0
|
||||
|
||||
while api_json is None:
|
||||
try:
|
||||
api_json = self._download_webpage(
|
||||
next_url, playlist_id,
|
||||
note='Downloading song information %d/%d' % (i + 1, track_count),
|
||||
errnote='Failed to download song information')
|
||||
except ExtractorError:
|
||||
if download_tries > 3:
|
||||
raise
|
||||
else:
|
||||
download_tries += 1
|
||||
self._sleep(avg_song_duration, playlist_id)
|
||||
|
||||
api_data = json.loads(api_json)
|
||||
track_data = api_data['set']['track']
|
||||
info = {
|
||||
@ -131,6 +149,7 @@ class EightTracksIE(InfoExtractor):
|
||||
'ext': 'm4a',
|
||||
}
|
||||
entries.append(info)
|
||||
|
||||
next_url = 'http://8tracks.com/sets/%s/next?player=sm&mix_id=%s&format=jsonh&track_id=%s' % (
|
||||
session, mix_id, track_data['id'])
|
||||
return {
|
||||
|
@ -1,7 +1,6 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
import json
|
||||
|
||||
from .common import InfoExtractor
|
||||
@ -12,32 +11,49 @@ from ..utils import (
|
||||
|
||||
|
||||
class EllenTVIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?ellentv\.com/videos/(?P<id>[a-z0-9_-]+)'
|
||||
_TEST = {
|
||||
_VALID_URL = r'https?://(?:www\.)?(?:ellentv|ellentube)\.com/videos/(?P<id>[a-z0-9_-]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.ellentv.com/videos/0-7jqrsr18/',
|
||||
'md5': 'e4af06f3bf0d5f471921a18db5764642',
|
||||
'info_dict': {
|
||||
'id': '0-7jqrsr18',
|
||||
'ext': 'mp4',
|
||||
'title': 'What\'s Wrong with These Photos? A Whole Lot',
|
||||
'description': 'md5:35f152dc66b587cf13e6d2cf4fa467f6',
|
||||
'timestamp': 1406876400,
|
||||
'upload_date': '20140801',
|
||||
}
|
||||
}
|
||||
}, {
|
||||
'url': 'http://ellentube.com/videos/0-dvzmabd5/',
|
||||
'md5': '98238118eaa2bbdf6ad7f708e3e4f4eb',
|
||||
'info_dict': {
|
||||
'id': '0-dvzmabd5',
|
||||
'ext': 'mp4',
|
||||
'title': '1 year old twin sister makes her brother laugh',
|
||||
'description': '1 year old twin sister makes her brother laugh',
|
||||
'timestamp': 1419542075,
|
||||
'upload_date': '20141225',
|
||||
}
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
video_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
video_url = self._html_search_meta('VideoURL', webpage, 'url')
|
||||
title = self._og_search_title(webpage, default=None) or self._search_regex(
|
||||
r'pageName\s*=\s*"([^"]+)"', webpage, 'title')
|
||||
description = self._html_search_meta(
|
||||
'description', webpage, 'description') or self._og_search_description(webpage)
|
||||
timestamp = parse_iso8601(self._search_regex(
|
||||
r'<span class="publish-date"><time datetime="([^"]+)">',
|
||||
webpage, 'timestamp'))
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': self._og_search_title(webpage),
|
||||
'url': self._html_search_meta('VideoURL', webpage, 'url'),
|
||||
'url': video_url,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'timestamp': timestamp,
|
||||
}
|
||||
|
||||
@ -55,8 +71,7 @@ class EllenTVClipsIE(InfoExtractor):
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
playlist_id = mobj.group('id')
|
||||
playlist_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, playlist_id)
|
||||
playlist = self._extract_playlist(webpage)
|
||||
|
@ -1,8 +1,6 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import unified_strdate
|
||||
|
||||
@ -24,9 +22,7 @@ class ElPaisIE(InfoExtractor):
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
prefix = self._html_search_regex(
|
||||
|
@ -5,6 +5,7 @@ import hashlib
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import (
|
||||
compat_urllib_parse,
|
||||
compat_urllib_request,
|
||||
compat_urlparse,
|
||||
)
|
||||
@ -16,7 +17,8 @@ from ..utils import (
|
||||
class FC2IE(InfoExtractor):
|
||||
_VALID_URL = r'^http://video\.fc2\.com/(?:[^/]+/)?content/(?P<id>[^/]+)'
|
||||
IE_NAME = 'fc2'
|
||||
_TEST = {
|
||||
_NETRC_MACHINE = 'fc2'
|
||||
_TESTS = [{
|
||||
'url': 'http://video.fc2.com/en/content/20121103kUan1KHs',
|
||||
'md5': 'a6ebe8ebe0396518689d963774a54eb7',
|
||||
'info_dict': {
|
||||
@ -24,12 +26,57 @@ class FC2IE(InfoExtractor):
|
||||
'ext': 'flv',
|
||||
'title': 'Boxing again with Puff',
|
||||
},
|
||||
}
|
||||
}, {
|
||||
'url': 'http://video.fc2.com/en/content/20150125cEva0hDn/',
|
||||
'info_dict': {
|
||||
'id': '20150125cEva0hDn',
|
||||
'ext': 'mp4',
|
||||
},
|
||||
'params': {
|
||||
'username': 'ytdl@yt-dl.org',
|
||||
'password': '(snip)',
|
||||
'skip': 'requires actual password'
|
||||
}
|
||||
}]
|
||||
|
||||
def _login(self):
|
||||
(username, password) = self._get_login_info()
|
||||
if username is None or password is None:
|
||||
return False
|
||||
|
||||
# Log in
|
||||
login_form_strs = {
|
||||
'email': username,
|
||||
'password': password,
|
||||
'done': 'video',
|
||||
'Submit': ' Login ',
|
||||
}
|
||||
|
||||
# Convert to UTF-8 *before* urlencode because Python 2.x's urlencode
|
||||
# chokes on unicode
|
||||
login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k, v in login_form_strs.items())
|
||||
login_data = compat_urllib_parse.urlencode(login_form).encode('utf-8')
|
||||
request = compat_urllib_request.Request(
|
||||
'https://secure.id.fc2.com/index.php?mode=login&switch_language=en', login_data)
|
||||
|
||||
login_results = self._download_webpage(request, None, note='Logging in', errnote='Unable to log in')
|
||||
if 'mode=redirect&login=done' not in login_results:
|
||||
self.report_warning('unable to log in: bad username or password')
|
||||
return False
|
||||
|
||||
# this is also needed
|
||||
login_redir = compat_urllib_request.Request('http://id.fc2.com/?mode=redirect&login=done')
|
||||
self._download_webpage(
|
||||
login_redir, None, note='Login redirect', errnote='Login redirect failed')
|
||||
|
||||
return True
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
self._login()
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
self._downloader.cookiejar.clear_session_cookies() # must clear
|
||||
self._login()
|
||||
|
||||
title = self._og_search_title(webpage)
|
||||
thumbnail = self._og_search_thumbnail(webpage)
|
||||
@ -46,7 +93,12 @@ class FC2IE(InfoExtractor):
|
||||
info = compat_urlparse.parse_qs(info_webpage)
|
||||
|
||||
if 'err_code' in info:
|
||||
raise ExtractorError('Error code: %s' % info['err_code'][0])
|
||||
# most of the time we can still download wideo even if err_code is 403 or 602
|
||||
self.report_warning(
|
||||
'Error code was: %s... but still trying' % info['err_code'][0])
|
||||
|
||||
if 'filepath' not in info:
|
||||
raise ExtractorError('Cannot download file. Are you logged in?')
|
||||
|
||||
video_url = info['filepath'][0] + '?mid=' + info['mid'][0]
|
||||
title_info = info.get('title')
|
||||
|
@ -13,7 +13,7 @@ from ..utils import (
|
||||
|
||||
class FKTVIE(InfoExtractor):
|
||||
IE_NAME = 'fernsehkritik.tv'
|
||||
_VALID_URL = r'http://(?:www\.)?fernsehkritik\.tv/folge-(?P<ep>[0-9]+)(?:/.*)?'
|
||||
_VALID_URL = r'http://(?:www\.)?fernsehkritik\.tv/folge-(?P<id>[0-9]+)(?:/.*)?'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://fernsehkritik.tv/folge-1',
|
||||
@ -26,29 +26,32 @@ class FKTVIE(InfoExtractor):
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
episode = int(mobj.group('ep'))
|
||||
episode = int(self._match_id(url))
|
||||
|
||||
server = random.randint(2, 4)
|
||||
video_thumbnail = 'http://fernsehkritik.tv/images/magazin/folge%d.jpg' % episode
|
||||
start_webpage = self._download_webpage('http://fernsehkritik.tv/folge-%d/Start' % episode,
|
||||
video_thumbnail = 'http://fernsehkritik.tv/images/magazin/folge%s.jpg' % episode
|
||||
start_webpage = self._download_webpage('http://fernsehkritik.tv/folge-%s/Start' % episode,
|
||||
episode)
|
||||
playlist = self._search_regex(r'playlist = (\[.*?\]);', start_webpage,
|
||||
'playlist', flags=re.DOTALL)
|
||||
files = json.loads(re.sub('{[^{}]*?}', '{}', playlist))
|
||||
# TODO: return a single multipart video
|
||||
|
||||
videos = []
|
||||
for i, _ in enumerate(files, 1):
|
||||
video_id = '%04d%d' % (episode, i)
|
||||
video_url = 'http://dl%d.fernsehkritik.tv/fernsehkritik%d%s.flv' % (server, episode, '' if i == 1 else '-%d' % i)
|
||||
video_url = 'http://fernsehkritik.tv/js/directme.php?file=%s%s.flv' % (episode, '' if i == 1 else '-%d' % i)
|
||||
videos.append({
|
||||
'ext': 'flv',
|
||||
'id': video_id,
|
||||
'url': video_url,
|
||||
'title': clean_html(get_element_by_id('eptitle', start_webpage)),
|
||||
'description': clean_html(get_element_by_id('contentlist', start_webpage)),
|
||||
'thumbnail': video_thumbnail
|
||||
})
|
||||
return videos
|
||||
return {
|
||||
'_type': 'multi_video',
|
||||
'entries': videos,
|
||||
'id': 'folge-%s' % episode,
|
||||
}
|
||||
|
||||
|
||||
class FKTVPosteckeIE(InfoExtractor):
|
||||
|
@ -16,6 +16,7 @@ class FolketingetIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?ft\.dk/webtv/video/[^?#]*?\.(?P<id>[0-9]+)\.aspx'
|
||||
_TEST = {
|
||||
'url': 'http://www.ft.dk/webtv/video/20141/eru/td.1165642.aspx?as=1#player',
|
||||
'md5': '6269e8626fa1a891bf5369b386ae996a',
|
||||
'info_dict': {
|
||||
'id': '1165642',
|
||||
'ext': 'mp4',
|
||||
@ -29,9 +30,6 @@ class FolketingetIE(InfoExtractor):
|
||||
'upload_date': '20141120',
|
||||
'duration': 3960,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': 'rtmpdump required',
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
@ -7,10 +7,9 @@ from ..compat import (
|
||||
compat_urllib_request,
|
||||
)
|
||||
from ..utils import (
|
||||
clean_html,
|
||||
parse_duration,
|
||||
parse_iso8601,
|
||||
str_to_int,
|
||||
unified_strdate,
|
||||
)
|
||||
|
||||
|
||||
@ -28,68 +27,81 @@ class FourTubeIE(InfoExtractor):
|
||||
'uploader': 'WCP Club',
|
||||
'uploader_id': 'wcp-club',
|
||||
'upload_date': '20131031',
|
||||
'timestamp': 1383263892,
|
||||
'duration': 583,
|
||||
'view_count': int,
|
||||
'like_count': int,
|
||||
'categories': list,
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage_url = 'http://www.4tube.com/videos/' + video_id
|
||||
webpage = self._download_webpage(webpage_url, video_id)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
self.report_extraction(video_id)
|
||||
title = self._html_search_meta('name', webpage)
|
||||
timestamp = parse_iso8601(self._html_search_meta(
|
||||
'uploadDate', webpage))
|
||||
thumbnail = self._html_search_meta('thumbnailUrl', webpage)
|
||||
uploader_id = self._html_search_regex(
|
||||
r'<a class="img-avatar" href="[^"]+/channels/([^/"]+)" title="Go to [^"]+ page">',
|
||||
webpage, 'uploader id')
|
||||
uploader = self._html_search_regex(
|
||||
r'<a class="img-avatar" href="[^"]+/channels/[^/"]+" title="Go to ([^"]+) page">',
|
||||
webpage, 'uploader')
|
||||
|
||||
playlist_json = self._html_search_regex(r'var playerConfigPlaylist\s+=\s+([^;]+)', webpage, 'Playlist')
|
||||
media_id = self._search_regex(r'idMedia:\s*(\d+)', playlist_json, 'Media Id')
|
||||
sources = self._search_regex(r'sources:\s*\[([^\]]*)\]', playlist_json, 'Sources').split(',')
|
||||
title = self._search_regex(r'title:\s*"([^"]*)', playlist_json, 'Title')
|
||||
thumbnail_url = self._search_regex(r'image:\s*"([^"]*)', playlist_json, 'Thumbnail', fatal=False)
|
||||
categories_html = self._search_regex(
|
||||
r'(?s)><i class="icon icon-tag"></i>\s*Categories / Tags\s*.*?<ul class="list">(.*?)</ul>',
|
||||
webpage, 'categories', fatal=False)
|
||||
categories = None
|
||||
if categories_html:
|
||||
categories = [
|
||||
c.strip() for c in re.findall(
|
||||
r'(?s)<li><a.*?>(.*?)</a>', categories_html)]
|
||||
|
||||
uploader_str = self._search_regex(r'<span>Uploaded by</span>(.*?)<span>', webpage, 'uploader', fatal=False)
|
||||
mobj = re.search(r'<a href="/sites/(?P<id>[^"]+)"><strong>(?P<name>[^<]+)</strong></a>', uploader_str)
|
||||
(uploader, uploader_id) = (mobj.group('name'), mobj.group('id')) if mobj else (clean_html(uploader_str), None)
|
||||
view_count = str_to_int(self._search_regex(
|
||||
r'<meta itemprop="interactionCount" content="UserPlays:([0-9,]+)">',
|
||||
webpage, 'view count', fatal=False))
|
||||
like_count = str_to_int(self._search_regex(
|
||||
r'<meta itemprop="interactionCount" content="UserLikes:([0-9,]+)">',
|
||||
webpage, 'like count', fatal=False))
|
||||
duration = parse_duration(self._html_search_meta('duration', webpage))
|
||||
|
||||
upload_date = None
|
||||
view_count = None
|
||||
duration = None
|
||||
description = self._html_search_meta('description', webpage, 'description')
|
||||
if description:
|
||||
upload_date = self._search_regex(r'Published Date: (\d{2} [a-zA-Z]{3} \d{4})', description, 'upload date',
|
||||
fatal=False)
|
||||
if upload_date:
|
||||
upload_date = unified_strdate(upload_date)
|
||||
view_count = self._search_regex(r'Views: ([\d,\.]+)', description, 'view count', fatal=False)
|
||||
if view_count:
|
||||
view_count = str_to_int(view_count)
|
||||
duration = parse_duration(self._search_regex(r'Length: (\d+m\d+s)', description, 'duration', fatal=False))
|
||||
params_js = self._search_regex(
|
||||
r'\$\.ajax\(url,\ opts\);\s*\}\s*\}\)\(([0-9,\[\] ]+)\)',
|
||||
webpage, 'initialization parameters'
|
||||
)
|
||||
params = self._parse_json('[%s]' % params_js, video_id)
|
||||
media_id = params[0]
|
||||
sources = ['%s' % p for p in params[2]]
|
||||
|
||||
token_url = "http://tkn.4tube.com/{0}/desktop/{1}".format(media_id, "+".join(sources))
|
||||
token_url = 'http://tkn.4tube.com/{0}/desktop/{1}'.format(
|
||||
media_id, '+'.join(sources))
|
||||
headers = {
|
||||
b'Content-Type': b'application/x-www-form-urlencoded',
|
||||
b'Origin': b'http://www.4tube.com',
|
||||
}
|
||||
token_req = compat_urllib_request.Request(token_url, b'{}', headers)
|
||||
tokens = self._download_json(token_req, video_id)
|
||||
|
||||
formats = [{
|
||||
'url': tokens[format]['token'],
|
||||
'format_id': format + 'p',
|
||||
'resolution': format + 'p',
|
||||
'quality': int(format),
|
||||
} for format in sources]
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'formats': formats,
|
||||
'thumbnail': thumbnail_url,
|
||||
'categories': categories,
|
||||
'thumbnail': thumbnail,
|
||||
'uploader': uploader,
|
||||
'uploader_id': uploader_id,
|
||||
'upload_date': upload_date,
|
||||
'timestamp': timestamp,
|
||||
'like_count': like_count,
|
||||
'view_count': view_count,
|
||||
'duration': duration,
|
||||
'age_limit': 18,
|
||||
'webpage_url': webpage_url,
|
||||
}
|
||||
|
@ -230,12 +230,13 @@ class FranceTVIE(FranceTVBaseInfoExtractor):
|
||||
|
||||
class GenerationQuoiIE(InfoExtractor):
|
||||
IE_NAME = 'france2.fr:generation-quoi'
|
||||
_VALID_URL = r'https?://generation-quoi\.france2\.fr/portrait/(?P<name>.*)(\?|$)'
|
||||
_VALID_URL = r'https?://generation-quoi\.france2\.fr/portrait/(?P<id>[^/?#]+)'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://generation-quoi.france2.fr/portrait/garde-a-vous',
|
||||
'file': 'k7FJX8VBcvvLmX4wA5Q.mp4',
|
||||
'info_dict': {
|
||||
'id': 'k7FJX8VBcvvLmX4wA5Q',
|
||||
'ext': 'mp4',
|
||||
'title': 'Génération Quoi - Garde à Vous',
|
||||
'uploader': 'Génération Quoi',
|
||||
},
|
||||
@ -243,14 +244,12 @@ class GenerationQuoiIE(InfoExtractor):
|
||||
# It uses Dailymotion
|
||||
'skip_download': True,
|
||||
},
|
||||
'skip': 'Only available from France',
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
name = mobj.group('name')
|
||||
info_url = compat_urlparse.urljoin(url, '/medias/video/%s.json' % name)
|
||||
info_json = self._download_webpage(info_url, name)
|
||||
display_id = self._match_id(url)
|
||||
info_url = compat_urlparse.urljoin(url, '/medias/video/%s.json' % display_id)
|
||||
info_json = self._download_webpage(info_url, display_id)
|
||||
info = json.loads(info_json)
|
||||
return self.url_result('http://www.dailymotion.com/video/%s' % info['id'],
|
||||
ie='Dailymotion')
|
||||
|
@ -57,8 +57,7 @@ class GameOneIE(InfoExtractor):
|
||||
]
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
video_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
og_video = self._og_search_video_url(webpage, secure=False)
|
||||
|
@ -1,8 +1,6 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
@ -29,9 +27,7 @@ class GameStarIE(InfoExtractor):
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
og_title = self._og_search_title(webpage)
|
||||
|
@ -39,7 +39,8 @@ class GDCVaultIE(InfoExtractor):
|
||||
'id': '1015301',
|
||||
'ext': 'flv',
|
||||
'title': 'Thexder Meets Windows 95, or Writing Great Games in the Windows 95 Environment',
|
||||
}
|
||||
},
|
||||
'skip': 'Requires login',
|
||||
}
|
||||
]
|
||||
|
||||
|
@ -17,6 +17,7 @@ from ..utils import (
|
||||
ExtractorError,
|
||||
float_or_none,
|
||||
HEADRequest,
|
||||
is_html,
|
||||
orderedSet,
|
||||
parse_xml,
|
||||
smuggle_url,
|
||||
@ -131,12 +132,13 @@ class GenericIE(InfoExtractor):
|
||||
# ooyala video
|
||||
{
|
||||
'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
|
||||
'md5': '5644c6ca5d5782c1d0d350dad9bd840c',
|
||||
'md5': '166dd577b433b4d4ebfee10b0824d8ff',
|
||||
'info_dict': {
|
||||
'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
|
||||
'ext': 'mp4',
|
||||
'title': '2cc213299525360.mov', # that's what we get
|
||||
},
|
||||
'add_ie': ['Ooyala'],
|
||||
},
|
||||
# google redirect
|
||||
{
|
||||
@ -146,7 +148,7 @@ class GenericIE(InfoExtractor):
|
||||
'ext': 'mp4',
|
||||
'upload_date': '20130224',
|
||||
'uploader_id': 'TheVerge',
|
||||
'description': 'Chris Ziegler takes a look at the Alcatel OneTouch Fire and the ZTE Open; two of the first Firefox OS handsets to be officially announced.',
|
||||
'description': 're:^Chris Ziegler takes a look at the\.*',
|
||||
'uploader': 'The Verge',
|
||||
'title': 'First Firefox OS phones side-by-side',
|
||||
},
|
||||
@ -181,6 +183,14 @@ class GenericIE(InfoExtractor):
|
||||
'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
|
||||
},
|
||||
},
|
||||
# BBC iPlayer embeds
|
||||
{
|
||||
'url': 'http://www.bbc.co.uk/blogs/adamcurtis/posts/BUGGER',
|
||||
'info_dict': {
|
||||
'title': 'BBC - Blogs - Adam Curtis - BUGGER',
|
||||
},
|
||||
'playlist_mincount': 18,
|
||||
},
|
||||
# RUTV embed
|
||||
{
|
||||
'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
|
||||
@ -352,7 +362,7 @@ class GenericIE(InfoExtractor):
|
||||
'info_dict': {
|
||||
'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
|
||||
'title': 'Zero Punctuation',
|
||||
'description': 're:'
|
||||
'description': 're:.*groundbreaking video review series.*'
|
||||
},
|
||||
'playlist_mincount': 11,
|
||||
},
|
||||
@ -479,6 +489,29 @@ class GenericIE(InfoExtractor):
|
||||
'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
|
||||
}
|
||||
},
|
||||
# Cinerama player
|
||||
{
|
||||
'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
|
||||
'info_dict': {
|
||||
'id': '730m_DandD_1901_512k',
|
||||
'ext': 'mp4',
|
||||
'uploader': 'www.abc.net.au',
|
||||
'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
|
||||
}
|
||||
},
|
||||
# embedded viddler video
|
||||
{
|
||||
'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
|
||||
'info_dict': {
|
||||
'id': '4d03aad9',
|
||||
'ext': 'mp4',
|
||||
'uploader': 'deadspin',
|
||||
'title': 'WALL-TO-GORTAT',
|
||||
'timestamp': 1422285291,
|
||||
'upload_date': '20150126',
|
||||
},
|
||||
'add_ie': ['Viddler'],
|
||||
}
|
||||
]
|
||||
|
||||
def report_following_redirect(self, new_url):
|
||||
@ -638,7 +671,7 @@ class GenericIE(InfoExtractor):
|
||||
# Maybe it's a direct link to a video?
|
||||
# Be careful not to download the whole thing!
|
||||
first_bytes = full_response.read(512)
|
||||
if not re.match(r'^\s*<', first_bytes.decode('utf-8', 'replace')):
|
||||
if not is_html(first_bytes):
|
||||
self._downloader.report_warning(
|
||||
'URL could be a direct video link, returning it as such.')
|
||||
upload_date = unified_strdate(
|
||||
@ -699,9 +732,9 @@ class GenericIE(InfoExtractor):
|
||||
r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
|
||||
|
||||
# Helper method
|
||||
def _playlist_from_matches(matches, getter, ie=None):
|
||||
def _playlist_from_matches(matches, getter=None, ie=None):
|
||||
urlrs = orderedSet(
|
||||
self.url_result(self._proto_relative_url(getter(m)), ie)
|
||||
self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
|
||||
for m in matches)
|
||||
return self.playlist_result(
|
||||
urlrs, playlist_id=video_id, playlist_title=video_title)
|
||||
@ -840,9 +873,16 @@ class GenericIE(InfoExtractor):
|
||||
if mobj is not None:
|
||||
return self.url_result(mobj.group('url'))
|
||||
|
||||
# Look for embedded Viddler player
|
||||
mobj = re.search(
|
||||
r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
|
||||
webpage)
|
||||
if mobj is not None:
|
||||
return self.url_result(mobj.group('url'))
|
||||
|
||||
# Look for Ooyala videos
|
||||
mobj = (re.search(r'player.ooyala.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
|
||||
re.search(r'OO.Player.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage))
|
||||
mobj = (re.search(r'player\.ooyala\.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
|
||||
re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage))
|
||||
if mobj is not None:
|
||||
return OoyalaIE._build_url_result(mobj.group('ec'))
|
||||
|
||||
@ -908,7 +948,7 @@ class GenericIE(InfoExtractor):
|
||||
# Look for BBC iPlayer embed
|
||||
matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
|
||||
if matches:
|
||||
return self.playlist_result([self.url_result(video_url, ie='BBCCoUk') for video_url in matches])
|
||||
return _playlist_from_matches(matches, ie='BBCCoUk')
|
||||
|
||||
# Look for embedded RUTV player
|
||||
rutv_url = RUTVIE._extract_url(webpage)
|
||||
@ -917,7 +957,7 @@ class GenericIE(InfoExtractor):
|
||||
|
||||
# Look for embedded TED player
|
||||
mobj = re.search(
|
||||
r'<iframe[^>]+?src=(["\'])(?P<url>http://embed\.ted\.com/.+?)\1', webpage)
|
||||
r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
|
||||
if mobj is not None:
|
||||
return self.url_result(mobj.group('url'), 'TED')
|
||||
|
||||
@ -1033,9 +1073,13 @@ class GenericIE(InfoExtractor):
|
||||
found = filter_video(re.findall(r'''(?xs)
|
||||
flowplayer\("[^"]+",\s*
|
||||
\{[^}]+?\}\s*,
|
||||
\s*{[^}]+? ["']?clip["']?\s*:\s*\{\s*
|
||||
\s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
|
||||
["']?url["']?\s*:\s*["']([^"']+)["']
|
||||
''', webpage))
|
||||
if not found:
|
||||
# Cinerama player
|
||||
found = re.findall(
|
||||
r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
|
||||
if not found:
|
||||
# Try to find twitter cards info
|
||||
found = filter_video(re.findall(
|
||||
|
101
youtube_dl/extractor/giga.py
Normal file
101
youtube_dl/extractor/giga.py
Normal file
@ -0,0 +1,101 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import itertools
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
qualities,
|
||||
compat_str,
|
||||
parse_duration,
|
||||
parse_iso8601,
|
||||
str_to_int,
|
||||
)
|
||||
|
||||
|
||||
class GigaIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?giga\.de/(?:[^/]+/)*(?P<id>[^/]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.giga.de/filme/anime-awesome/trailer/anime-awesome-chihiros-reise-ins-zauberland-das-beste-kommt-zum-schluss/',
|
||||
'md5': '6bc5535e945e724640664632055a584f',
|
||||
'info_dict': {
|
||||
'id': '2622086',
|
||||
'display_id': 'anime-awesome-chihiros-reise-ins-zauberland-das-beste-kommt-zum-schluss',
|
||||
'ext': 'mp4',
|
||||
'title': 'Anime Awesome: Chihiros Reise ins Zauberland – Das Beste kommt zum Schluss',
|
||||
'description': 'md5:afdf5862241aded4718a30dff6a57baf',
|
||||
'thumbnail': 're:^https?://.*\.jpg$',
|
||||
'duration': 578,
|
||||
'timestamp': 1414749706,
|
||||
'upload_date': '20141031',
|
||||
'uploader': 'Robin Schweiger',
|
||||
'view_count': int,
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.giga.de/games/channel/giga-top-montag/giga-topmontag-die-besten-serien-2014/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.giga.de/extra/netzkultur/videos/giga-games-tom-mats-robin-werden-eigene-wege-gehen-eine-ankuendigung/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.giga.de/tv/jonas-liest-spieletitel-eingedeutscht-episode-2/',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
video_id = self._search_regex(
|
||||
[r'data-video-id="(\d+)"', r'/api/video/jwplayer/#v=(\d+)'],
|
||||
webpage, 'video id')
|
||||
|
||||
playlist = self._download_json(
|
||||
'http://www.giga.de/api/syndication/video/video_id/%s/playlist.json?content=syndication/key/368b5f151da4ae05ced7fa296bdff65a/'
|
||||
% video_id, video_id)[0]
|
||||
|
||||
quality = qualities(['normal', 'hd720'])
|
||||
|
||||
formats = []
|
||||
for format_id in itertools.count(0):
|
||||
fmt = playlist.get(compat_str(format_id))
|
||||
if not fmt:
|
||||
break
|
||||
formats.append({
|
||||
'url': fmt['src'],
|
||||
'format_id': '%s-%s' % (fmt['quality'], fmt['type'].split('/')[-1]),
|
||||
'quality': quality(fmt['quality']),
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
title = self._html_search_meta(
|
||||
'title', webpage, 'title', fatal=True)
|
||||
description = self._html_search_meta(
|
||||
'description', webpage, 'description')
|
||||
thumbnail = self._og_search_thumbnail(webpage)
|
||||
|
||||
duration = parse_duration(self._search_regex(
|
||||
r'(?s)(?:data-video-id="{0}"|data-video="[^"]*/api/video/jwplayer/#v={0}[^"]*")[^>]*>.+?<span class="duration">([^<]+)</span>'.format(video_id),
|
||||
webpage, 'duration', fatal=False))
|
||||
|
||||
timestamp = parse_iso8601(self._search_regex(
|
||||
r'datetime="([^"]+)"', webpage, 'upload date', fatal=False))
|
||||
uploader = self._search_regex(
|
||||
r'class="author">([^<]+)</a>', webpage, 'uploader', fatal=False)
|
||||
|
||||
view_count = str_to_int(self._search_regex(
|
||||
r'<span class="views"><strong>([\d.]+)</strong>', webpage, 'view count', fatal=False))
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'display_id': display_id,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
'duration': duration,
|
||||
'timestamp': timestamp,
|
||||
'uploader': uploader,
|
||||
'view_count': view_count,
|
||||
'formats': formats,
|
||||
}
|
@ -70,6 +70,19 @@ class GloboIE(InfoExtractor):
|
||||
'like_count': int,
|
||||
}
|
||||
},
|
||||
{
|
||||
'url': 'http://globotv.globo.com/canal-brasil/sangue-latino/t/todos-os-videos/v/ator-e-diretor-argentino-ricado-darin-fala-sobre-utopias-e-suas-perdas/3928201/',
|
||||
'md5': 'c1defca721ce25b2354e927d3e4b3dec',
|
||||
'info_dict': {
|
||||
'id': '3928201',
|
||||
'ext': 'mp4',
|
||||
'title': 'Ator e diretor argentino, Ricado Darín fala sobre utopias e suas perdas',
|
||||
'duration': 1472.906,
|
||||
'uploader': 'Canal Brasil',
|
||||
'uploader_id': 705,
|
||||
'like_count': int,
|
||||
}
|
||||
},
|
||||
]
|
||||
|
||||
class MD5():
|
||||
@ -381,11 +394,16 @@ class GloboIE(InfoExtractor):
|
||||
signed_md5 = self.MD5.b64_md5(received_md5 + compat_str(sign_time) + padding)
|
||||
signed_hash = hash_code + compat_str(received_time) + received_random + compat_str(sign_time) + padding + signed_md5
|
||||
|
||||
formats.append({
|
||||
'url': '%s?h=%s&k=%s' % (resource['url'], signed_hash, 'flash'),
|
||||
'format_id': resource_id,
|
||||
'height': resource['height']
|
||||
})
|
||||
resource_url = resource['url']
|
||||
signed_url = '%s?h=%s&k=%s' % (resource_url, signed_hash, 'flash')
|
||||
if resource_id.endswith('m3u8') or resource_url.endswith('.m3u8'):
|
||||
formats.extend(self._extract_m3u8_formats(signed_url, resource_id, 'mp4'))
|
||||
else:
|
||||
formats.append({
|
||||
'url': signed_url,
|
||||
'format_id': resource_id,
|
||||
'height': resource.get('height'),
|
||||
})
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
|
@ -83,7 +83,7 @@ class GroovesharkIE(InfoExtractor):
|
||||
return compat_urlparse.urlunparse((uri.scheme, uri.netloc, obj['attrs']['data'], None, None, None))
|
||||
|
||||
def _transform_bootstrap(self, js):
|
||||
return re.split('(?m)^\s*try\s*{', js)[0] \
|
||||
return re.split('(?m)^\s*try\s*\{', js)[0] \
|
||||
.split(' = ', 1)[1].strip().rstrip(';')
|
||||
|
||||
def _transform_meta(self, js):
|
||||
|
117
youtube_dl/extractor/hearthisat.py
Normal file
117
youtube_dl/extractor/hearthisat.py
Normal file
@ -0,0 +1,117 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import (
|
||||
compat_urllib_request,
|
||||
compat_urlparse,
|
||||
)
|
||||
from ..utils import (
|
||||
HEADRequest,
|
||||
str_to_int,
|
||||
urlencode_postdata,
|
||||
urlhandle_detect_ext,
|
||||
)
|
||||
|
||||
|
||||
class HearThisAtIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?hearthis\.at/(?P<artist>[^/]+)/(?P<title>[A-Za-z0-9\-]+)/?$'
|
||||
_PLAYLIST_URL = 'https://hearthis.at/playlist.php'
|
||||
_TEST = {
|
||||
'url': 'https://hearthis.at/moofi/dr-kreep',
|
||||
'md5': 'ab6ec33c8fed6556029337c7885eb4e0',
|
||||
'info_dict': {
|
||||
'id': '150939',
|
||||
'ext': 'wav',
|
||||
'title': 'Moofi - Dr. Kreep',
|
||||
'thumbnail': 're:^https?://.*\.jpg$',
|
||||
'timestamp': 1421564134,
|
||||
'description': 'Creepy Patch. Mutable Instruments Braids Vowel + Formant Mode.',
|
||||
'upload_date': '20150118',
|
||||
'comment_count': int,
|
||||
'view_count': int,
|
||||
'like_count': int,
|
||||
'duration': 71,
|
||||
'categories': ['Experimental'],
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
m = re.match(self._VALID_URL, url)
|
||||
display_id = '{artist:s} - {title:s}'.format(**m.groupdict())
|
||||
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
track_id = self._search_regex(
|
||||
r'intTrackId\s*=\s*(\d+)', webpage, 'track ID')
|
||||
|
||||
payload = urlencode_postdata({'tracks[]': track_id})
|
||||
req = compat_urllib_request.Request(self._PLAYLIST_URL, payload)
|
||||
req.add_header('Content-type', 'application/x-www-form-urlencoded')
|
||||
|
||||
track = self._download_json(req, track_id, 'Downloading playlist')[0]
|
||||
title = '{artist:s} - {title:s}'.format(**track)
|
||||
|
||||
categories = None
|
||||
if track.get('category'):
|
||||
categories = [track['category']]
|
||||
|
||||
description = self._og_search_description(webpage)
|
||||
thumbnail = self._og_search_thumbnail(webpage)
|
||||
|
||||
meta_span = r'<span[^>]+class="%s".*?</i>([^<]+)</span>'
|
||||
view_count = str_to_int(self._search_regex(
|
||||
meta_span % 'plays_count', webpage, 'view count', fatal=False))
|
||||
like_count = str_to_int(self._search_regex(
|
||||
meta_span % 'likes_count', webpage, 'like count', fatal=False))
|
||||
comment_count = str_to_int(self._search_regex(
|
||||
meta_span % 'comment_count', webpage, 'comment count', fatal=False))
|
||||
duration = str_to_int(self._search_regex(
|
||||
r'data-length="(\d+)', webpage, 'duration', fatal=False))
|
||||
timestamp = str_to_int(self._search_regex(
|
||||
r'<span[^>]+class="calctime"[^>]+data-time="(\d+)', webpage, 'timestamp', fatal=False))
|
||||
|
||||
formats = []
|
||||
mp3_url = self._search_regex(
|
||||
r'(?s)<a class="player-link"\s+(?:[a-zA-Z0-9_:-]+="[^"]+"\s+)*?data-mp3="([^"]+)"',
|
||||
webpage, 'mp3 URL', fatal=False)
|
||||
if mp3_url:
|
||||
formats.append({
|
||||
'format_id': 'mp3',
|
||||
'vcodec': 'none',
|
||||
'acodec': 'mp3',
|
||||
'url': mp3_url,
|
||||
})
|
||||
download_path = self._search_regex(
|
||||
r'<a class="[^"]*download_fct[^"]*"\s+href="([^"]+)"',
|
||||
webpage, 'download URL', default=None)
|
||||
if download_path:
|
||||
download_url = compat_urlparse.urljoin(url, download_path)
|
||||
ext_req = HEADRequest(download_url)
|
||||
ext_handle = self._request_webpage(
|
||||
ext_req, display_id, note='Determining extension')
|
||||
ext = urlhandle_detect_ext(ext_handle)
|
||||
formats.append({
|
||||
'format_id': 'download',
|
||||
'vcodec': 'none',
|
||||
'ext': ext,
|
||||
'url': download_url,
|
||||
'preference': 2, # Usually better quality
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': track_id,
|
||||
'display_id': display_id,
|
||||
'title': title,
|
||||
'formats': formats,
|
||||
'thumbnail': thumbnail,
|
||||
'description': description,
|
||||
'duration': duration,
|
||||
'timestamp': timestamp,
|
||||
'view_count': view_count,
|
||||
'comment_count': comment_count,
|
||||
'like_count': like_count,
|
||||
'categories': categories,
|
||||
}
|
46
youtube_dl/extractor/historicfilms.py
Normal file
46
youtube_dl/extractor/historicfilms.py
Normal file
@ -0,0 +1,46 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import parse_duration
|
||||
|
||||
|
||||
class HistoricFilmsIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?historicfilms\.com/(?:tapes/|play)(?P<id>\d+)'
|
||||
_TEST = {
|
||||
'url': 'http://www.historicfilms.com/tapes/4728',
|
||||
'md5': 'd4a437aec45d8d796a38a215db064e9a',
|
||||
'info_dict': {
|
||||
'id': '4728',
|
||||
'ext': 'mov',
|
||||
'title': 'Historic Films: GP-7',
|
||||
'description': 'md5:1a86a0f3ac54024e419aba97210d959a',
|
||||
'thumbnail': 're:^https?://.*\.jpg$',
|
||||
'duration': 2096,
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
tape_id = self._search_regex(
|
||||
r'class="tapeId">([^<]+)<', webpage, 'tape id')
|
||||
|
||||
title = self._og_search_title(webpage)
|
||||
description = self._og_search_description(webpage)
|
||||
thumbnail = self._html_search_meta(
|
||||
'thumbnailUrl', webpage, 'thumbnails') or self._og_search_thumbnail(webpage)
|
||||
duration = parse_duration(self._html_search_meta(
|
||||
'duration', webpage, 'duration'))
|
||||
|
||||
video_url = 'http://www.historicfilms.com/video/%s_%s_web.mov' % (tape_id, video_id)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'url': video_url,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
'duration': duration,
|
||||
}
|
@ -39,8 +39,9 @@ class HuffPostIE(InfoExtractor):
|
||||
data = self._download_json(api_url, video_id)['data']
|
||||
|
||||
video_title = data['title']
|
||||
duration = parse_duration(data['running_time'])
|
||||
upload_date = unified_strdate(data['schedule']['starts_at'])
|
||||
duration = parse_duration(data.get('running_time'))
|
||||
upload_date = unified_strdate(
|
||||
data.get('schedule', {}).get('starts_at') or data.get('segment_start_date_time'))
|
||||
description = data.get('description')
|
||||
|
||||
thumbnails = []
|
||||
@ -59,16 +60,11 @@ class HuffPostIE(InfoExtractor):
|
||||
'ext': 'mp4',
|
||||
'url': url,
|
||||
'vcodec': 'none' if key.startswith('audio/') else None,
|
||||
} for key, url in data['sources']['live'].items()]
|
||||
if data.get('fivemin_id'):
|
||||
fid = data['fivemin_id']
|
||||
fcat = str(int(fid) // 100 + 1)
|
||||
furl = 'http://avideos.5min.com/2/' + fcat[-3:] + '/' + fcat + '/' + fid + '.mp4'
|
||||
formats.append({
|
||||
'format': 'fivemin',
|
||||
'url': furl,
|
||||
'preference': 1,
|
||||
})
|
||||
} for key, url in data.get('sources', {}).get('live', {}).items()]
|
||||
|
||||
if not formats and data.get('fivemin_id'):
|
||||
return self.url_result('5min:%s' % data['fivemin_id'])
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
|
@ -16,7 +16,6 @@ class ImdbIE(InfoExtractor):
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://www.imdb.com/video/imdb/vi2524815897',
|
||||
'md5': '9f34fa777ade3a6e57a054fdbcb3a068',
|
||||
'info_dict': {
|
||||
'id': '2524815897',
|
||||
'ext': 'mp4',
|
||||
|
@ -16,7 +16,7 @@ from ..utils import (
|
||||
class IviIE(InfoExtractor):
|
||||
IE_DESC = 'ivi.ru'
|
||||
IE_NAME = 'ivi'
|
||||
_VALID_URL = r'https?://(?:www\.)?ivi\.ru/(?:watch/(?:[^/]+/)?|video/player\?.*?videoId=)(?P<videoid>\d+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?ivi\.ru/(?:watch/(?:[^/]+/)?|video/player\?.*?videoId=)(?P<id>\d+)'
|
||||
|
||||
_TESTS = [
|
||||
# Single movie
|
||||
@ -63,29 +63,34 @@ class IviIE(InfoExtractor):
|
||||
return int(m.group('commentcount')) if m is not None else 0
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('videoid')
|
||||
video_id = self._match_id(url)
|
||||
|
||||
api_url = 'http://api.digitalaccess.ru/api/json/'
|
||||
|
||||
data = {'method': 'da.content.get',
|
||||
'params': [video_id, {'site': 's183',
|
||||
'referrer': 'http://www.ivi.ru/watch/%s' % video_id,
|
||||
'contentid': video_id
|
||||
}
|
||||
]
|
||||
data = {
|
||||
'method': 'da.content.get',
|
||||
'params': [
|
||||
video_id, {
|
||||
'site': 's183',
|
||||
'referrer': 'http://www.ivi.ru/watch/%s' % video_id,
|
||||
'contentid': video_id
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
request = compat_urllib_request.Request(api_url, json.dumps(data))
|
||||
|
||||
video_json_page = self._download_webpage(request, video_id, 'Downloading video JSON')
|
||||
video_json_page = self._download_webpage(
|
||||
request, video_id, 'Downloading video JSON')
|
||||
video_json = json.loads(video_json_page)
|
||||
|
||||
if 'error' in video_json:
|
||||
error = video_json['error']
|
||||
if error['origin'] == 'NoRedisValidData':
|
||||
raise ExtractorError('Video %s does not exist' % video_id, expected=True)
|
||||
raise ExtractorError('Unable to download video %s: %s' % (video_id, error['message']), expected=True)
|
||||
raise ExtractorError(
|
||||
'Unable to download video %s: %s' % (video_id, error['message']),
|
||||
expected=True)
|
||||
|
||||
result = video_json['result']
|
||||
|
||||
|
@ -13,17 +13,17 @@ class KankanIE(InfoExtractor):
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://yinyue.kankan.com/vod/48/48863.shtml',
|
||||
'file': '48863.flv',
|
||||
'md5': '29aca1e47ae68fc28804aca89f29507e',
|
||||
'info_dict': {
|
||||
'id': '48863',
|
||||
'ext': 'flv',
|
||||
'title': 'Ready To Go',
|
||||
},
|
||||
'skip': 'Only available from China',
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
title = self._search_regex(r'(?:G_TITLE=|G_MOVIE_TITLE = )[\'"](.+?)[\'"]', webpage, 'video title')
|
||||
|
40
youtube_dl/extractor/karaoketv.py
Normal file
40
youtube_dl/extractor/karaoketv.py
Normal file
@ -0,0 +1,40 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_urllib_parse
|
||||
from ..utils import (
|
||||
js_to_json,
|
||||
)
|
||||
|
||||
|
||||
class KaraoketvIE(InfoExtractor):
|
||||
_VALID_URL = r'http://karaoketv\.co\.il/\?container=songs&id=(?P<id>[0-9]+)'
|
||||
_TEST = {
|
||||
'url': 'http://karaoketv.co.il/?container=songs&id=171568',
|
||||
'info_dict': {
|
||||
'id': '171568',
|
||||
'ext': 'mp4',
|
||||
'title': 'אל העולם שלך - רותם כהן - שרים קריוקי',
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
page_video_url = self._og_search_video_url(webpage, video_id)
|
||||
config_json = compat_urllib_parse.unquote_plus(self._search_regex(
|
||||
r'config=(.*)', page_video_url, 'configuration'))
|
||||
|
||||
urls_info_json = self._download_json(
|
||||
config_json, video_id, 'Downloading configuration',
|
||||
transform_source=js_to_json)
|
||||
|
||||
url = urls_info_json['playlist'][0]['url']
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': self._og_search_title(webpage),
|
||||
'url': url,
|
||||
}
|
@ -7,10 +7,6 @@ from .common import InfoExtractor
|
||||
from ..compat import (
|
||||
compat_urllib_parse_urlparse,
|
||||
compat_urllib_request,
|
||||
compat_urllib_parse,
|
||||
)
|
||||
from ..aes import (
|
||||
aes_decrypt_text
|
||||
)
|
||||
|
||||
|
||||
@ -18,9 +14,10 @@ class KeezMoviesIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?keezmovies\.com/video/.+?(?P<id>[0-9]+)(?:[/?&]|$)'
|
||||
_TEST = {
|
||||
'url': 'http://www.keezmovies.com/video/petite-asian-lady-mai-playing-in-bathtub-1214711',
|
||||
'file': '1214711.mp4',
|
||||
'md5': '6e297b7e789329923fcf83abb67c9289',
|
||||
'info_dict': {
|
||||
'id': '1214711',
|
||||
'ext': 'mp4',
|
||||
'title': 'Petite Asian Lady Mai Playing In Bathtub',
|
||||
'age_limit': 18,
|
||||
}
|
||||
@ -39,11 +36,10 @@ class KeezMoviesIE(InfoExtractor):
|
||||
embedded_url = mobj.group(1)
|
||||
return self.url_result(embedded_url)
|
||||
|
||||
video_title = self._html_search_regex(r'<h1 [^>]*>([^<]+)', webpage, 'title')
|
||||
video_url = compat_urllib_parse.unquote(self._html_search_regex(r'video_url=(.+?)&', webpage, 'video_url'))
|
||||
if 'encrypted=true' in webpage:
|
||||
password = self._html_search_regex(r'video_title=(.+?)&', webpage, 'password')
|
||||
video_url = aes_decrypt_text(video_url, password, 32).decode('utf-8')
|
||||
video_title = self._html_search_regex(
|
||||
r'<h1 [^>]*>([^<]+)', webpage, 'title')
|
||||
video_url = self._html_search_regex(
|
||||
r'(?s)html5VideoPlayer = .*?src="([^"]+)"', webpage, 'video URL')
|
||||
path = compat_urllib_parse_urlparse(video_url).path
|
||||
extension = os.path.splitext(path)[1][1:]
|
||||
format = path.split('/')[4].split('_')[:2]
|
||||
|
@ -22,8 +22,10 @@ class KhanAcademyIE(InfoExtractor):
|
||||
'description': 'The perfect cipher',
|
||||
'duration': 176,
|
||||
'uploader': 'Brit Cruise',
|
||||
'uploader_id': 'khanacademy',
|
||||
'upload_date': '20120411',
|
||||
}
|
||||
},
|
||||
'add_ie': ['Youtube'],
|
||||
}, {
|
||||
'url': 'https://www.khanacademy.org/math/applied-math/cryptography',
|
||||
'info_dict': {
|
||||
|
@ -10,13 +10,14 @@ from ..utils import int_or_none
|
||||
class KontrTubeIE(InfoExtractor):
|
||||
IE_NAME = 'kontrtube'
|
||||
IE_DESC = 'KontrTube.ru - Труба зовёт'
|
||||
_VALID_URL = r'http://(?:www\.)?kontrtube\.ru/videos/(?P<id>\d+)/.+'
|
||||
_VALID_URL = r'http://(?:www\.)?kontrtube\.ru/videos/(?P<id>\d+)/(?P<display_id>[^/]+)/'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://www.kontrtube.ru/videos/2678/nad-olimpiyskoy-derevney-v-sochi-podnyat-rossiyskiy-flag/',
|
||||
'md5': '975a991a4926c9a85f383a736a2e6b80',
|
||||
'info_dict': {
|
||||
'id': '2678',
|
||||
'display_id': 'nad-olimpiyskoy-derevney-v-sochi-podnyat-rossiyskiy-flag',
|
||||
'ext': 'mp4',
|
||||
'title': 'Над олимпийской деревней в Сочи поднят российский флаг',
|
||||
'description': 'md5:80edc4c613d5887ae8ccf1d59432be41',
|
||||
@ -28,21 +29,28 @@ class KontrTubeIE(InfoExtractor):
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
display_id = mobj.group('display_id')
|
||||
|
||||
webpage = self._download_webpage(url, video_id, 'Downloading page')
|
||||
webpage = self._download_webpage(
|
||||
url, display_id, 'Downloading page')
|
||||
|
||||
video_url = self._html_search_regex(r"video_url: '(.+?)/?',", webpage, 'video URL')
|
||||
thumbnail = self._html_search_regex(r"preview_url: '(.+?)/?',", webpage, 'video thumbnail', fatal=False)
|
||||
video_url = self._html_search_regex(
|
||||
r"video_url\s*:\s*'(.+?)/?',", webpage, 'video URL')
|
||||
thumbnail = self._html_search_regex(
|
||||
r"preview_url\s*:\s*'(.+?)/?',", webpage, 'video thumbnail', fatal=False)
|
||||
title = self._html_search_regex(
|
||||
r'<title>(.+?)</title>', webpage, 'video title')
|
||||
description = self._html_search_meta('description', webpage, 'video description')
|
||||
description = self._html_search_meta(
|
||||
'description', webpage, 'video description')
|
||||
|
||||
mobj = re.search(
|
||||
r'<div class="col_2">Длительность: <span>(?P<minutes>\d+)м:(?P<seconds>\d+)с</span></div>', webpage)
|
||||
r'<div class="col_2">Длительность: <span>(?P<minutes>\d+)м:(?P<seconds>\d+)с</span></div>',
|
||||
webpage)
|
||||
duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None
|
||||
|
||||
view_count = self._html_search_regex(
|
||||
r'<div class="col_2">Просмотров: <span>(\d+)</span></div>', webpage, 'view count', fatal=False)
|
||||
r'<div class="col_2">Просмотров: <span>(\d+)</span></div>',
|
||||
webpage, 'view count', fatal=False)
|
||||
|
||||
comment_count = None
|
||||
comment_str = self._html_search_regex(
|
||||
@ -56,6 +64,7 @@ class KontrTubeIE(InfoExtractor):
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'display_id': display_id,
|
||||
'url': video_url,
|
||||
'thumbnail': thumbnail,
|
||||
'title': title,
|
||||
|
@ -2,18 +2,17 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import json
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
unescapeHTML,
|
||||
js_to_json,
|
||||
)
|
||||
|
||||
|
||||
class KrasViewIE(InfoExtractor):
|
||||
IE_DESC = 'Красвью'
|
||||
_VALID_URL = r'https?://krasview\.ru/video/(?P<id>\d+)'
|
||||
_VALID_URL = r'https?://krasview\.ru/(?:video|embed)/(?P<id>\d+)'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://krasview.ru/video/512228',
|
||||
@ -29,20 +28,18 @@ class KrasViewIE(InfoExtractor):
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
video_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
flashvars = json.loads(self._search_regex(
|
||||
r'flashvars\s*:\s*({.+?})\s*}\);', webpage, 'flashvars'))
|
||||
flashvars = json.loads(js_to_json(self._search_regex(
|
||||
r'video_Init\(({.+?})', webpage, 'flashvars')))
|
||||
|
||||
video_url = flashvars['url']
|
||||
title = unescapeHTML(flashvars['title'])
|
||||
description = unescapeHTML(flashvars.get('subtitle') or self._og_search_description(webpage, default=None))
|
||||
thumbnail = flashvars['image']
|
||||
duration = int(flashvars['duration'])
|
||||
filesize = int(flashvars['size'])
|
||||
title = self._og_search_title(webpage)
|
||||
description = self._og_search_description(webpage, default=None)
|
||||
thumbnail = flashvars.get('image') or self._og_search_thumbnail(webpage)
|
||||
duration = int_or_none(flashvars.get('duration'))
|
||||
width = int_or_none(self._og_search_property('video:width', webpage, 'video width'))
|
||||
height = int_or_none(self._og_search_property('video:height', webpage, 'video height'))
|
||||
|
||||
@ -53,7 +50,6 @@ class KrasViewIE(InfoExtractor):
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
'duration': duration,
|
||||
'filesize': filesize,
|
||||
'width': width,
|
||||
'height': height,
|
||||
}
|
||||
|
@ -1,7 +1,5 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
parse_duration,
|
||||
@ -20,9 +18,10 @@ class LA7IE(InfoExtractor):
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://www.la7.tv/richplayer/?assetid=50355319',
|
||||
'file': '50355319.mp4',
|
||||
'md5': 'ec7d1f0224d20ba293ab56cf2259651f',
|
||||
'info_dict': {
|
||||
'id': '50355319',
|
||||
'ext': 'mp4',
|
||||
'title': 'IL DIVO',
|
||||
'description': 'Un film di Paolo Sorrentino con Toni Servillo, Anna Bonaiuto, Giulio Bosetti e Flavio Bucci',
|
||||
'duration': 6254,
|
||||
@ -31,9 +30,7 @@ class LA7IE(InfoExtractor):
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
|
||||
video_id = self._match_id(url)
|
||||
xml_url = 'http://www.la7.tv/repliche/content/index.php?contentId=%s' % video_id
|
||||
doc = self._download_xml(xml_url, video_id)
|
||||
|
||||
|
@ -8,20 +8,20 @@ from ..utils import int_or_none
|
||||
|
||||
|
||||
class LiveLeakIE(InfoExtractor):
|
||||
_VALID_URL = r'^(?:http://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<video_id>[\w_]+)(?:.*)'
|
||||
_VALID_URL = r'https?://(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<id>[\w_]+)(?:.*)'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.liveleak.com/view?i=757_1364311680',
|
||||
'md5': '0813c2430bea7a46bf13acf3406992f4',
|
||||
'md5': '50f79e05ba149149c1b4ea961223d5b3',
|
||||
'info_dict': {
|
||||
'id': '757_1364311680',
|
||||
'ext': 'mp4',
|
||||
'ext': 'flv',
|
||||
'description': 'extremely bad day for this guy..!',
|
||||
'uploader': 'ljfriel2',
|
||||
'title': 'Most unlucky car accident'
|
||||
}
|
||||
}, {
|
||||
'url': 'http://www.liveleak.com/view?i=f93_1390833151',
|
||||
'md5': 'd3f1367d14cc3c15bf24fbfbe04b9abf',
|
||||
'md5': 'b13a29626183c9d33944e6a04f41aafc',
|
||||
'info_dict': {
|
||||
'id': 'f93_1390833151',
|
||||
'ext': 'mp4',
|
||||
@ -43,8 +43,7 @@ class LiveLeakIE(InfoExtractor):
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('video_id')
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
video_title = self._og_search_title(webpage).replace('LiveLeak.com -', '').strip()
|
||||
@ -81,9 +80,19 @@ class LiveLeakIE(InfoExtractor):
|
||||
sources = json.loads(sources_json)
|
||||
|
||||
formats = [{
|
||||
'format_id': '%s' % i,
|
||||
'format_note': s.get('label'),
|
||||
'url': s['file'],
|
||||
} for s in sources]
|
||||
} for i, s in enumerate(sources)]
|
||||
for i, s in enumerate(sources):
|
||||
orig_url = s['file'].replace('.h264_base.mp4', '')
|
||||
if s['file'] != orig_url:
|
||||
formats.append({
|
||||
'format_id': 'original-%s' % i,
|
||||
'format_note': s.get('label'),
|
||||
'url': orig_url,
|
||||
'preference': 1,
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
|
113
youtube_dl/extractor/lnkgo.py
Normal file
113
youtube_dl/extractor/lnkgo.py
Normal file
@ -0,0 +1,113 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
unified_strdate,
|
||||
)
|
||||
|
||||
|
||||
class LnkGoIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?lnkgo\.alfa\.lt/visi-video/(?P<show>[^/]+)/ziurek-(?P<id>[A-Za-z0-9-]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://lnkgo.alfa.lt/visi-video/yra-kaip-yra/ziurek-yra-kaip-yra-162',
|
||||
'info_dict': {
|
||||
'id': '46712',
|
||||
'ext': 'mp4',
|
||||
'title': 'Yra kaip yra',
|
||||
'upload_date': '20150107',
|
||||
'description': 'md5:d82a5e36b775b7048617f263a0e3475e',
|
||||
'age_limit': 7,
|
||||
'duration': 3019,
|
||||
'thumbnail': 're:^https?://.*\.jpg$'
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True, # HLS download
|
||||
},
|
||||
}, {
|
||||
'url': 'http://lnkgo.alfa.lt/visi-video/aktualai-pratesimas/ziurek-nerdas-taiso-kompiuteri-2',
|
||||
'info_dict': {
|
||||
'id': '47289',
|
||||
'ext': 'mp4',
|
||||
'title': 'Nėrdas: Kompiuterio Valymas',
|
||||
'upload_date': '20150113',
|
||||
'description': 'md5:7352d113a242a808676ff17e69db6a69',
|
||||
'age_limit': 18,
|
||||
'duration': 346,
|
||||
'thumbnail': 're:^https?://.*\.jpg$'
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True, # HLS download
|
||||
},
|
||||
}]
|
||||
_AGE_LIMITS = {
|
||||
'N-7': 7,
|
||||
'N-14': 14,
|
||||
'S': 18,
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(
|
||||
url, display_id, 'Downloading player webpage')
|
||||
|
||||
video_id = self._search_regex(
|
||||
r'data-ep="([^"]+)"', webpage, 'video ID')
|
||||
title = self._og_search_title(webpage)
|
||||
description = self._og_search_description(webpage)
|
||||
upload_date = unified_strdate(self._search_regex(
|
||||
r'class="[^"]*meta-item[^"]*air-time[^"]*">.*?<strong>([^<]+)</strong>', webpage, 'upload date', fatal=False))
|
||||
|
||||
thumbnail_w = int_or_none(
|
||||
self._og_search_property('image:width', webpage, 'thumbnail width', fatal=False))
|
||||
thumbnail_h = int_or_none(
|
||||
self._og_search_property('image:height', webpage, 'thumbnail height', fatal=False))
|
||||
thumbnail = {
|
||||
'url': self._og_search_thumbnail(webpage),
|
||||
}
|
||||
if thumbnail_w and thumbnail_h:
|
||||
thumbnail.update({
|
||||
'width': thumbnail_w,
|
||||
'height': thumbnail_h,
|
||||
})
|
||||
|
||||
config = self._parse_json(self._search_regex(
|
||||
r'episodePlayer\((\{.*?\}),\s*\{', webpage, 'sources'), video_id)
|
||||
|
||||
if config.get('pGeo'):
|
||||
self.report_warning(
|
||||
'This content might not be available in your country due to copyright reasons')
|
||||
|
||||
formats = [{
|
||||
'format_id': 'hls',
|
||||
'ext': 'mp4',
|
||||
'url': config['EpisodeVideoLink_HLS'],
|
||||
}]
|
||||
|
||||
m = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>[^/]+))/(?P<play_path>.+)$', config['EpisodeVideoLink'])
|
||||
if m:
|
||||
formats.append({
|
||||
'format_id': 'rtmp',
|
||||
'ext': 'flv',
|
||||
'url': m.group('url'),
|
||||
'play_path': m.group('play_path'),
|
||||
'page_url': url,
|
||||
})
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'display_id': display_id,
|
||||
'title': title,
|
||||
'formats': formats,
|
||||
'thumbnails': [thumbnail],
|
||||
'duration': int_or_none(config.get('VideoTime')),
|
||||
'description': description,
|
||||
'age_limit': self._AGE_LIMITS.get(config.get('PGRating'), 0),
|
||||
'upload_date': upload_date,
|
||||
}
|
@ -2,7 +2,6 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
import json
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
@ -28,7 +27,6 @@ class LRTIE(InfoExtractor):
|
||||
'params': {
|
||||
'skip_download': True, # HLS download
|
||||
},
|
||||
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
@ -44,7 +42,9 @@ class LRTIE(InfoExtractor):
|
||||
|
||||
formats = []
|
||||
for js in re.findall(r'(?s)config:\s*(\{.*?\})', webpage):
|
||||
data = json.loads(js_to_json(js))
|
||||
data = self._parse_json(js, video_id, transform_source=js_to_json)
|
||||
if 'provider' not in data:
|
||||
continue
|
||||
if data['provider'] == 'rtmp':
|
||||
formats.append({
|
||||
'format_id': 'rtmp',
|
||||
|
@ -85,6 +85,7 @@ class LyndaIE(SubtitlesInfoExtractor):
|
||||
} for format_id, video_url in prioritized_streams['0'].items()
|
||||
])
|
||||
|
||||
self._check_formats(formats, video_id)
|
||||
self._sort_formats(formats)
|
||||
|
||||
if self._downloader.params.get('listsubtitles', False):
|
||||
|
@ -1,7 +1,5 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import ExtractorError
|
||||
|
||||
@ -13,21 +11,22 @@ class MacGameStoreIE(InfoExtractor):
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://www.macgamestore.com/mediaviewer.php?trailer=2450',
|
||||
'file': '2450.m4v',
|
||||
'md5': '8649b8ea684b6666b4c5be736ecddc61',
|
||||
'info_dict': {
|
||||
'id': '2450',
|
||||
'ext': 'm4v',
|
||||
'title': 'Crow',
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(
|
||||
url, video_id, 'Downloading trailer page')
|
||||
|
||||
webpage = self._download_webpage(url, video_id, 'Downloading trailer page')
|
||||
|
||||
if re.search(r'>Missing Media<', webpage) is not None:
|
||||
raise ExtractorError('Trailer %s does not exist' % video_id, expected=True)
|
||||
if '>Missing Media<' in webpage:
|
||||
raise ExtractorError(
|
||||
'Trailer %s does not exist' % video_id, expected=True)
|
||||
|
||||
video_title = self._html_search_regex(
|
||||
r'<title>MacGameStore: (.*?) Trailer</title>', webpage, 'title')
|
||||
|
@ -105,6 +105,9 @@ class OCWMITIE(InfoExtractor):
|
||||
'ext': 'mp4',
|
||||
'title': 'Lecture 7: Multiple Discrete Random Variables: Expectations, Conditioning, Independence',
|
||||
'description': 'In this lecture, the professor discussed multiple random variables, expectations, and binomial distribution.',
|
||||
'upload_date': '20121109',
|
||||
'uploader_id': 'MIT',
|
||||
'uploader': 'MIT OpenCourseWare',
|
||||
# 'subtitles': 'http://ocw.mit.edu/courses/electrical-engineering-and-computer-science/6-041-probabilistic-systems-analysis-and-applied-probability-fall-2010/video-lectures/lecture-7-multiple-variables-expectations-independence/MIT6_041F11_lec07_300k.mp4.srt'
|
||||
}
|
||||
},
|
||||
@ -114,6 +117,9 @@ class OCWMITIE(InfoExtractor):
|
||||
'id': '7K1sB05pE0A',
|
||||
'ext': 'mp4',
|
||||
'title': 'Session 1: Introduction to Derivatives',
|
||||
'upload_date': '20090818',
|
||||
'uploader_id': 'MIT',
|
||||
'uploader': 'MIT OpenCourseWare',
|
||||
'description': 'This section contains lecture video excerpts, lecture notes, an interactive mathlet with supporting documents, and problem solving videos.',
|
||||
# 'subtitles': 'http://ocw.mit.edu//courses/mathematics/18-01sc-single-variable-calculus-fall-2010/ocw-18.01-f07-lec01_300k.SRT'
|
||||
}
|
||||
|
@ -9,7 +9,7 @@ from ..compat import (
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
HEADRequest,
|
||||
int_or_none,
|
||||
str_to_int,
|
||||
parse_iso8601,
|
||||
)
|
||||
|
||||
@ -85,15 +85,17 @@ class MixcloudIE(InfoExtractor):
|
||||
uploader_id = self._search_regex(
|
||||
r'\s+"profile": "([^"]+)",', webpage, 'uploader id', fatal=False)
|
||||
description = self._og_search_description(webpage)
|
||||
like_count = int_or_none(self._search_regex(
|
||||
r'<meta itemprop="interactionCount" content="UserLikes:([0-9]+)"',
|
||||
like_count = str_to_int(self._search_regex(
|
||||
[r'<meta itemprop="interactionCount" content="UserLikes:([0-9]+)"',
|
||||
r'/favorites/?">([0-9]+)<'],
|
||||
webpage, 'like count', fatal=False))
|
||||
view_count = int_or_none(self._search_regex(
|
||||
r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"',
|
||||
view_count = str_to_int(self._search_regex(
|
||||
[r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"',
|
||||
r'/listeners/?">([0-9,.]+)</a>'],
|
||||
webpage, 'play count', fatal=False))
|
||||
timestamp = parse_iso8601(self._search_regex(
|
||||
r'<time itemprop="dateCreated" datetime="([^"]+)">',
|
||||
webpage, 'upload date'))
|
||||
webpage, 'upload date', default=None))
|
||||
|
||||
return {
|
||||
'id': track_id,
|
||||
|
@ -1,63 +1,49 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import hashlib
|
||||
import json
|
||||
import time
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import (
|
||||
compat_parse_qs,
|
||||
compat_str,
|
||||
)
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
compat_urlparse,
|
||||
)
|
||||
|
||||
|
||||
class MotorsportIE(InfoExtractor):
|
||||
IE_DESC = 'motorsport.com'
|
||||
_VALID_URL = r'http://www\.motorsport\.com/[^/?#]+/video/(?:[^/?#]+/)(?P<id>[^/]+)/(?:$|[?#])'
|
||||
_VALID_URL = r'http://www\.motorsport\.com/[^/?#]+/video/(?:[^/?#]+/)(?P<id>[^/]+)/?(?:$|[?#])'
|
||||
_TEST = {
|
||||
'url': 'http://www.motorsport.com/f1/video/main-gallery/red-bull-racing-2014-rules-explained/',
|
||||
'md5': '5592cb7c5005d9b2c163df5ac3dc04e4',
|
||||
'info_dict': {
|
||||
'id': '7063',
|
||||
'id': '2-T3WuR-KMM',
|
||||
'ext': 'mp4',
|
||||
'title': 'Red Bull Racing: 2014 Rules Explained',
|
||||
'duration': 207,
|
||||
'duration': 208,
|
||||
'description': 'A new clip from Red Bull sees Daniel Ricciardo and Sebastian Vettel explain the 2014 Formula One regulations – which are arguably the most complex the sport has ever seen.',
|
||||
'uploader': 'rainiere',
|
||||
'thumbnail': r're:^http://.*motorsport\.com/.+\.jpg$'
|
||||
}
|
||||
'uploader': 'mcomstaff',
|
||||
'uploader_id': 'UC334JIYKkVnyFoNCclfZtHQ',
|
||||
'upload_date': '20140903',
|
||||
'thumbnail': r're:^https?://.+\.jpg$'
|
||||
},
|
||||
'add_ie': ['Youtube'],
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
flashvars_code = self._html_search_regex(
|
||||
r'<embed id="player".*?flashvars="([^"]+)"', webpage, 'flashvars')
|
||||
flashvars = compat_parse_qs(flashvars_code)
|
||||
params = json.loads(flashvars['parameters'][0])
|
||||
|
||||
e = compat_str(int(time.time()) + 24 * 60 * 60)
|
||||
base_video_url = params['location'] + '?e=' + e
|
||||
s = 'h3hg713fh32'
|
||||
h = hashlib.md5((s + base_video_url).encode('utf-8')).hexdigest()
|
||||
video_url = base_video_url + '&h=' + h
|
||||
|
||||
uploader = self._html_search_regex(
|
||||
r'(?s)<span class="label">Video by: </span>(.*?)</a>', webpage,
|
||||
'uploader', fatal=False)
|
||||
iframe_path = self._html_search_regex(
|
||||
r'<iframe id="player_iframe"[^>]+src="([^"]+)"', webpage,
|
||||
'iframe path')
|
||||
iframe = self._download_webpage(
|
||||
compat_urlparse.urljoin(url, iframe_path), display_id,
|
||||
'Downloading iframe')
|
||||
youtube_id = self._search_regex(
|
||||
r'www.youtube.com/embed/(.{11})', iframe, 'youtube id')
|
||||
|
||||
return {
|
||||
'id': params['video_id'],
|
||||
'_type': 'url_transparent',
|
||||
'display_id': display_id,
|
||||
'title': params['title'],
|
||||
'url': video_url,
|
||||
'description': params.get('description'),
|
||||
'thumbnail': params.get('main_thumb'),
|
||||
'duration': int_or_none(params.get('duration')),
|
||||
'uploader': uploader,
|
||||
'url': 'https://youtube.com/watch?v=%s' % youtube_id,
|
||||
}
|
||||
|
@ -1,21 +1,19 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import json
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import int_or_none
|
||||
|
||||
|
||||
class MporaIE(InfoExtractor):
|
||||
_VALID_URL = r'^https?://(www\.)?mpora\.(?:com|de)/videos/(?P<id>[^?#/]+)'
|
||||
_VALID_URL = r'https?://(www\.)?mpora\.(?:com|de)/videos/(?P<id>[^?#/]+)'
|
||||
IE_NAME = 'MPORA'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://mpora.de/videos/AAdo8okx4wiz/embed?locale=de',
|
||||
'file': 'AAdo8okx4wiz.mp4',
|
||||
'md5': 'a7a228473eedd3be741397cf452932eb',
|
||||
'info_dict': {
|
||||
'id': 'AAdo8okx4wiz',
|
||||
'ext': 'mp4',
|
||||
'title': 'Katy Curd - Winter in the Forest',
|
||||
'duration': 416,
|
||||
'uploader': 'Peter Newman Media',
|
||||
@ -23,14 +21,12 @@ class MporaIE(InfoExtractor):
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
m = re.match(self._VALID_URL, url)
|
||||
video_id = m.group('id')
|
||||
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
data_json = self._search_regex(
|
||||
r"new FM\.Player\('[^']+',\s*(\{.*?)\).player;", webpage, 'json')
|
||||
|
||||
data = json.loads(data_json)
|
||||
data = self._parse_json(data_json, video_id)
|
||||
|
||||
uploader = data['info_overlay'].get('username')
|
||||
duration = data['video']['duration'] // 1000
|
||||
|
@ -2,10 +2,11 @@ from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from .subtitles import SubtitlesInfoExtractor
|
||||
from ..compat import (
|
||||
compat_urllib_parse,
|
||||
compat_urllib_request,
|
||||
compat_str,
|
||||
)
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
@ -22,7 +23,7 @@ def _media_xml_tag(tag):
|
||||
return '{http://search.yahoo.com/mrss/}%s' % tag
|
||||
|
||||
|
||||
class MTVServicesInfoExtractor(InfoExtractor):
|
||||
class MTVServicesInfoExtractor(SubtitlesInfoExtractor):
|
||||
_MOBILE_TEMPLATE = None
|
||||
|
||||
@staticmethod
|
||||
@ -53,7 +54,7 @@ class MTVServicesInfoExtractor(InfoExtractor):
|
||||
webpage_url = self._MOBILE_TEMPLATE % mtvn_id
|
||||
req = compat_urllib_request.Request(webpage_url)
|
||||
# Otherwise we get a webpage that would execute some javascript
|
||||
req.add_header('Youtubedl-user-agent', 'curl/7')
|
||||
req.add_header('User-Agent', 'curl/7')
|
||||
webpage = self._download_webpage(req, mtvn_id,
|
||||
'Downloading mobile page')
|
||||
metrics_url = unescapeHTML(self._search_regex(r'<a href="(http://metrics.+?)"', webpage, 'url'))
|
||||
@ -78,17 +79,42 @@ class MTVServicesInfoExtractor(InfoExtractor):
|
||||
try:
|
||||
_, _, ext = rendition.attrib['type'].partition('/')
|
||||
rtmp_video_url = rendition.find('./src').text
|
||||
formats.append({'ext': ext,
|
||||
'url': self._transform_rtmp_url(rtmp_video_url),
|
||||
'format_id': rendition.get('bitrate'),
|
||||
'width': int(rendition.get('width')),
|
||||
'height': int(rendition.get('height')),
|
||||
})
|
||||
if rtmp_video_url.endswith('siteunavail.png'):
|
||||
continue
|
||||
formats.append({
|
||||
'ext': ext,
|
||||
'url': self._transform_rtmp_url(rtmp_video_url),
|
||||
'format_id': rendition.get('bitrate'),
|
||||
'width': int(rendition.get('width')),
|
||||
'height': int(rendition.get('height')),
|
||||
})
|
||||
except (KeyError, TypeError):
|
||||
raise ExtractorError('Invalid rendition field.')
|
||||
self._sort_formats(formats)
|
||||
return formats
|
||||
|
||||
def _extract_subtitles(self, mdoc, mtvn_id):
|
||||
subtitles = {}
|
||||
FORMATS = {
|
||||
'scc': 'cea-608',
|
||||
'eia-608': 'cea-608',
|
||||
'xml': 'ttml',
|
||||
}
|
||||
subtitles_format = FORMATS.get(
|
||||
self._downloader.params.get('subtitlesformat'), 'ttml')
|
||||
for transcript in mdoc.findall('.//transcript'):
|
||||
if transcript.get('kind') != 'captions':
|
||||
continue
|
||||
lang = transcript.get('srclang')
|
||||
for typographic in transcript.findall('./typographic'):
|
||||
captions_format = typographic.get('format')
|
||||
if captions_format == subtitles_format:
|
||||
subtitles[lang] = compat_str(typographic.get('src'))
|
||||
break
|
||||
if self._downloader.params.get('listsubtitles', False):
|
||||
self._list_available_subtitles(mtvn_id, subtitles)
|
||||
return self.extract_subtitles(mtvn_id, subtitles)
|
||||
|
||||
def _get_video_info(self, itemdoc):
|
||||
uri = itemdoc.find('guid').text
|
||||
video_id = self._id_from_uri(uri)
|
||||
@ -135,6 +161,7 @@ class MTVServicesInfoExtractor(InfoExtractor):
|
||||
return {
|
||||
'title': title,
|
||||
'formats': self._extract_video_formats(mediagen_doc, mtvn_id),
|
||||
'subtitles': self._extract_subtitles(mediagen_doc, mtvn_id),
|
||||
'id': video_id,
|
||||
'thumbnail': self._get_thumbnail_url(uri, itemdoc),
|
||||
'description': description,
|
||||
@ -167,7 +194,11 @@ class MTVServicesInfoExtractor(InfoExtractor):
|
||||
mgid = self._search_regex(
|
||||
[r'data-mgid="(.*?)"', r'swfobject.embedSWF\(".*?(mgid:.*?)"'],
|
||||
webpage, 'mgid')
|
||||
return self._get_videos_info(mgid)
|
||||
|
||||
videos_info = self._get_videos_info(mgid)
|
||||
if self._downloader.params.get('listsubtitles', False):
|
||||
return
|
||||
return videos_info
|
||||
|
||||
|
||||
class MTVServicesEmbeddedIE(MTVServicesInfoExtractor):
|
||||
@ -212,25 +243,14 @@ class MTVIE(MTVServicesInfoExtractor):
|
||||
_TESTS = [
|
||||
{
|
||||
'url': 'http://www.mtv.com/videos/misc/853555/ours-vh1-storytellers.jhtml',
|
||||
'file': '853555.mp4',
|
||||
'md5': '850f3f143316b1e71fa56a4edfd6e0f8',
|
||||
'info_dict': {
|
||||
'id': '853555',
|
||||
'ext': 'mp4',
|
||||
'title': 'Taylor Swift - "Ours (VH1 Storytellers)"',
|
||||
'description': 'Album: Taylor Swift performs "Ours" for VH1 Storytellers at Harvey Mudd College.',
|
||||
},
|
||||
},
|
||||
{
|
||||
'add_ie': ['Vevo'],
|
||||
'url': 'http://www.mtv.com/videos/taylor-swift/916187/everything-has-changed-ft-ed-sheeran.jhtml',
|
||||
'file': 'USCJY1331283.mp4',
|
||||
'md5': '73b4e7fcadd88929292fe52c3ced8caf',
|
||||
'info_dict': {
|
||||
'title': 'Everything Has Changed',
|
||||
'upload_date': '20130606',
|
||||
'uploader': 'Taylor Swift',
|
||||
},
|
||||
'skip': 'VEVO is only available in some countries',
|
||||
},
|
||||
]
|
||||
|
||||
def _get_thumbnail_url(self, uri, itemdoc):
|
||||
@ -244,8 +264,8 @@ class MTVIE(MTVServicesInfoExtractor):
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
# Some videos come from Vevo.com
|
||||
m_vevo = re.search(r'isVevoVideo = true;.*?vevoVideoId = "(.*?)";',
|
||||
webpage, re.DOTALL)
|
||||
m_vevo = re.search(
|
||||
r'(?s)isVevoVideo = true;.*?vevoVideoId = "(.*?)";', webpage)
|
||||
if m_vevo:
|
||||
vevo_id = m_vevo.group(1)
|
||||
self.to_screen('Vevo video detected: %s' % vevo_id)
|
||||
|
@ -6,6 +6,7 @@ import json
|
||||
from .common import InfoExtractor
|
||||
from ..compat import (
|
||||
compat_str,
|
||||
compat_HTTPError,
|
||||
)
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
@ -78,6 +79,16 @@ class NBCNewsIE(InfoExtractor):
|
||||
},
|
||||
'add_ie': ['ThePlatform'],
|
||||
},
|
||||
{
|
||||
'url': 'http://www.nbcnews.com/feature/dateline-full-episodes/full-episode-family-business-n285156',
|
||||
'md5': 'fdbf39ab73a72df5896b6234ff98518a',
|
||||
'info_dict': {
|
||||
'id': 'Wjf9EDR3A_60',
|
||||
'ext': 'mp4',
|
||||
'title': 'FULL EPISODE: Family Business',
|
||||
'description': 'md5:757988edbaae9d7be1d585eb5d55cc04',
|
||||
},
|
||||
},
|
||||
]
|
||||
|
||||
def _real_extract(self, url):
|
||||
@ -115,10 +126,19 @@ class NBCNewsIE(InfoExtractor):
|
||||
if not base_url:
|
||||
continue
|
||||
playlist_url = base_url + '?form=MPXNBCNewsAPI'
|
||||
all_videos = self._download_json(playlist_url, title)['videos']
|
||||
|
||||
try:
|
||||
info = next(v for v in all_videos if v['mpxId'] == mpxid)
|
||||
all_videos = self._download_json(playlist_url, title)
|
||||
except ExtractorError as ee:
|
||||
if isinstance(ee.cause, compat_HTTPError):
|
||||
continue
|
||||
raise
|
||||
|
||||
if not all_videos or 'videos' not in all_videos:
|
||||
continue
|
||||
|
||||
try:
|
||||
info = next(v for v in all_videos['videos'] if v['mpxId'] == mpxid)
|
||||
break
|
||||
except StopIteration:
|
||||
continue
|
||||
|
@ -27,9 +27,7 @@ class NDTVIE(InfoExtractor):
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
filename = self._search_regex(
|
||||
|
@ -11,6 +11,7 @@ class NerdCubedFeedIE(InfoExtractor):
|
||||
_TEST = {
|
||||
'url': 'http://www.nerdcubed.co.uk/feed.json',
|
||||
'info_dict': {
|
||||
'id': 'nerdcubed-feed',
|
||||
'title': 'nerdcubed.co.uk feed',
|
||||
},
|
||||
'playlist_mincount': 1300,
|
||||
|
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user