Compare commits

...

96 Commits

Author SHA1 Message Date
Philipp Hagemeister
8f1ae18a18 release 2013.10.09 2013-10-09 23:50:47 +02:00
Philipp Hagemeister
57da92b7df [youtube] Do not recognize attribution link as user (Fixes #1573) 2013-10-09 23:50:38 +02:00
Jaime Marquínez Ferrándiz
df4f632dbc Merge pull request #1584 from wingsuit/master
Tiny tpo
2013-10-09 07:44:06 -07:00
Jaime Marquínez Ferrándiz
a34c2faae4 [youtube] set the 'name' parameter in the subtitles url (fixes #1577) 2013-10-09 16:41:36 +02:00
Tom
1d368c7589 Tiny tpo 2013-10-09 21:56:09 +08:00
Jaime Marquínez Ferrándiz
88bd97e34c [vevo] Some improvements (fixes #1580)
Extract the info from http://videoplayer.vevo.com/VideoService/AuthenticateVideo?isrc={id}
Some videos don't have an smil manifest, extract the video urls directly from the json and use the last version of the video.
Extract all the available formats and set the 'formats' field of the result
2013-10-08 21:25:38 +02:00
Jaime Marquínez Ferrándiz
2ae3edb1cf Fix the printing of the proxy map in debug mode
The proxies have to be extracted from the opener.handlers
2013-10-07 21:10:31 +02:00
Philipp Hagemeister
b2ad967e45 Simplify test setup 2013-10-07 19:06:36 +02:00
Philipp Hagemeister
a27b9e8bd5 Move opener setup into a separate helper function 2013-10-07 19:01:47 +02:00
Philipp Hagemeister
4481a754e4 release 2013.10.07 2013-10-07 14:34:19 +02:00
Philipp Hagemeister
faa6ef6bc8 [jeuxvideo] Improve code quality (fixes #1567) 2013-10-07 14:33:23 +02:00
Philipp Hagemeister
15870e90b0 Restore warning when user forgets to quote URL (#1396) 2013-10-07 12:21:24 +02:00
Jaime Marquínez Ferrándiz
387ae5f30b [vimeo] Recognize urls ending in a slash (fixes #1242) 2013-10-06 21:56:23 +02:00
Philipp Hagemeister
1310bf2474 [redtube] add age_limit 2013-10-06 16:39:35 +02:00
Philipp Hagemeister
b24f347190 Merge branch 'download-archive'
Conflicts:
	youtube_dl/YoutubeDL.py
	youtube_dl/__init__.py
2013-10-06 16:30:26 +02:00
Philipp Hagemeister
ee6c9f95e1 Remove superfluous parenthesis 2013-10-06 16:28:36 +02:00
Philipp Hagemeister
2a69c6b879 Merge branch 'age_limit' 2013-10-06 16:23:18 +02:00
Philipp Hagemeister
cfadd183c4 Call extracted property age_limit everywhere 2013-10-06 16:23:06 +02:00
Philipp Hagemeister
e484c81f0c [generic] Clarify error messages 2013-10-06 16:03:18 +02:00
Philipp Hagemeister
7e5e8306fd release 2013.10.06 2013-10-06 07:13:14 +02:00
Philipp Hagemeister
41e8bca4d0 [viddler] Add basic support (Fixes #1520) 2013-10-06 07:12:47 +02:00
Philipp Hagemeister
8dbe9899a9 Allow users to specify an age limit (fixes #1545)
With these changes, users can now restrict what videos are downloaded by the intented audience, by specifying their age with --age-limit YEARS .
Add rudimentary support in youtube, pornotube, and youporn.
2013-10-06 06:08:56 +02:00
Philipp Hagemeister
f4aac741d5 Move try_rm to test helpers 2013-10-06 05:47:17 +02:00
Philipp Hagemeister
c1c9a79c49 Add basic --download-archive option
Often, users want to be able to download only videos they haven't seen before, despite the video files having been deleted or moved in the mean time.
When --download-archive FILE is given, the extractor and ID of every download is recorded in the specified file. If it is already present, the video in question is skipped.
2013-10-06 04:27:10 +02:00
Philipp Hagemeister
226113c880 Merge remote-tracking branch 'origin/tox' 2013-10-05 22:47:44 +02:00
Filippo Valsorda
8932a66e49 [fixup] remove unnecessary commented function 2013-10-05 16:38:37 -04:00
Filippo Valsorda
79cfb46d42 add tox configuration file for easy testing 2013-10-05 16:08:48 -04:00
Filippo Valsorda
00fcc17aee add capability to suppress expected warnings in tests 2013-10-05 15:55:58 -04:00
Philipp Hagemeister
e94b783c74 [googleplus] Fix upload_date detection 2013-10-05 16:38:33 +02:00
Philipp Hagemeister
97dae9ae07 [bliptv] Make sure video ID is a string 2013-10-05 16:12:29 +02:00
Jaime Marquínez Ferrándiz
c3fef636b5 [dailymotion] Fix playlist extraction
The html code has changed, make the video ids extraction more solid.
2013-10-04 14:07:29 +02:00
Philipp Hagemeister
46e28a84ca [brightcove] Fix up some broken HTML (#1553) 2013-10-04 11:53:49 +02:00
Philipp Hagemeister
17ad2b3fb1 [yahoo] Switch ext of test 2013-10-04 11:44:56 +02:00
Philipp Hagemeister
5e2a60db4a [yahoo] Fix test title 2013-10-04 11:44:02 +02:00
Philipp Hagemeister
cd214418f6 [redtube] pep8 2013-10-04 11:41:57 +02:00
Philipp Hagemeister
ba2d9f213e [jeuxvideo] fix video file md5sum 2013-10-04 11:38:56 +02:00
Philipp Hagemeister
7f8ae73a5d Include length in player cache ID
Some videos use the same player with IDs of multiple lengths.
See https://travis-ci.org/rg3/youtube-dl/jobs/12126506#L319 for an example.
2013-10-04 11:36:06 +02:00
Philipp Hagemeister
466880f531 [yahoo] Do not try to run rtmpdump on travis 2013-10-04 11:34:12 +02:00
Philipp Hagemeister
9f1f6d2437 [rtlnow] Skip test on travis 2013-10-04 11:33:14 +02:00
Philipp Hagemeister
9e0f897f6b [francetv] Use common format for ID of generation-quoi subextractor 2013-10-04 11:30:47 +02:00
Philipp Hagemeister
c0f6aa876f Merge remote-tracking branch 'origin/master' 2013-10-04 11:14:20 +02:00
Philipp Hagemeister
d93bdee9a6 [comedycentral] Prepare for generic video extraction (#980) 2013-10-04 11:14:10 +02:00
Philipp Hagemeister
f13d09332d [mtv] Prepare for #980 2013-10-04 11:10:04 +02:00
Philipp Hagemeister
2f5865cc6d Clarify that url and ext are optional when formats is given (#980) 2013-10-04 11:09:43 +02:00
Philipp Hagemeister
deefc05b88 Document formats (for #980) 2013-10-04 10:40:42 +02:00
Philipp Hagemeister
0d8cb1cc14 [ted] Prepare #980 merge 2013-10-04 10:32:34 +02:00
Jaime Marquínez Ferrándiz
a90b9fd209 Merge pull request #1551 from rzhxeo/flickr
[FlickrIE] Fix HTTPS url
2013-10-03 23:14:12 -07:00
rzhxeo
829493439a [FlickrIE] Fix HTTPS url 2013-10-04 07:47:40 +02:00
Philipp Hagemeister
3cd022f6e6 Merge remote-tracking branch 'rzhxeo/rtl_ntv' 2013-10-04 00:59:11 +02:00
Philipp Hagemeister
abefd1f7c4 Merge remote-tracking branch 'rzhxeo/rtl_upload_date' 2013-10-04 00:58:35 +02:00
Philipp Hagemeister
c21315f273 [youtube] new static 82 signature 2013-10-04 00:43:01 +02:00
Philipp Hagemeister
9ab1018b1a release 2013.10.04 2013-10-04 00:38:19 +02:00
Philipp Hagemeister
da0a5d2d6e [france2] Add support for URLs without video IDs (Fixes #1547) 2013-10-04 00:34:36 +02:00
Jaime Marquínez Ferrándiz
ee6adb166c [ign] Support more urls and detect multiple videos in articles (fixes #1543) 2013-10-02 20:59:34 +02:00
Philipp Hagemeister
be8fe32c92 Fix help of --cachedir 2013-10-02 14:37:19 +02:00
Philipp Hagemeister
c38b1e776d [youtube] Simplify cache_dir code (#1529) 2013-10-02 08:41:14 +02:00
Philipp Hagemeister
4f8bf17f23 Merge remote-tracking branch 'holomorph/master' 2013-10-02 08:23:53 +02:00
Philipp Hagemeister
ca40186c75 [youtube] Fix static 82 signature (Closes #1539) 2013-10-02 08:20:00 +02:00
Philipp Hagemeister
a8c6b24155 [youtube] Support videos without a title (Fixes #1391, Closes #1542) 2013-10-02 07:25:35 +02:00
Filippo Valsorda
bd8e5c7ca2 Merge pull request #1531 from rg3/no-playlist
[youtube] implement --no-playlist to only download current video
2013-10-01 10:08:20 -07:00
Filippo Valsorda
7c61bd36bb [youtube] correct --no-playlist for python3 2013-10-01 11:58:13 -04:00
Jaime Marquínez Ferrándiz
c54283824c [dailymotion] Detect vevo videos (fixes #1532)
All videos from the Vevo user, just embed videos from vevo.com
2013-10-01 15:05:41 +02:00
Philipp Hagemeister
52f15da2ca release 2013.10.01.1 2013-10-01 14:44:26 +02:00
Philipp Hagemeister
44d466559e Properly handle stream meap not being present 2013-10-01 14:44:09 +02:00
Philipp Hagemeister
05751eb047 release 2013.10.01 2013-10-01 11:43:54 +02:00
Philipp Hagemeister
f10503db67 Handle videos without url_encoded_fmt_stream_map (Fixes #1535) 2013-10-01 11:39:11 +02:00
rzhxeo
adfeafe9e1 [RTLnowIE] Allow video description without upload date
Some videos (feature films) have no upload date.
2013-10-01 07:22:49 +02:00
rzhxeo
4c62a16f4f [RTLnowIE] Add support for http://n-tvnow.de 2013-10-01 06:55:30 +02:00
rzhxeo
c0de39e6d4 Merge pull request #2 from rg3/master
Update
2013-09-30 21:39:58 -07:00
Mark Oteiza
fa55675593 Support XDG base directory specification 2013-09-30 18:22:38 -04:00
Filippo Valsorda
d4d9920a26 add test for --no-playlist 2013-09-30 18:01:17 -04:00
Filippo Valsorda
47192f92d8 implement --no-playlist to only download current video - closes #755 2013-09-30 16:26:25 -04:00
Jaime Marquínez Ferrándiz
722076a123 [rtlnow] Replace one of the tests
The video is no longer available.
2013-09-29 23:07:26 +02:00
Jaime Marquínez Ferrándiz
bb4aa62cf7 [appletrailers] The request for the settings must have the trailer name in lower case (fixes #1329) 2013-09-29 20:59:19 +02:00
Jaime Marquínez Ferrándiz
843530568f [appletrailers] Rework extraction (fixes #1387)
The exraction was broken:
* The includes page contains img elements that need to be fixed.
* Use the 'itunes.inc' page, it contains a json dictionary for each trailer with information.
* Get the formats from 'includes/settings{trailer_name}.json'
* Use urljoin to allow urls with a fragment identifier to work

Removed the thumbnail urls from the tests, they are different now.
2013-09-29 20:49:58 +02:00
Philipp Hagemeister
138a5454b5 release 2013.09.29 2013-09-29 14:38:37 +02:00
Philipp Hagemeister
d279037036 [update] Prevent cmd window popup on Windows (Fixes #1478) 2013-09-29 14:37:06 +02:00
Philipp Hagemeister
46353f6783 [update] Look for .exe extension on Windows (Fixes #745) 2013-09-29 14:37:00 +02:00
Jaime Marquínez Ferrándiz
70922df8b5 [dailymotion] Disable the family filter in the playlists (fixes #1524) 2013-09-29 12:44:02 +02:00
Jaime Marquínez Ferrándiz
9c15e9de84 [yahoo] Fix video extraction (fixes #1521)
There's no need to use two different methods.
Now we can also download videos over http if possible.
Also run the test for rtmp videos, but skip the download.
2013-09-28 21:19:52 +02:00
Philipp Hagemeister
123c10608d Merge branch 'master' of github.com:rg3/youtube-dl 2013-09-28 15:43:38 +02:00
Philipp Hagemeister
0b7c2485b6 [zdf] Add support for hash URLs and simplify (#1518) 2013-09-28 15:43:34 +02:00
Jaime Marquínez Ferrándiz
9abb32045a [youtube] Add hlsvp to the error message if it can't be found and remove the live stream test
It's no longer available, other olympics streams have the same problem.
2013-09-27 15:06:27 +02:00
Jaime Marquínez Ferrándiz
f490e77e77 [youtube] Set the thumbnail to None if it can't be extracted 2013-09-27 14:22:36 +02:00
Jaime Marquínez Ferrándiz
2dc592991a [youtube] update description of test 2013-09-27 14:20:52 +02:00
Jaime Marquínez Ferrándiz
0a60edcfa9 Don't fail if the video thumbnail couldn't be downloaded (fixes #1516)
Just report a warning
2013-09-27 14:19:19 +02:00
Philipp Hagemeister
c53f9d30c8 Merge branch 'master' of github.com:rg3/youtube-dl 2013-09-27 13:09:58 +02:00
Philipp Hagemeister
509f398292 Remove youtube_genalgo (#1515)
With the automatic signature extraction, this script has become superfluous now
2013-09-27 13:09:24 +02:00
Jaime Marquínez Ferrándiz
74bab3f0a4 Don't embed subtitles if the list is empty or the field is not set (fixes #1510) 2013-09-27 08:08:43 +02:00
Philipp Hagemeister
8574862991 Merge remote-tracking branch 'rzhxeo/RTL_T' 2013-09-27 06:25:04 +02:00
Philipp Hagemeister
2de957c7e1 Merge remote-tracking branch 'rzhxeo/RTL' 2013-09-27 06:23:10 +02:00
Philipp Hagemeister
920de7a27d [youtube] Fix 83 signature (Closes #1511) 2013-09-27 06:15:21 +02:00
rzhxeo
63efc427cd [RTLnowIE] Clean video title
The title of some videos has the following format:
Series - Episode | Series online schauen bei ... NOW
2013-09-27 06:00:37 +02:00
rzhxeo
ce65fb6c76 [RTLnowIE] Add support for http://rtlnitronow.de 2013-09-27 05:50:16 +02:00
Jaime Marquínez Ferrándiz
4de1994b6e [brightcove] Use direct url for the tests
The test_all_urls.py test failed because BrightcoveIE doesn't match them.
2013-09-26 18:59:56 +02:00
Jaime Marquínez Ferrándiz
592882aa9f [brightcove] Support videos that only provide flv versions (fixes #1504)
Moved the test from generic.py to brightcove.py
2013-09-26 13:54:31 +02:00
41 changed files with 1020 additions and 587 deletions

1
.gitignore vendored
View File

@@ -25,3 +25,4 @@ updates_key.pem
*.mp4
*.part
test/testdata
.tox

View File

@@ -31,8 +31,9 @@ which means you can modify it, redistribute it or use it however you like.
--proxy URL Use the specified HTTP/HTTPS proxy
--no-check-certificate Suppress HTTPS certificate validation.
--cache-dir None Location in the filesystem where youtube-dl can
store downloaded information permanently.
~/.youtube-dl/cache by default
store downloaded information permanently. By
default $XDG_CACHE_HOME/youtube-dl or ~/.cache
/youtube-dl .
--no-cache-dir Disable filesystem caching
## Video Selection:
@@ -50,6 +51,10 @@ which means you can modify it, redistribute it or use it however you like.
--date DATE download only videos uploaded in this date
--datebefore DATE download only videos uploaded before this date
--dateafter DATE download only videos uploaded after this date
--no-playlist download only the currently playing video
--age-limit YEARS download only videos suitable for the given age
--download-archive FILE Download only videos not present in the archive
file. Record all downloaded videos in it.
## Download Options:
-r, --rate-limit LIMIT maximum download rate (e.g. 50k or 44.6m)

View File

@@ -1,116 +0,0 @@
#!/usr/bin/env python
# encoding: utf-8
# Generate youtube signature algorithm from test cases
import sys
tests = [
# 93 - vfl79wBKW 2013/07/20
(u"qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[]}|:;?/>.<'`~\"",
u".>/?;:|}][{=+-_)(*&^%$#@!MNBVCXZASDFGHJKLPOIUYTREWQ098765'321mnbvcxzasdfghjklpoiu"),
# 92 - vflQw-fB4 2013/07/17
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[]}|:;?/>.<'`~\"",
"mrtyuioplkjhgfdsazxcvbnq1234567890QWERTY}IOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[]\"|:;"),
# 91 - vfl79wBKW 2013/07/20 (sporadic)
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[]}|:;?/>.<'`~",
"/?;:|}][{=+-_)(*&^%$#@!MNBVCXZASDFGHJKLPOIUYTREWQ09876543.1mnbvcxzasdfghjklpoiu"),
# 90
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[]}|:;?/>.<'`",
"mrtyuioplkjhgfdsazxcvbne1234567890QWER[YUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={`]}|"),
# 89
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[]}|:;?/>.<'",
"/?;:|}<[{=+-_)(*&^%$#@!MqBVCXZASDFGHJKLPOIUYTREWQ0987654321mnbvcxzasdfghjklpoiuyt"),
# 88 - vflapUV9V 2013/08/28
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[]}|:;?/>.<",
"ioplkjhgfdsazxcvbnm12<4567890QWERTYUIOZLKJHGFDSAeXCVBNM!@#$%^&*()_-+={[]}|:;?/>.3"),
# 87
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$^&*()_-+={[]}|:;?/>.<",
"uioplkjhgfdsazxcvbnm1t34567890QWE2TYUIOPLKJHGFDSAZXCVeNM!@#$^&*()_-+={[]}|:;?/>.<"),
# 86 - vflHql6Pr 2013/09/24
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[|};?/>.<",
";}|[{=+-d)(*&^%$#@!MNBVCXZASDFGHJKLPOIUYT_EWQ0987654321mnbvcxzas/fghjklpoiuytrewq"),
# 85 - vflkuzxcs 2013/09/11
('0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ!"#$%&\'()*+,-./:;<=>?@[',
'3456789a0cdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRS[UVWXYZ!"#$%&\'()*+,-./:;<=>?@'),
# 84 - vflHql6Pr 2013/09/24 (sporadic)
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[};?>.<",
"}[{=+-_)g*&^%$#@!MNBVCXZASDFGHJKLPOIUYTRE(Q0987654321mnbvcxzasdf?hjklpoiuytrewq"),
# 83
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!#$%^&*()_+={[};?/>.<",
".>/?;}[{=+_)(*&^%<#!MNBVCXZASPFGHJKLwOIUYTREWQ0987654321mnbvcxzasdfghjklpoiuytreq"),
# 82 - vflGNjMhJ 2013/09/12
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKHGFDSAZXCVBNM!@#$%^&*(-+={[};?/>.<",
".>/?;}[<=+-(*&^%$#@!MNBVCXeASDFGHKLPOqUYTREWQ0987654321mnbvcxzasdfghjklpoiuytrIwZ"),
# 81 - vflLC8JvQ 2013/07/25
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKHGFDSAZXCVBNM!@#$%^&*(-+={[};?/>.",
"C>/?;}[{=+-(*&^%$#@!MNBVYXZASDFGHKLPOIU.TREWQ0q87659321mnbvcxzasdfghjkl4oiuytrewp"),
# 80 - vflZK4ZYR 2013/08/23 (sporadic)
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKHGFDSAZXCVBNM!@#$%^&*(-+={[};?/>",
"wertyuioplkjhgfdsaqxcvbnm1234567890QWERTYUIOPLKHGFDSAZXCVBNM!@#$%^&z(-+={[};?/>"),
# 79 - vflLC8JvQ 2013/07/25 (sporadic)
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKHGFDSAZXCVBNM!@#$%^&*(-+={[};?/",
"Z?;}[{=+-(*&^%$#@!MNBVCXRASDFGHKLPOIUYT/EWQ0q87659321mnbvcxzasdfghjkl4oiuytrewp"),
]
tests_age_gate = [
# 86 - vflqinMWD
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[|};?/>.<",
"ertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!/#$%^&*()_-+={[|};?@"),
]
def find_matching(wrong, right):
idxs = [wrong.index(c) for c in right]
return compress(idxs)
return ('s[%d]' % i for i in idxs)
def compress(idxs):
def _genslice(start, end, step):
starts = '' if start == 0 else str(start)
ends = ':%d' % (end+step)
steps = '' if step == 1 else (':%d' % step)
return 's[%s%s%s]' % (starts, ends, steps)
step = None
for i, prev in zip(idxs[1:], idxs[:-1]):
if step is not None:
if i - prev == step:
continue
yield _genslice(start, prev, step)
step = None
continue
if i - prev in [-1, 1]:
step = i - prev
start = prev
continue
else:
yield 's[%d]' % prev
if step is None:
yield 's[%d]' % i
else:
yield _genslice(start, i, step)
def _assert_compress(inp, exp):
res = list(compress(inp))
if res != exp:
print('Got %r, expected %r' % (res, exp))
assert res == exp
_assert_compress([0,2,4,6], ['s[0]', 's[2]', 's[4]', 's[6]'])
_assert_compress([0,1,2,4,6,7], ['s[:3]', 's[4]', 's[6:8]'])
_assert_compress([8,0,1,2,4,7,6,9], ['s[8]', 's[:3]', 's[4]', 's[7:5:-1]', 's[9]'])
def gen(wrong, right, indent):
code = ' + '.join(find_matching(wrong, right))
return 'if len(s) == %d:\n%s return %s\n' % (len(wrong), indent, code)
def genall(tests):
indent = ' ' * 8
return indent + (indent + 'el').join(gen(wrong, right, indent) for wrong,right in tests)
def main():
print(genall(tests))
print(u' Age gate:')
print(genall(tests_age_gate))
if __name__ == '__main__':
main()

View File

@@ -1,6 +1,9 @@
import errno
import io
import json
import os.path
import re
import types
import youtube_dl.extractor
from youtube_dl import YoutubeDL, YoutubeDLHandler
@@ -9,30 +12,47 @@ from youtube_dl.utils import (
compat_urllib_request,
)
# General configuration (from __init__, not very elegant...)
jar = compat_cookiejar.CookieJar()
cookie_processor = compat_urllib_request.HTTPCookieProcessor(jar)
proxy_handler = compat_urllib_request.ProxyHandler()
opener = compat_urllib_request.build_opener(proxy_handler, cookie_processor, YoutubeDLHandler())
compat_urllib_request.install_opener(opener)
youtube_dl._setup_opener(timeout=10)
PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), "parameters.json")
with io.open(PARAMETERS_FILE, encoding='utf-8') as pf:
parameters = json.load(pf)
def try_rm(filename):
""" Remove a file if it exists """
try:
os.remove(filename)
except OSError as ose:
if ose.errno != errno.ENOENT:
raise
class FakeYDL(YoutubeDL):
def __init__(self):
self.result = []
# Different instances of the downloader can't share the same dictionary
# some test set the "sublang" parameter, which would break the md5 checks.
self.params = dict(parameters)
def to_screen(self, s):
params = dict(parameters)
super(FakeYDL, self).__init__(params)
self.result = []
def to_screen(self, s, skip_eol=None):
print(s)
def trouble(self, s, tb=None):
raise Exception(s)
def download(self, x):
self.result.append(x)
def expect_warning(self, regex):
# Silence an expected warning matching a regex
old_report_warning = self.report_warning
def report_warning(self, message):
if re.match(regex, message): return
old_report_warning(message)
self.report_warning = types.MethodType(report_warning, self)
def get_testcases():
for ie in youtube_dl.extractor.gen_extractors():
t = getattr(ie, '_TEST', None)

View File

@@ -0,0 +1,53 @@
#!/usr/bin/env python
import sys
import unittest
# Allow direct execution
import os
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from youtube_dl import YoutubeDL
from helper import try_rm
def _download_restricted(url, filename, age):
""" Returns true iff the file has been downloaded """
params = {
'age_limit': age,
'skip_download': True,
'writeinfojson': True,
"outtmpl": "%(id)s.%(ext)s",
}
ydl = YoutubeDL(params)
ydl.add_default_info_extractors()
json_filename = filename + '.info.json'
try_rm(json_filename)
ydl.download([url])
res = os.path.exists(json_filename)
try_rm(json_filename)
return res
class TestAgeRestriction(unittest.TestCase):
def _assert_restricted(self, url, filename, age, old_age=None):
self.assertTrue(_download_restricted(url, filename, old_age))
self.assertFalse(_download_restricted(url, filename, age))
def test_youtube(self):
self._assert_restricted('07FYdnEawAQ', '07FYdnEawAQ.mp4', 10)
def test_youporn(self):
self._assert_restricted(
'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()

View File

@@ -2,8 +2,6 @@
import sys
import unittest
import json
import io
import hashlib
# Allow direct execution
@@ -45,15 +43,18 @@ class TestDailymotionSubtitles(unittest.TestCase):
subtitles = self.getSubtitles()
self.assertEqual(len(subtitles.keys()), 5)
def test_list_subtitles(self):
self.DL.expect_warning(u'Automatic Captions not supported by this server')
self.DL.params['listsubtitles'] = True
info_dict = self.getInfoDict()
self.assertEqual(info_dict, None)
def test_automatic_captions(self):
self.DL.expect_warning(u'Automatic Captions not supported by this server')
self.DL.params['writeautomaticsub'] = True
self.DL.params['subtitleslang'] = ['en']
subtitles = self.getSubtitles()
self.assertTrue(len(subtitles.keys()) == 0)
def test_nosubtitles(self):
self.DL.expect_warning(u'video doesn\'t have subtitles')
self.url = 'http://www.dailymotion.com/video/x12u166_le-zapping-tele-star-du-08-aout-2013_tv'
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True

View File

@@ -1,6 +1,5 @@
#!/usr/bin/env python
import errno
import hashlib
import io
import os
@@ -20,22 +19,6 @@ PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), "para
RETRIES = 3
# General configuration (from __init__, not very elegant...)
jar = compat_cookiejar.CookieJar()
cookie_processor = compat_urllib_request.HTTPCookieProcessor(jar)
proxy_handler = compat_urllib_request.ProxyHandler()
opener = compat_urllib_request.build_opener(proxy_handler, cookie_processor, YoutubeDLHandler())
compat_urllib_request.install_opener(opener)
socket.setdefaulttimeout(10)
def _try_rm(filename):
""" Remove a file if it exists """
try:
os.remove(filename)
except OSError as ose:
if ose.errno != errno.ENOENT:
raise
md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest()
class YoutubeDL(youtube_dl.YoutubeDL):
@@ -54,7 +37,8 @@ def _file_md5(fn):
with open(fn, 'rb') as f:
return hashlib.md5(f.read()).hexdigest()
from helper import get_testcases
import helper # Set up remaining global configuration
from helper import get_testcases, try_rm
defs = get_testcases()
with io.open(PARAMETERS_FILE, encoding='utf-8') as pf:
@@ -97,9 +81,9 @@ def generator(test_case):
test_cases = test_case.get('playlist', [test_case])
for tc in test_cases:
_try_rm(tc['file'])
_try_rm(tc['file'] + '.part')
_try_rm(tc['file'] + '.info.json')
try_rm(tc['file'])
try_rm(tc['file'] + '.part')
try_rm(tc['file'] + '.info.json')
try:
for retry in range(1, RETRIES + 1):
try:
@@ -145,9 +129,9 @@ def generator(test_case):
self.assertTrue(key in info_dict.keys() and info_dict[key])
finally:
for tc in test_cases:
_try_rm(tc['file'])
_try_rm(tc['file'] + '.part')
_try_rm(tc['file'] + '.info.json')
try_rm(tc['file'])
try_rm(tc['file'] + '.part')
try_rm(tc['file'] + '.info.json')
return test_template

View File

@@ -27,6 +27,14 @@ class TestYoutubeLists(unittest.TestCase):
ytie_results = [YoutubeIE()._extract_id(url['url']) for url in result['entries']]
self.assertEqual(ytie_results, [ 'bV9L5Ht9LgY', 'FXxLjLQi3Fg', 'tU3Bgo5qJZE'])
def test_youtube_playlist_noplaylist(self):
dl = FakeYDL()
dl.params['noplaylist'] = True
ie = YoutubePlaylistIE(dl)
result = ie.extract('https://www.youtube.com/watch?v=FXxLjLQi3Fg&list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re')
self.assertEqual(result['_type'], 'url')
self.assertEqual(YoutubeIE()._extract_id(result['url']), 'FXxLjLQi3Fg')
def test_issue_673(self):
dl = FakeYDL()
ie = YoutubePlaylistIE(dl)

View File

@@ -2,8 +2,6 @@
import sys
import unittest
import json
import io
import hashlib
# Allow direct execution
@@ -56,6 +54,7 @@ class TestYoutubeSubtitles(unittest.TestCase):
subtitles = self.getSubtitles()
self.assertEqual(md5(subtitles['en']), '356cdc577fde0c6783b9b822e7206ff7')
def test_youtube_list_subtitles(self):
self.DL.expect_warning(u'Video doesn\'t have automatic captions')
self.DL.params['listsubtitles'] = True
info_dict = self.getInfoDict()
self.assertEqual(info_dict, None)
@@ -66,6 +65,7 @@ class TestYoutubeSubtitles(unittest.TestCase):
subtitles = self.getSubtitles()
self.assertTrue(subtitles['it'] is not None)
def test_youtube_nosubtitles(self):
self.DL.expect_warning(u'video doesn\'t have subtitles')
self.url = 'sAjKT8FhjI8'
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True

5
tox.ini Normal file
View File

@@ -0,0 +1,5 @@
[tox]
envlist = py26,py27,py33
[testenv]
deps = nose
commands = nosetests --with-coverage --cover-package=youtube_dl --cover-html --verbose test

View File

@@ -444,8 +444,11 @@ class FFmpegEmbedSubtitlePP(FFmpegPostProcessor):
if information['ext'] != u'mp4':
self._downloader.to_screen(u'[ffmpeg] Subtitles can only be embedded in mp4 files')
return True, information
sub_langs = [key for key in information['subtitles']]
if not information.get('subtitles'):
self._downloader.to_screen(u'[ffmpeg] There aren\'t any subtitles to embed')
return True, information
sub_langs = [key for key in information['subtitles']]
filename = information['filepath']
input_files = [filename] + [subtitles_filename(filename, lang, self._subformat) for lang in sub_langs]

View File

@@ -3,6 +3,7 @@
from __future__ import absolute_import
import errno
import io
import os
import re
@@ -83,6 +84,12 @@ class YoutubeDL(object):
skip_download: Skip the actual download of the video file
cachedir: Location of the cache files in the filesystem.
None to disable filesystem cache.
noplaylist: Download single video instead of a playlist if in doubt.
age_limit: An integer representing the user's age in years.
Unsuitable videos for the given age are skipped.
downloadarchive: File name of a file where all downloads are recorded.
Videos already present in the file are not downloaded
again.
The following parameters are not used by YoutubeDL itself, they are used by
the FileDownloader:
@@ -112,7 +119,7 @@ class YoutubeDL(object):
and not params['restrictfilenames']):
# On Python 3, the Unicode filesystem API will throw errors (#1474)
self.report_warning(
u'Assuming --restrict-filenames isnce file system encoding '
u'Assuming --restrict-filenames since file system encoding '
u'cannot encode all charactes. '
u'Set the LC_ALL environment variable to fix this.')
params['restrictfilenames'] = True
@@ -308,6 +315,13 @@ class YoutubeDL(object):
dateRange = self.params.get('daterange', DateRange())
if date not in dateRange:
return u'[download] %s upload date is not in range %s' % (date_from_str(date).isoformat(), dateRange)
age_limit = self.params.get('age_limit')
if age_limit is not None:
if age_limit < info_dict.get('age_limit', 0):
return u'Skipping "' + title + '" because it is age restricted'
if self.in_download_archive(info_dict):
return (u'%(title)s has already been recorded in archive'
% info_dict)
return None
def extract_info(self, url, download=True, ie_key=None, extra_info={}):
@@ -545,11 +559,15 @@ class YoutubeDL(object):
thumb_filename = filename.rpartition('.')[0] + u'.' + thumb_format
self.to_screen(u'[%s] %s: Downloading thumbnail ...' %
(info_dict['extractor'], info_dict['id']))
uf = compat_urllib_request.urlopen(info_dict['thumbnail'])
with open(thumb_filename, 'wb') as thumbf:
shutil.copyfileobj(uf, thumbf)
self.to_screen(u'[%s] %s: Writing thumbnail to: %s' %
(info_dict['extractor'], info_dict['id'], thumb_filename))
try:
uf = compat_urllib_request.urlopen(info_dict['thumbnail'])
with open(thumb_filename, 'wb') as thumbf:
shutil.copyfileobj(uf, thumbf)
self.to_screen(u'[%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(u'Unable to download thumbnail "%s": %s' %
(info_dict['thumbnail'], compat_str(err)))
if not self.params.get('skip_download', False):
if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(filename)):
@@ -573,6 +591,8 @@ class YoutubeDL(object):
self.report_error(u'postprocessing: %s' % str(err))
return
self.record_download_archive(info_dict)
def download(self, url_list):
"""Download a given list of URLs."""
if len(url_list) > 1 and self.fixed_template():
@@ -612,3 +632,26 @@ class YoutubeDL(object):
os.remove(encodeFilename(filename))
except (IOError, OSError):
self.report_warning(u'Unable to remove downloaded video file')
def in_download_archive(self, info_dict):
fn = self.params.get('download_archive')
if fn is None:
return False
vid_id = info_dict['extractor'] + u' ' + info_dict['id']
try:
with locked_file(fn, 'r', encoding='utf-8') as archive_file:
for line in archive_file:
if line.strip() == vid_id:
return True
except IOError as ioe:
if ioe.errno != errno.ENOENT:
raise
return False
def record_download_archive(self, info_dict):
fn = self.params.get('download_archive')
if fn is None:
return
vid_id = info_dict['extractor'] + u' ' + info_dict['id']
with locked_file(fn, 'a', encoding='utf-8') as archive_file:
archive_file.write(vid_id + u'\n')

View File

@@ -36,6 +36,7 @@ __authors__ = (
__license__ = 'Public Domain'
import codecs
import collections
import getpass
import optparse
import os
@@ -168,8 +169,8 @@ def parseOpts(overrideArguments=None):
general.add_option('--proxy', dest='proxy', default=None, help='Use the specified HTTP/HTTPS proxy', metavar='URL')
general.add_option('--no-check-certificate', action='store_true', dest='no_check_certificate', default=False, help='Suppress HTTPS certificate validation.')
general.add_option(
'--cache-dir', dest='cachedir', default=u'~/.youtube-dl/cache',
help='Location in the filesystem where youtube-dl can store downloaded information permanently. %default by default')
'--cache-dir', dest='cachedir', default=get_cachedir(),
help='Location in the filesystem where youtube-dl can store downloaded information permanently. By default $XDG_CACHE_HOME/youtube-dl or ~/.cache/youtube-dl .')
general.add_option(
'--no-cache-dir', action='store_const', const=None, dest='cachedir',
help='Disable filesystem caching')
@@ -187,6 +188,13 @@ def parseOpts(overrideArguments=None):
selection.add_option('--date', metavar='DATE', dest='date', help='download only videos uploaded in this date', default=None)
selection.add_option('--datebefore', metavar='DATE', dest='datebefore', help='download only videos uploaded before this date', default=None)
selection.add_option('--dateafter', metavar='DATE', dest='dateafter', help='download only videos uploaded after this date', default=None)
selection.add_option('--no-playlist', action='store_true', dest='noplaylist', help='download only the currently playing video', default=False)
selection.add_option('--age-limit', metavar='YEARS', dest='age_limit',
help='download only videos suitable for the given age',
default=None, type=int)
selection.add_option('--download-archive', metavar='FILE',
dest='download_archive',
help='Download only videos not present in the archive file. Record all downloaded videos in it.')
authentication.add_option('-u', '--username',
@@ -369,9 +377,13 @@ def parseOpts(overrideArguments=None):
else:
xdg_config_home = os.environ.get('XDG_CONFIG_HOME')
if xdg_config_home:
userConfFile = os.path.join(xdg_config_home, 'youtube-dl.conf')
userConfFile = os.path.join(xdg_config_home, 'youtube-dl', 'config')
if not os.path.isfile(userConfFile):
userConfFile = os.path.join(xdg_config_home, 'youtube-dl.conf')
else:
userConfFile = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl.conf')
userConfFile = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl', 'config')
if not os.path.isfile(userConfFile):
userConfFile = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl.conf')
systemConf = _readOptions('/etc/youtube-dl.conf')
userConf = _readOptions(userConfFile)
commandLineConf = sys.argv[1:]
@@ -436,27 +448,7 @@ def _real_main(argv=None):
all_urls = batchurls + args
all_urls = [url.strip() for url in all_urls]
# General configuration
cookie_processor = compat_urllib_request.HTTPCookieProcessor(jar)
if opts.proxy is not None:
if opts.proxy == '':
proxies = {}
else:
proxies = {'http': opts.proxy, 'https': opts.proxy}
else:
proxies = compat_urllib_request.getproxies()
# Set HTTPS proxy to HTTP one if given (https://github.com/rg3/youtube-dl/issues/805)
if 'http' in proxies and 'https' not in proxies:
proxies['https'] = proxies['http']
proxy_handler = compat_urllib_request.ProxyHandler(proxies)
https_handler = make_HTTPS_handler(opts)
opener = compat_urllib_request.build_opener(https_handler, proxy_handler, cookie_processor, YoutubeDLHandler())
# Delete the default user-agent header, which would otherwise apply in
# cases where our custom HTTP handler doesn't come into play
# (See https://github.com/rg3/youtube-dl/issues/1309 for details)
opener.addheaders =[]
compat_urllib_request.install_opener(opener)
socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
opener = _setup_opener(jar=jar, opts=opts)
extractors = gen_extractors()
@@ -473,6 +465,8 @@ def _real_main(argv=None):
if not ie._WORKING:
continue
desc = getattr(ie, 'IE_DESC', ie.IE_NAME)
if desc is False:
continue
if hasattr(ie, 'SEARCH_KEY'):
_SEARCHES = (u'cute kittens', u'slithering pythons', u'falling cat', u'angry poodle', u'purple fish', u'running tortoise')
_COUNTS = (u'', u'5', u'10', u'all')
@@ -599,6 +593,7 @@ def _real_main(argv=None):
'progress_with_newline': opts.progress_with_newline,
'playliststart': opts.playliststart,
'playlistend': opts.playlistend,
'noplaylist': opts.noplaylist,
'logtostderr': opts.outtmpl == '-',
'consoletitle': opts.consoletitle,
'nopart': opts.nopart,
@@ -625,6 +620,8 @@ def _real_main(argv=None):
'daterange': date,
'cachedir': opts.cachedir,
'youtube_print_sig_code': opts.youtube_print_sig_code,
'age_limit': opts.age_limit,
'download_archive': opts.download_archive,
})
if opts.verbose:
@@ -644,7 +641,12 @@ def _real_main(argv=None):
except:
pass
write_string(u'[debug] Python version %s - %s' %(platform.python_version(), platform_name()) + u'\n')
write_string(u'[debug] Proxy map: ' + str(proxy_handler.proxies) + u'\n')
proxy_map = {}
for handler in opener.handlers:
if hasattr(handler, 'proxies'):
proxy_map.update(handler.proxies)
write_string(u'[debug] Proxy map: ' + compat_str(proxy_map) + u'\n')
ydl.add_default_info_extractors()
@@ -658,7 +660,7 @@ def _real_main(argv=None):
# Update version
if opts.update_self:
update_self(ydl.to_screen, opts.verbose, sys.argv[0])
update_self(ydl.to_screen, opts.verbose)
# Maybe do nothing
if len(all_urls) < 1:
@@ -682,6 +684,37 @@ def _real_main(argv=None):
sys.exit(retcode)
def _setup_opener(jar=None, opts=None, timeout=300):
if opts is None:
FakeOptions = collections.namedtuple(
'FakeOptions', ['proxy', 'no_check_certificate'])
opts = FakeOptions(proxy=None, no_check_certificate=False)
cookie_processor = compat_urllib_request.HTTPCookieProcessor(jar)
if opts.proxy is not None:
if opts.proxy == '':
proxies = {}
else:
proxies = {'http': opts.proxy, 'https': opts.proxy}
else:
proxies = compat_urllib_request.getproxies()
# Set HTTPS proxy to HTTP one if given (https://github.com/rg3/youtube-dl/issues/805)
if 'http' in proxies and 'https' not in proxies:
proxies['https'] = proxies['http']
proxy_handler = compat_urllib_request.ProxyHandler(proxies)
https_handler = make_HTTPS_handler(opts)
opener = compat_urllib_request.build_opener(
https_handler, proxy_handler, cookie_processor, YoutubeDLHandler())
# Delete the default user-agent header, which would otherwise apply in
# cases where our custom HTTP handler doesn't come into play
# (See https://github.com/rg3/youtube-dl/issues/1309 for details)
opener.addheaders = []
compat_urllib_request.install_opener(opener)
socket.setdefaulttimeout(timeout)
return opener
def main(argv=None):
try:
_real_main(argv)

View File

@@ -117,6 +117,7 @@ from .veehd import VeeHDIE
from .veoh import VeohIE
from .vevo import VevoIE
from .vice import ViceIE
from .viddler import ViddlerIE
from .videofyme import VideofyMeIE
from .vimeo import VimeoIE, VimeoChannelIE
from .vine import VineIE
@@ -140,6 +141,7 @@ from .youtube import (
YoutubeShowIE,
YoutubeSubscriptionsIE,
YoutubeRecommendedIE,
YoutubeTruncatedURLIE,
YoutubeWatchLaterIE,
YoutubeFavouritesIE,
)

View File

@@ -1,8 +1,10 @@
import re
import xml.etree.ElementTree
import json
from .common import InfoExtractor
from ..utils import (
compat_urlparse,
determine_ext,
)
@@ -14,10 +16,9 @@ class AppleTrailersIE(InfoExtractor):
u"playlist": [
{
u"file": u"manofsteel-trailer4.mov",
u"md5": u"11874af099d480cc09e103b189805d5f",
u"md5": u"d97a8e575432dbcb81b7c3acb741f8a8",
u"info_dict": {
u"duration": 111,
u"thumbnail": u"http://trailers.apple.com/trailers/wb/manofsteel/images/thumbnail_11624.jpg",
u"title": u"Trailer 4",
u"upload_date": u"20130523",
u"uploader_id": u"wb",
@@ -25,10 +26,9 @@ class AppleTrailersIE(InfoExtractor):
},
{
u"file": u"manofsteel-trailer3.mov",
u"md5": u"07a0a262aae5afe68120eed61137ab34",
u"md5": u"b8017b7131b721fb4e8d6f49e1df908c",
u"info_dict": {
u"duration": 182,
u"thumbnail": u"http://trailers.apple.com/trailers/wb/manofsteel/images/thumbnail_10793.jpg",
u"title": u"Trailer 3",
u"upload_date": u"20130417",
u"uploader_id": u"wb",
@@ -36,10 +36,9 @@ class AppleTrailersIE(InfoExtractor):
},
{
u"file": u"manofsteel-trailer.mov",
u"md5": u"e401fde0813008e3307e54b6f384cff1",
u"md5": u"d0f1e1150989b9924679b441f3404d48",
u"info_dict": {
u"duration": 148,
u"thumbnail": u"http://trailers.apple.com/trailers/wb/manofsteel/images/thumbnail_8703.jpg",
u"title": u"Trailer",
u"upload_date": u"20121212",
u"uploader_id": u"wb",
@@ -47,10 +46,9 @@ class AppleTrailersIE(InfoExtractor):
},
{
u"file": u"manofsteel-teaser.mov",
u"md5": u"76b392f2ae9e7c98b22913c10a639c97",
u"md5": u"5fe08795b943eb2e757fa95cb6def1cb",
u"info_dict": {
u"duration": 93,
u"thumbnail": u"http://trailers.apple.com/trailers/wb/manofsteel/images/thumbnail_6899.jpg",
u"title": u"Teaser",
u"upload_date": u"20120721",
u"uploader_id": u"wb",
@@ -59,87 +57,61 @@ class AppleTrailersIE(InfoExtractor):
]
}
_JSON_RE = r'iTunes.playURL\((.*?)\);'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
movie = mobj.group('movie')
uploader_id = mobj.group('company')
playlist_url = url.partition(u'?')[0] + u'/includes/playlists/web.inc'
playlist_url = compat_urlparse.urljoin(url, u'includes/playlists/itunes.inc')
playlist_snippet = self._download_webpage(playlist_url, movie)
playlist_cleaned = re.sub(r'(?s)<script>.*?</script>', u'', playlist_snippet)
playlist_cleaned = re.sub(r'(?s)<script[^<]*?>.*?</script>', u'', playlist_snippet)
playlist_cleaned = re.sub(r'<img ([^<]*?)>', r'<img \1/>', playlist_cleaned)
# The ' in the onClick attributes are not escaped, it couldn't be parsed
# with xml.etree.ElementTree.fromstring
# like: http://trailers.apple.com/trailers/wb/gravity/
def _clean_json(m):
return u'iTunes.playURL(%s);' % m.group(1).replace('\'', '&#39;')
playlist_cleaned = re.sub(self._JSON_RE, _clean_json, playlist_cleaned)
playlist_html = u'<html>' + playlist_cleaned + u'</html>'
size_cache = {}
doc = xml.etree.ElementTree.fromstring(playlist_html)
playlist = []
for li in doc.findall('./div/ul/li'):
title = li.find('.//h3').text
on_click = li.find('.//a').attrib['onClick']
trailer_info_json = self._search_regex(self._JSON_RE,
on_click, u'trailer info')
trailer_info = json.loads(trailer_info_json)
title = trailer_info['title']
video_id = movie + '-' + re.sub(r'[^a-zA-Z0-9]', '', title).lower()
thumbnail = li.find('.//img').attrib['src']
upload_date = trailer_info['posted'].replace('-', '')
date_el = li.find('.//p')
upload_date = None
m = re.search(r':\s?(?P<month>[0-9]{2})/(?P<day>[0-9]{2})/(?P<year>[0-9]{2})', date_el.text)
if m:
upload_date = u'20' + m.group('year') + m.group('month') + m.group('day')
runtime_el = date_el.find('./br')
m = re.search(r':\s?(?P<minutes>[0-9]+):(?P<seconds>[0-9]{1,2})', runtime_el.tail)
runtime = trailer_info['runtime']
m = re.search(r'(?P<minutes>[0-9]+):(?P<seconds>[0-9]{1,2})', runtime)
duration = None
if m:
duration = 60 * int(m.group('minutes')) + int(m.group('seconds'))
first_url = trailer_info['url']
trailer_id = first_url.split('/')[-1].rpartition('_')[0].lower()
settings_json_url = compat_urlparse.urljoin(url, 'includes/settings/%s.json' % trailer_id)
settings_json = self._download_webpage(settings_json_url, trailer_id, u'Downloading settings json')
settings = json.loads(settings_json)
formats = []
for formats_el in li.findall('.//a'):
if formats_el.attrib['class'] != 'OverlayPanel':
continue
target = formats_el.attrib['target']
format_code = formats_el.text
if 'Automatic' in format_code:
continue
size_q = formats_el.attrib['href']
size_id = size_q.rpartition('#videos-')[2]
if size_id not in size_cache:
size_url = url + size_q
sizepage_html = self._download_webpage(
size_url, movie,
note=u'Downloading size info %s' % size_id,
errnote=u'Error while downloading size info %s' % size_id,
)
_doc = xml.etree.ElementTree.fromstring(sizepage_html)
size_cache[size_id] = _doc
sizepage_doc = size_cache[size_id]
links = sizepage_doc.findall('.//{http://www.w3.org/1999/xhtml}ul/{http://www.w3.org/1999/xhtml}li/{http://www.w3.org/1999/xhtml}a')
for vid_a in links:
href = vid_a.get('href')
if not href.endswith(target):
continue
detail_q = href.partition('#')[0]
detail_url = url + '/' + detail_q
m = re.match(r'includes/(?P<detail_id>[^/]+)/', detail_q)
detail_id = m.group('detail_id')
detail_html = self._download_webpage(
detail_url, movie,
note=u'Downloading detail %s %s' % (detail_id, size_id),
errnote=u'Error while downloading detail %s %s' % (detail_id, size_id)
)
detail_doc = xml.etree.ElementTree.fromstring(detail_html)
movie_link_el = detail_doc.find('.//{http://www.w3.org/1999/xhtml}a')
assert movie_link_el.get('class') == 'movieLink'
movie_link = movie_link_el.get('href').partition('?')[0].replace('_', '_h')
ext = determine_ext(movie_link)
assert ext == 'mov'
formats.append({
'format': format_code,
'ext': ext,
'url': movie_link,
})
for format in settings['metadata']['sizes']:
# The src is a file pointing to the real video file
format_url = re.sub(r'_(\d*p.mov)', r'_h\1', format['src'])
formats.append({
'url': format_url,
'ext': determine_ext(format_url),
'format': format['type'],
'width': format['width'],
'height': int(format['height']),
})
formats = sorted(formats, key=lambda f: (f['height'], f['width']))
info = {
'_type': 'video',

View File

@@ -115,7 +115,7 @@ class BlipTVIE(InfoExtractor):
ext = umobj.group(1)
info = {
'id': data['item_id'],
'id': compat_str(data['item_id']),
'url': video_url,
'uploader': data['display_name'],
'upload_date': upload_date,

View File

@@ -1,3 +1,5 @@
# encoding: utf-8
import re
import json
import xml.etree.ElementTree
@@ -7,15 +9,39 @@ from ..utils import (
compat_urllib_parse,
find_xpath_attr,
compat_urlparse,
ExtractorError,
)
class BrightcoveIE(InfoExtractor):
_VALID_URL = r'https?://.*brightcove\.com/(services|viewer).*\?(?P<query>.*)'
_FEDERATED_URL_TEMPLATE = 'http://c.brightcove.com/services/viewer/htmlFederated?%s'
_PLAYLIST_URL_TEMPLATE = 'http://c.brightcove.com/services/json/experience/runtime/?command=get_programming_for_experience&playerKey=%s'
# There is a test for Brigtcove in GenericIE, that way we test both the download
# and the detection of videos, and we don't have to find an URL that is always valid
_TESTS = [
{
# From http://www.8tv.cat/8aldia/videos/xavier-sala-i-martin-aquesta-tarda-a-8-al-dia/
u'url': u'http://c.brightcove.com/services/viewer/htmlFederated?playerID=1654948606001&flashID=myExperience&%40videoPlayer=2371591881001',
u'file': u'2371591881001.mp4',
u'md5': u'9e80619e0a94663f0bdc849b4566af19',
u'note': u'Test Brightcove downloads and detection in GenericIE',
u'info_dict': {
u'title': u'Xavier Sala i Martín: “Un banc que no presta és un banc zombi que no serveix per a res”',
u'uploader': u'8TV',
u'description': u'md5:a950cc4285c43e44d763d036710cd9cd',
}
},
{
# From http://medianetwork.oracle.com/video/player/1785452137001
u'url': u'http://c.brightcove.com/services/viewer/htmlFederated?playerID=1217746023001&flashID=myPlayer&%40videoPlayer=1785452137001',
u'file': u'1785452137001.flv',
u'info_dict': {
u'title': u'JVMLS 2012: Arrays 2.0 - Opportunities and Challenges',
u'description': u'John Rose speaks at the JVM Language Summit, August 1, 2012.',
u'uploader': u'Oracle',
},
},
]
@classmethod
def _build_brighcove_url(cls, object_str):
@@ -23,6 +49,11 @@ class BrightcoveIE(InfoExtractor):
Build a Brightcove url from a xml string containing
<object class="BrightcoveExperience">{params}</object>
"""
# Fix up some stupid HTML, see https://github.com/rg3/youtube-dl/issues/1553
object_str = re.sub(r'(<param name="[^"]+" value="[^"]+")>',
lambda m: m.group(1) + '/>', object_str)
object_doc = xml.etree.ElementTree.fromstring(object_str)
assert u'BrightcoveExperience' in object_doc.attrib['class']
params = {'flashID': object_doc.attrib['id'],
@@ -72,15 +103,27 @@ class BrightcoveIE(InfoExtractor):
playlist_title=playlist_info['mediaCollectionDTO']['displayName'])
def _extract_video_info(self, video_info):
renditions = video_info['renditions']
renditions = sorted(renditions, key=lambda r: r['size'])
best_format = renditions[-1]
info = {
'id': video_info['id'],
'title': video_info['displayName'],
'description': video_info.get('shortDescription'),
'thumbnail': video_info.get('videoStillURL') or video_info.get('thumbnailURL'),
'uploader': video_info.get('publisherName'),
}
return {'id': video_info['id'],
'title': video_info['displayName'],
'url': best_format['defaultURL'],
renditions = video_info.get('renditions')
if renditions:
renditions = sorted(renditions, key=lambda r: r['size'])
best_format = renditions[-1]
info.update({
'url': best_format['defaultURL'],
'ext': 'mp4',
'description': video_info.get('shortDescription'),
'thumbnail': video_info.get('videoStillURL') or video_info.get('thumbnailURL'),
'uploader': video_info.get('publisherName'),
}
})
elif video_info.get('FLVFullLengthURL') is not None:
info.update({
'url': video_info['FLVFullLengthURL'],
'ext': 'flv',
})
else:
raise ExtractorError(u'Unable to extract video url for %s' % info['id'])
return info

View File

@@ -51,12 +51,12 @@ class ComedyCentralIE(InfoExtractor):
'400': 'mp4',
}
_video_dimensions = {
'3500': '1280x720',
'2200': '960x540',
'1700': '768x432',
'1200': '640x360',
'750': '512x288',
'400': '384x216',
'3500': (1280, 720),
'2200': (960, 540),
'1700': (768, 432),
'1200': (640, 360),
'750': (512, 288),
'400': (384, 216),
}
@classmethod
@@ -64,11 +64,13 @@ class ComedyCentralIE(InfoExtractor):
"""Receives a URL and returns True if suitable for this IE."""
return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
def _print_formats(self, formats):
print('Available formats:')
for x in formats:
print('%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'mp4'), self._video_dimensions.get(x, '???')))
@staticmethod
def _transform_rtmp_url(rtmp_video_url):
m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp.comedystor/.*)$', rtmp_video_url)
if not m:
raise ExtractorError(u'Cannot transform RTMP url')
base = 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=1+_pxI0=Ripod-h264+_pxL0=undefined+_pxM0=+_pxK=18639+_pxE=mp4/44620/mtvnorigin/'
return base + m.group('finalid')
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url, re.VERBOSE)
@@ -155,40 +157,31 @@ class ComedyCentralIE(InfoExtractor):
self._downloader.report_error(u'unable to download ' + mediaId + ': No videos found')
continue
if self._downloader.params.get('listformats', None):
self._print_formats([i[0] for i in turls])
return
# For now, just pick the highest bitrate
format,rtmp_video_url = turls[-1]
# Get the format arg from the arg stream
req_format = self._downloader.params.get('format', None)
# Select format if we can find one
for f,v in turls:
if f == req_format:
format, rtmp_video_url = f, v
break
m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp.comedystor/.*)$', rtmp_video_url)
if not m:
raise ExtractorError(u'Cannot transform RTMP url')
base = 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=1+_pxI0=Ripod-h264+_pxL0=undefined+_pxM0=+_pxK=18639+_pxE=mp4/44620/mtvnorigin/'
video_url = base + m.group('finalid')
formats = []
for format, rtmp_video_url in turls:
w, h = self._video_dimensions.get(format, (None, None))
formats.append({
'url': self._transform_rtmp_url(rtmp_video_url),
'ext': self._video_extensions.get(format, 'mp4'),
'format_id': format,
'height': h,
'width': w,
})
effTitle = showId + u'-' + epTitle + u' part ' + compat_str(partNum+1)
info = {
'id': shortMediaId,
'url': video_url,
'formats': formats,
'uploader': showId,
'upload_date': officialDate,
'title': effTitle,
'ext': 'mp4',
'format': format,
'thumbnail': None,
'description': compat_str(officialTitle),
}
# TODO: Remove when #980 has been merged
info.update(info['formats'][-1])
results.append(info)
return results

View File

@@ -35,6 +35,8 @@ class InfoExtractor(object):
title: Video title, unescaped.
ext: Video filename extension.
Instead of url and ext, formats can also specified.
The following fields are optional:
format: The video format, defaults to ext (used for --get-format)
@@ -52,8 +54,20 @@ class InfoExtractor(object):
view_count: How many users have watched the video on the platform.
urlhandle: [internal] The urlHandle to be used to download the file,
like returned by urllib.request.urlopen
age_limit: Age restriction for the video, as an integer (years)
formats: A list of dictionaries for each format available, it must
be ordered from worst to best quality. Potential fields:
* url Mandatory. The URL of the video file
* ext Will be calculated from url if missing
* format A human-readable description of the format
("mp4 container with h264/opus").
Calculated from width and height if missing.
* format_id A short description of the format
("mp4_h264_opus" or "19")
* width Width of the video, if known
* height Height of the video, if known
The fields should all be Unicode strings.
Unless mentioned otherwise, the fields should be Unicode strings.
Subclasses of this one should re-define the _real_initialize() and
_real_extract() methods and define a _VALID_URL regexp.
@@ -305,6 +319,15 @@ class InfoExtractor(object):
self._og_regex('video')],
html, name, **kargs)
def _rta_search(self, html):
# See http://www.rtalabel.org/index.php?content=howtofaq#single
if re.search(r'(?ix)<meta\s+name="rating"\s+'
r' content="RTA-5042-1996-1400-1577-RTA"',
html):
return 18
return 0
class SearchInfoExtractor(InfoExtractor):
"""
Base class for paged search queries extractors.

View File

@@ -10,25 +10,49 @@ from ..utils import (
compat_str,
get_element_by_attribute,
get_element_by_id,
orderedSet,
ExtractorError,
)
class DailymotionBaseInfoExtractor(InfoExtractor):
@staticmethod
def _build_request(url):
"""Build a request with the family filter disabled"""
request = compat_urllib_request.Request(url)
request.add_header('Cookie', 'family_filter=off')
return request
class DailymotionIE(SubtitlesInfoExtractor):
class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
"""Information Extractor for Dailymotion"""
_VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/(?:embed/)?video/([^/]+)'
IE_NAME = u'dailymotion'
_TEST = {
u'url': u'http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech',
u'file': u'x33vw9.mp4',
u'md5': u'392c4b85a60a90dc4792da41ce3144eb',
u'info_dict': {
u"uploader": u"Amphora Alex and Van .",
u"title": u"Tutoriel de Youtubeur\"DL DES VIDEO DE YOUTUBE\""
}
}
_TESTS = [
{
u'url': u'http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech',
u'file': u'x33vw9.mp4',
u'md5': u'392c4b85a60a90dc4792da41ce3144eb',
u'info_dict': {
u"uploader": u"Amphora Alex and Van .",
u"title": u"Tutoriel de Youtubeur\"DL DES VIDEO DE YOUTUBE\""
}
},
# Vevo video
{
u'url': u'http://www.dailymotion.com/video/x149uew_katy-perry-roar-official_musi',
u'file': u'USUV71301934.mp4',
u'info_dict': {
u'title': u'Roar (Official)',
u'uploader': u'Katy Perry',
u'upload_date': u'20130905',
},
u'params': {
u'skip_download': True,
},
u'skip': u'VEVO is only available in some countries',
},
]
def _real_extract(self, url):
# Extract id and simplified title from URL
@@ -40,13 +64,21 @@ class DailymotionIE(SubtitlesInfoExtractor):
url = 'http://www.dailymotion.com/video/%s' % video_id
# Retrieve video webpage to extract further information
request = compat_urllib_request.Request(url)
request.add_header('Cookie', 'family_filter=off')
request = self._build_request(url)
webpage = self._download_webpage(request, video_id)
# Extract URL, uploader and title from webpage
self.report_extraction(video_id)
# It may just embed a vevo video:
m_vevo = re.search(
r'<link rel="video_src" href="[^"]*?vevo.com[^"]*?videoId=(?P<id>[\w]*)',
webpage)
if m_vevo is not None:
vevo_id = m_vevo.group('id')
self.to_screen(u'Vevo video detected: %s' % vevo_id)
return self.url_result(u'vevo:%s' % vevo_id, ie='Vevo')
video_uploader = self._search_regex([r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a>',
# Looking for official user
r'<(?:span|a) .*?rel="author".*?>([^<]+?)</'],
@@ -113,7 +145,7 @@ class DailymotionIE(SubtitlesInfoExtractor):
return {}
class DailymotionPlaylistIE(InfoExtractor):
class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
IE_NAME = u'dailymotion:playlist'
_VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P<id>.+?)/'
_MORE_PAGES_INDICATOR = r'<div class="next">.*?<a.*?href="/playlist/.+?".*?>.*?</a>.*?</div>'
@@ -122,16 +154,17 @@ class DailymotionPlaylistIE(InfoExtractor):
def _extract_entries(self, id):
video_ids = []
for pagenum in itertools.count(1):
webpage = self._download_webpage(self._PAGE_TEMPLATE % (id, pagenum),
request = self._build_request(self._PAGE_TEMPLATE % (id, pagenum))
webpage = self._download_webpage(request,
id, u'Downloading page %s' % pagenum)
playlist_el = get_element_by_attribute(u'class', u'video_list', webpage)
video_ids.extend(re.findall(r'data-id="(.+?)" data-ext-id', playlist_el))
video_ids.extend(re.findall(r'data-id="(.+?)"', playlist_el))
if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
break
return [self.url_result('http://www.dailymotion.com/video/%s' % video_id, 'Dailymotion')
for video_id in video_ids]
for video_id in orderedSet(video_ids)]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)

View File

@@ -9,7 +9,7 @@ from ..utils import (
class FlickrIE(InfoExtractor):
"""Information Extractor for Flickr videos"""
_VALID_URL = r'(?:https?://)?(?:www\.)?flickr\.com/photos/(?P<uploader_id>[\w\-_@]+)/(?P<id>\d+).*'
_VALID_URL = r'(?:https?://)?(?:www\.|secure\.)?flickr\.com/photos/(?P<uploader_id>[\w\-_@]+)/(?P<id>\d+).*'
_TEST = {
u'url': u'http://www.flickr.com/photos/forestwander-nature-pictures/5645318632/in/photostream/',
u'file': u'5645318632.mp4',

View File

@@ -70,7 +70,11 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor):
class France2IE(FranceTVBaseInfoExtractor):
IE_NAME = u'france2.fr'
_VALID_URL = r'https?://www\.france2\.fr/emissions/.*?/videos/(?P<id>\d+)'
_VALID_URL = r'''(?x)https?://www\.france2\.fr/
(?:
emissions/.*?/videos/(?P<id>\d+)
| emission/(?P<key>[^/?]+)
)'''
_TEST = {
u'url': u'http://www.france2.fr/emissions/13h15-le-samedi-le-dimanche/videos/75540104',
@@ -86,12 +90,20 @@ class France2IE(FranceTVBaseInfoExtractor):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
if mobj.group('key'):
webpage = self._download_webpage(url, mobj.group('key'))
video_id = self._html_search_regex(
r'''(?x)<div\s+class="video-player">\s*
<a\s+href="http://videos.francetv.fr/video/([0-9]+)"\s+
class="francetv-video-player">''',
webpage, u'video ID')
else:
video_id = mobj.group('id')
return self._extract_video(video_id)
class GenerationQuoiIE(InfoExtractor):
IE_NAME = u'http://generation-quoi.france2.fr'
IE_NAME = u'france2.fr:generation-quoi'
_VALID_URL = r'https?://generation-quoi\.france2\.fr/portrait/(?P<name>.*)(\?|$)'
_TEST = {

View File

@@ -29,17 +29,6 @@ class GenericIE(InfoExtractor):
u"title": u"R\u00e9gis plante sa Jeep"
}
},
{
u'url': u'http://www.8tv.cat/8aldia/videos/xavier-sala-i-martin-aquesta-tarda-a-8-al-dia/',
u'file': u'2371591881001.mp4',
u'md5': u'9e80619e0a94663f0bdc849b4566af19',
u'note': u'Test Brightcove downloads and detection in GenericIE',
u'info_dict': {
u'title': u'Xavier Sala i Martín: “Un banc que no presta és un banc zombi que no serveix per a res”',
u'uploader': u'8TV',
u'description': u'md5:a950cc4285c43e44d763d036710cd9cd',
}
},
]
def report_download_webpage(self, video_id):
@@ -128,7 +117,7 @@ class GenericIE(InfoExtractor):
except ValueError:
# since this is the last-resort InfoExtractor, if
# this error is thrown, it'll be thrown here
raise ExtractorError(u'Invalid URL: %s' % url)
raise ExtractorError(u'Failed to download URL: %s' % url)
self.report_extraction(video_id)
# Look for BrightCove:
@@ -160,12 +149,12 @@ class GenericIE(InfoExtractor):
# HTML5 video
mobj = re.search(r'<video[^<]*(?:>.*?<source.*?)? src="([^"]+)"', webpage, flags=re.DOTALL)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
raise ExtractorError(u'Unsupported URL: %s' % url)
# It's possible that one of the regexes
# matched, but returned an empty group:
if mobj.group(1) is None:
raise ExtractorError(u'Invalid URL: %s' % url)
raise ExtractorError(u'Did not find a valid video URL at %s' % url)
video_url = mobj.group(1)
video_url = compat_urlparse.urljoin(url, video_url)

View File

@@ -41,7 +41,8 @@ class GooglePlusIE(InfoExtractor):
# Extract update date
upload_date = self._html_search_regex(
['title="Timestamp">(.*?)</a>', r'<a.+?class="g-M.+?>(.+?)</a>'],
r'''(?x)<a.+?class="o-T-s\s[^"]+"\s+style="display:\s*none"\s*>
([0-9]{4}-[0-9]{2}-[0-9]{2})</a>''',
webpage, u'upload date', fatal=False)
if upload_date:
# Convert timestring to a format suitable for filename

View File

@@ -13,7 +13,7 @@ class IGNIE(InfoExtractor):
Some videos of it.ign.com are also supported
"""
_VALID_URL = r'https?://.+?\.ign\.com/(?P<type>videos|show_videos|articles)(/.+)?/(?P<name_or_id>.+)'
_VALID_URL = r'https?://.+?\.ign\.com/(?P<type>videos|show_videos|articles|(?:[^/]*/feature))(/.+)?/(?P<name_or_id>.+)'
IE_NAME = u'ign.com'
_CONFIG_URL_TEMPLATE = 'http://www.ign.com/videos/configs/id/%s.config'
@@ -21,15 +21,39 @@ class IGNIE(InfoExtractor):
r'id="my_show_video">.*?<p>(.*?)</p>',
]
_TEST = {
u'url': u'http://www.ign.com/videos/2013/06/05/the-last-of-us-review',
u'file': u'8f862beef863986b2785559b9e1aa599.mp4',
u'md5': u'eac8bdc1890980122c3b66f14bdd02e9',
u'info_dict': {
u'title': u'The Last of Us Review',
u'description': u'md5:c8946d4260a4d43a00d5ae8ed998870c',
}
}
_TESTS = [
{
u'url': u'http://www.ign.com/videos/2013/06/05/the-last-of-us-review',
u'file': u'8f862beef863986b2785559b9e1aa599.mp4',
u'md5': u'eac8bdc1890980122c3b66f14bdd02e9',
u'info_dict': {
u'title': u'The Last of Us Review',
u'description': u'md5:c8946d4260a4d43a00d5ae8ed998870c',
}
},
{
u'url': u'http://me.ign.com/en/feature/15775/100-little-things-in-gta-5-that-will-blow-your-mind',
u'playlist': [
{
u'file': u'5ebbd138523268b93c9141af17bec937.mp4',
u'info_dict': {
u'title': u'GTA 5 Video Review',
u'description': u'Rockstar drops the mic on this generation of games. Watch our review of the masterly Grand Theft Auto V.',
},
},
{
u'file': u'638672ee848ae4ff108df2a296418ee2.mp4',
u'info_dict': {
u'title': u'GTA 5\'s Twisted Beauty in Super Slow Motion',
u'description': u'The twisted beauty of GTA 5 in stunning slow motion.',
},
},
],
u'params': {
u'skip_download': True,
},
},
]
def _find_video_id(self, webpage):
res_id = [r'data-video-id="(.+?)"',
@@ -46,6 +70,13 @@ class IGNIE(InfoExtractor):
if page_type == 'articles':
video_url = self._search_regex(r'var videoUrl = "(.+?)"', webpage, u'video url')
return self.url_result(video_url, ie='IGN')
elif page_type != 'video':
multiple_urls = re.findall(
'<param name="flashvars" value="[^"]*?url=(https?://www\.ign\.com/videos/.*?)["&]',
webpage)
if multiple_urls:
return [self.url_result(u, ie='IGN') for u in multiple_urls]
video_id = self._find_video_id(webpage)
result = self._get_video_info(video_id)
description = self._html_search_regex(self._DESCRIPTION_RE,
@@ -87,6 +118,9 @@ class OneUPIE(IGNIE):
}
}
# Override IGN tests
_TESTS = []
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
id = mobj.group('name_or_id')

View File

@@ -6,13 +6,14 @@ import xml.etree.ElementTree
from .common import InfoExtractor
class JeuxVideoIE(InfoExtractor):
_VALID_URL = r'http://.*?\.jeuxvideo\.com/.*/(.*?)-\d+\.htm'
_TEST = {
u'url': u'http://www.jeuxvideo.com/reportages-videos-jeux/0004/00046170/tearaway-playstation-vita-gc-2013-tearaway-nous-presente-ses-papiers-d-identite-00115182.htm',
u'file': u'5182.mp4',
u'md5': u'e0fdb0cd3ce98713ef9c1e1e025779d0',
u'md5': u'046e491afb32a8aaac1f44dd4ddd54ee',
u'info_dict': {
u'title': u'GC 2013 : Tearaway nous présente ses papiers d\'identité',
u'description': u'Lorsque les développeurs de LittleBigPlanet proposent un nouveau titre, on ne peut que s\'attendre à un résultat original et fort attrayant.\n',
@@ -23,25 +24,29 @@ class JeuxVideoIE(InfoExtractor):
mobj = re.match(self._VALID_URL, url)
title = re.match(self._VALID_URL, url).group(1)
webpage = self._download_webpage(url, title)
m_download = re.search(r'<param name="flashvars" value="config=(.*?)" />', webpage)
xml_link = m_download.group(1)
xml_link = self._html_search_regex(
r'<param name="flashvars" value="config=(.*?)" />',
webpage, u'config URL')
id = re.search(r'http://www.jeuxvideo.com/config/\w+/0011/(.*?)/\d+_player\.xml', xml_link).group(1)
video_id = self._search_regex(
r'http://www\.jeuxvideo\.com/config/\w+/\d+/(.*?)/\d+_player\.xml',
xml_link, u'video ID')
xml_config = self._download_webpage(xml_link, title,
'Downloading XML config')
xml_config = self._download_webpage(
xml_link, title, u'Downloading XML config')
config = xml.etree.ElementTree.fromstring(xml_config.encode('utf-8'))
info = re.search(r'<format\.json>(.*?)</format\.json>',
xml_config, re.MULTILINE|re.DOTALL).group(1)
info = json.loads(info)['versions'][0]
info_json = self._search_regex(
r'(?sm)<format\.json>(.*?)</format\.json>',
xml_config, u'JSON information')
info = json.loads(info_json)['versions'][0]
video_url = 'http://video720.jeuxvideo.com/' + info['file']
return {'id': id,
'title' : config.find('titre_video').text,
'ext' : 'mp4',
'url' : video_url,
'description': self._og_search_description(webpage),
'thumbnail': config.find('image').text,
}
return {
'id': video_id,
'title': config.find('titre_video').text,
'ext': 'mp4',
'url': video_url,
'description': self._og_search_description(webpage),
'thumbnail': config.find('image').text,
}

View File

@@ -54,23 +54,26 @@ class MTVIE(InfoExtractor):
def _get_thumbnail_url(self, uri, itemdoc):
return 'http://mtv.mtvnimages.com/uri/' + uri
def _extract_video_url(self, metadataXml):
def _extract_video_formats(self, metadataXml):
if '/error_country_block.swf' in metadataXml:
raise ExtractorError(u'This video is not available from your country.', expected=True)
mdoc = xml.etree.ElementTree.fromstring(metadataXml.encode('utf-8'))
renditions = mdoc.findall('.//rendition')
# For now, always pick the highest quality.
rendition = renditions[-1]
try:
_,_,ext = rendition.attrib['type'].partition('/')
format = ext + '-' + rendition.attrib['width'] + 'x' + rendition.attrib['height'] + '_' + rendition.attrib['bitrate']
rtmp_video_url = rendition.find('./src').text
except KeyError:
raise ExtractorError('Invalid rendition field.')
video_url = self._transform_rtmp_url(rtmp_video_url)
return {'ext': ext, 'url': video_url, 'format': format}
formats = []
for rendition in mdoc.findall('.//rendition'):
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')),
})
except (KeyError, TypeError):
raise ExtractorError('Invalid rendition field.')
return formats
def _get_video_info(self, itemdoc):
uri = itemdoc.find('guid').text
@@ -81,19 +84,25 @@ class MTVIE(InfoExtractor):
mediagen_url += '&acceptMethods=fms'
mediagen_page = self._download_webpage(mediagen_url, video_id,
u'Downloading video urls')
video_info = self._extract_video_url(mediagen_page)
description_node = itemdoc.find('description')
if description_node is not None:
description = description_node.text
else:
description = None
video_info.update({'title': itemdoc.find('title').text,
'id': video_id,
'thumbnail': self._get_thumbnail_url(uri, itemdoc),
'description': description,
})
return video_info
info = {
'title': itemdoc.find('title').text,
'formats': self._extract_video_formats(mediagen_page),
'id': video_id,
'thumbnail': self._get_thumbnail_url(uri, itemdoc),
'description': description,
}
# TODO: Remove when #980 has been merged
info.update(info['formats'][-1])
return info
def _get_videos_info(self, uri):
video_id = self._id_from_uri(uri)

View File

@@ -38,6 +38,7 @@ class PornotubeIE(InfoExtractor):
VIDEO_UPLOADED_RE = r'<div class="video_added_by">Added (?P<date>[0-9\/]+) by'
upload_date = self._html_search_regex(VIDEO_UPLOADED_RE, webpage, u'upload date', fatal=False)
if upload_date: upload_date = unified_strdate(upload_date)
age_limit = self._rta_search(webpage)
info = {'id': video_id,
'url': video_url,
@@ -45,6 +46,7 @@ class PornotubeIE(InfoExtractor):
'upload_date': upload_date,
'title': video_title,
'ext': 'flv',
'format': 'flv'}
'format': 'flv',
'age_limit': age_limit}
return [info]

View File

@@ -14,24 +14,30 @@ class RedTubeIE(InfoExtractor):
}
}
def _real_extract(self,url):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
video_extension = 'mp4'
video_extension = 'mp4'
webpage = self._download_webpage(url, video_id)
self.report_extraction(video_id)
video_url = self._html_search_regex(r'<source src="(.+?)" type="video/mp4">',
webpage, u'video URL')
video_url = self._html_search_regex(
r'<source src="(.+?)" type="video/mp4">', webpage, u'video URL')
video_title = self._html_search_regex('<h1 class="videoTitle slidePanelMovable">(.+?)</h1>',
video_title = self._html_search_regex(
r'<h1 class="videoTitle slidePanelMovable">(.+?)</h1>',
webpage, u'title')
return [{
'id': video_id,
'url': video_url,
'ext': video_extension,
'title': video_title,
}]
# No self-labeling, but they describe themselves as
# "Home of Videos Porno"
age_limit = 18
return {
'id': video_id,
'url': video_url,
'ext': video_extension,
'title': video_title,
'age_limit': age_limit,
}

View File

@@ -8,8 +8,8 @@ from ..utils import (
)
class RTLnowIE(InfoExtractor):
"""Information Extractor for RTL NOW, RTL2 NOW, SUPER RTL NOW and VOX NOW"""
_VALID_URL = r'(?:http://)?(?P<url>(?P<base_url>rtl-now\.rtl\.de/|rtl2now\.rtl2\.de/|(?:www\.)?voxnow\.de/|(?:www\.)?superrtlnow\.de/)[a-zA-Z0-9-]+/[a-zA-Z0-9-]+\.php\?(?:container_id|film_id)=(?P<video_id>[0-9]+)&player=1(?:&season=[0-9]+)?(?:&.*)?)'
"""Information Extractor for RTL NOW, RTL2 NOW, RTL NITRO, SUPER RTL NOW, VOX NOW and n-tv NOW"""
_VALID_URL = r'(?:http://)?(?P<url>(?P<base_url>rtl-now\.rtl\.de/|rtl2now\.rtl2\.de/|(?:www\.)?voxnow\.de/|(?:www\.)?rtlnitronow\.de/|(?:www\.)?superrtlnow\.de/|(?:www\.)?n-tvnow\.de/)[a-zA-Z0-9-]+/[a-zA-Z0-9-]+\.php\?(?:container_id|film_id)=(?P<video_id>[0-9]+)&player=1(?:&season=[0-9]+)?(?:&.*)?)'
_TESTS = [{
u'url': u'http://rtl-now.rtl.de/ahornallee/folge-1.php?film_id=90419&player=1&season=1',
u'file': u'90419.flv',
@@ -61,8 +61,35 @@ class RTLnowIE(InfoExtractor):
u'params': {
u'skip_download': True,
},
},
{
u'url': u'http://www.rtlnitronow.de/recht-ordnung/lebensmittelkontrolle-erlangenordnungsamt-berlin.php?film_id=127367&player=1&season=1',
u'file': u'127367.flv',
u'info_dict': {
u'upload_date': u'20130926',
u'title': u'Recht & Ordnung - Lebensmittelkontrolle Erlangen/Ordnungsamt...',
u'description': u'Lebensmittelkontrolle Erlangen/Ordnungsamt Berlin',
u'thumbnail': u'http://autoimg.static-fra.de/nitronow/344787/1500x1500/image2.jpg',
},
u'params': {
u'skip_download': True,
},
},
{
u'url': u'http://www.n-tvnow.de/top-gear/episode-1-2013-01-01-00-00-00.php?film_id=124903&player=1&season=10',
u'file': u'124903.flv',
u'info_dict': {
u'upload_date': u'20130101',
u'title': u'Top Gear vom 01.01.2013',
u'description': u'Episode 1',
},
u'params': {
u'skip_download': True,
},
u'skip': u'Only works from Germany',
}]
def _real_extract(self,url):
mobj = re.match(self._VALID_URL, url)
@@ -79,20 +106,23 @@ class RTLnowIE(InfoExtractor):
msg = clean_html(note_m.group(1))
raise ExtractorError(msg)
video_title = self._html_search_regex(r'<title>(?P<title>[^<]+)</title>',
video_title = self._html_search_regex(r'<title>(?P<title>[^<]+?)( \| [^<]*)?</title>',
webpage, u'title')
playerdata_url = self._html_search_regex(r'\'playerdata\': \'(?P<playerdata_url>[^\']+)\'',
webpage, u'playerdata_url')
playerdata = self._download_webpage(playerdata_url, video_id)
mobj = re.search(r'<title><!\[CDATA\[(?P<description>.+?)\s+- (?:Sendung )?vom (?P<upload_date_d>[0-9]{2})\.(?P<upload_date_m>[0-9]{2})\.(?:(?P<upload_date_Y>[0-9]{4})|(?P<upload_date_y>[0-9]{2})) [0-9]{2}:[0-9]{2} Uhr\]\]></title>', playerdata)
mobj = re.search(r'<title><!\[CDATA\[(?P<description>.+?)(?:\s+- (?:Sendung )?vom (?P<upload_date_d>[0-9]{2})\.(?P<upload_date_m>[0-9]{2})\.(?:(?P<upload_date_Y>[0-9]{4})|(?P<upload_date_y>[0-9]{2})) [0-9]{2}:[0-9]{2} Uhr)?\]\]></title>', playerdata)
if mobj:
video_description = mobj.group(u'description')
if mobj.group('upload_date_Y'):
video_upload_date = mobj.group('upload_date_Y')
else:
elif mobj.group('upload_date_y'):
video_upload_date = u'20' + mobj.group('upload_date_y')
video_upload_date += mobj.group('upload_date_m')+mobj.group('upload_date_d')
else:
video_upload_date = None
if video_upload_date:
video_upload_date += mobj.group('upload_date_m')+mobj.group('upload_date_d')
else:
video_description = None
video_upload_date = None

View File

@@ -77,12 +77,20 @@ class TEDIE(InfoExtractor):
thumbnail = self._search_regex(r'</span>[\s.]*</div>[\s.]*<img src="(.*?)"',
webpage, 'thumbnail')
formats = [{
'ext': 'mp4',
'url': stream['file'],
'format': stream['id']
} for stream in info['htmlStreams']]
info = {
'id': info['id'],
'url': info['htmlStreams'][-1]['file'],
'ext': 'mp4',
'title': title,
'thumbnail': thumbnail,
'description': desc,
}
'id': info['id'],
'title': title,
'thumbnail': thumbnail,
'description': desc,
'formats': formats,
}
# TODO: Remove when #980 has been merged
info.update(info['formats'][-1])
return info

View File

@@ -1,11 +1,15 @@
import re
import json
import xml.etree.ElementTree
import datetime
from .common import InfoExtractor
from ..utils import (
determine_ext,
ExtractorError,
)
class VevoIE(InfoExtractor):
"""
Accepts urls from vevo.com or in the format 'vevo:{id}'
@@ -15,11 +19,11 @@ class VevoIE(InfoExtractor):
_TEST = {
u'url': u'http://www.vevo.com/watch/hurts/somebody-to-die-for/GB1101300280',
u'file': u'GB1101300280.mp4',
u'md5': u'06bea460acb744eab74a9d7dcb4bfd61',
u'info_dict': {
u"upload_date": u"20130624",
u"uploader": u"Hurts",
u"title": u"Somebody to Die For"
u"title": u"Somebody to Die For",
u'duration': 230,
}
}
@@ -27,27 +31,47 @@ class VevoIE(InfoExtractor):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
json_url = 'http://www.vevo.com/data/video/%s' % video_id
base_url = 'http://smil.lvl3.vevo.com'
videos_url = '%s/Video/V2/VFILE/%s/%sr.smil' % (base_url, video_id, video_id.lower())
json_url = 'http://videoplayer.vevo.com/VideoService/AuthenticateVideo?isrc=%s' % video_id
info_json = self._download_webpage(json_url, video_id, u'Downloading json info')
links_webpage = self._download_webpage(videos_url, video_id, u'Downloading videos urls')
self.report_extraction(video_id)
video_info = json.loads(info_json)
m_urls = list(re.finditer(r'<video src="(?P<ext>.*?):/?(?P<url>.*?)"', links_webpage))
if m_urls is None or len(m_urls) == 0:
raise ExtractorError(u'Unable to extract video url')
# They are sorted from worst to best quality
m_url = m_urls[-1]
video_url = base_url + '/' + m_url.group('url')
ext = m_url.group('ext')
video_info = json.loads(info_json)['video']
last_version = {'version': -1}
for version in video_info['videoVersions']:
# These are the HTTP downloads, other types are for different manifests
if version['sourceType'] == 2:
if version['version'] > last_version['version']:
last_version = version
if last_version['version'] == -1:
raise ExtractorError(u'Unable to extract last version of the video')
return {'url': video_url,
'ext': ext,
'id': video_id,
'title': video_info['title'],
'thumbnail': video_info['img'],
'upload_date': video_info['launchDate'].replace('/',''),
'uploader': video_info['Artists'][0]['title'],
}
renditions = xml.etree.ElementTree.fromstring(last_version['data'])
formats = []
# Already sorted from worst to best quality
for rend in renditions.findall('rendition'):
attr = rend.attrib
f_url = attr['url']
formats.append({
'url': f_url,
'ext': determine_ext(f_url),
'height': int(attr['frameheight']),
'width': int(attr['frameWidth']),
})
date_epoch = int(self._search_regex(
r'/Date\((\d+)\)/', video_info['launchDate'], u'launch date'))/1000
upload_date = datetime.datetime.fromtimestamp(date_epoch)
info = {
'id': video_id,
'title': video_info['title'],
'formats': formats,
'thumbnail': video_info['imageUrl'],
'upload_date': upload_date.strftime('%Y%m%d'),
'uploader': video_info['mainArtists'][0]['artistName'],
'duration': video_info['duration'],
}
# TODO: Remove when #980 has been merged
info.update(formats[-1])
return info

View File

@@ -0,0 +1,64 @@
import json
import re
from .common import InfoExtractor
from ..utils import (
determine_ext,
)
class ViddlerIE(InfoExtractor):
_VALID_URL = r'(?P<domain>https?://(?:www\.)?viddler.com)/(?:v|embed|player)/(?P<id>[0-9]+)'
_TEST = {
u"url": u"http://www.viddler.com/v/43903784",
u'file': u'43903784.mp4',
u'md5': u'fbbaedf7813e514eb7ca30410f439ac9',
u'info_dict': {
u"title": u"Video Made Easy",
u"uploader": u"viddler",
u"duration": 100.89,
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
embed_url = mobj.group('domain') + u'/embed/' + video_id
webpage = self._download_webpage(embed_url, video_id)
video_sources_code = self._search_regex(
r"(?ms)sources\s*:\s*(\{.*?\})", webpage, u'video URLs')
video_sources = json.loads(video_sources_code.replace("'", '"'))
formats = [{
'url': video_url,
'format': format_id,
} for video_url, format_id in video_sources.items()]
title = self._html_search_regex(
r"title\s*:\s*'([^']*)'", webpage, u'title')
uploader = self._html_search_regex(
r"authorName\s*:\s*'([^']*)'", webpage, u'uploader', fatal=False)
duration_s = self._html_search_regex(
r"duration\s*:\s*([0-9.]*)", webpage, u'duration', fatal=False)
duration = float(duration_s) if duration_s else None
thumbnail = self._html_search_regex(
r"thumbnail\s*:\s*'([^']*)'",
webpage, u'thumbnail', fatal=False)
info = {
'_type': 'video',
'id': video_id,
'title': title,
'thumbnail': thumbnail,
'uploader': uploader,
'duration': duration,
'formats': formats,
}
# TODO: Remove when #980 has been merged
info['formats'][-1]['ext'] = determine_ext(info['formats'][-1]['url'])
info.update(info['formats'][-1])
return info

View File

@@ -17,7 +17,7 @@ class VimeoIE(InfoExtractor):
"""Information extractor for vimeo.com."""
# _VALID_URL matches Vimeo URLs
_VALID_URL = r'(?P<proto>https?://)?(?:(?:www|player)\.)?vimeo(?P<pro>pro)?\.com/(?:(?:(?:groups|album)/[^/]+)|(?:.*?)/)?(?P<direct_link>play_redirect_hls\?clip_id=)?(?:videos?/)?(?P<id>[0-9]+)(?:[?].*)?$'
_VALID_URL = r'(?P<proto>https?://)?(?:(?:www|player)\.)?vimeo(?P<pro>pro)?\.com/(?:(?:(?:groups|album)/[^/]+)|(?:.*?)/)?(?P<direct_link>play_redirect_hls\?clip_id=)?(?:videos?/)?(?P<id>[0-9]+)/?(?:[?].*)?$'
_NETRC_MACHINE = 'vimeo'
IE_NAME = u'vimeo'
_TESTS = [

View File

@@ -1,4 +1,3 @@
import datetime
import itertools
import json
import re
@@ -6,86 +5,89 @@ import re
from .common import InfoExtractor, SearchInfoExtractor
from ..utils import (
compat_urllib_parse,
ExtractorError,
compat_urlparse,
determine_ext,
clean_html,
)
class YahooIE(InfoExtractor):
IE_DESC = u'Yahoo screen'
_VALID_URL = r'http://screen\.yahoo\.com/.*?-(?P<id>\d*?)\.html'
_TEST = {
u'url': u'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html',
u'file': u'214727115.flv',
u'md5': u'2e717f169c1be93d84d3794a00d4a325',
u'info_dict': {
u"title": u"Julian Smith & Travis Legg Watch Julian Smith"
_TESTS = [
{
u'url': u'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html',
u'file': u'214727115.flv',
u'info_dict': {
u'title': u'Julian Smith & Travis Legg Watch Julian Smith',
u'description': u'Julian and Travis watch Julian Smith',
},
u'params': {
# Requires rtmpdump
u'skip_download': True,
},
},
u'skip': u'Requires rtmpdump'
}
{
u'url': u'http://screen.yahoo.com/wired/codefellas-s1-ep12-cougar-lies-103000935.html',
u'file': u'103000935.flv',
u'info_dict': {
u'title': u'Codefellas - The Cougar Lies with Spanish Moss',
u'description': u'Agent Topple\'s mustache does its dirty work, and Nicole brokers a deal for peace. But why is the NSA collecting millions of Instagram brunch photos? And if your waffles have nothing to hide, what are they so worried about?',
},
u'params': {
# Requires rtmpdump
u'skip_download': True,
},
},
]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
m_id = re.search(r'YUI\.namespace\("Media"\)\.CONTENT_ID = "(?P<new_id>.+?)";', webpage)
if m_id is None:
# TODO: Check which url parameters are required
info_url = 'http://cosmos.bcst.yahoo.com/rest/v2/pops;lmsoverride=1;outputformat=mrss;cb=974419660;id=%s;rd=news.yahoo.com;datacontext=mdb;lg=KCa2IihxG3qE60vQ7HtyUy' % video_id
webpage = self._download_webpage(info_url, video_id, u'Downloading info webpage')
info_re = r'''<title><!\[CDATA\[(?P<title>.*?)\]\]></title>.*
<description><!\[CDATA\[(?P<description>.*?)\]\]></description>.*
<media:pubStart><!\[CDATA\[(?P<date>.*?)\ .*\]\]></media:pubStart>.*
<media:content\ medium="image"\ url="(?P<thumb>.*?)"\ name="LARGETHUMB"
'''
self.report_extraction(video_id)
m_info = re.search(info_re, webpage, re.VERBOSE|re.DOTALL)
if m_info is None:
raise ExtractorError(u'Unable to extract video info')
video_title = m_info.group('title')
video_description = m_info.group('description')
video_thumb = m_info.group('thumb')
video_date = m_info.group('date')
video_date = datetime.datetime.strptime(video_date, '%m/%d/%Y').strftime('%Y%m%d')
# TODO: Find a way to get mp4 videos
rest_url = 'http://cosmos.bcst.yahoo.com/rest/v2/pops;element=stream;outputformat=mrss;id=%s;lmsoverride=1;bw=375;dynamicstream=1;cb=83521105;tech=flv,mp4;rd=news.yahoo.com;datacontext=mdb;lg=KCa2IihxG3qE60vQ7HtyUy' % video_id
webpage = self._download_webpage(rest_url, video_id, u'Downloading video url webpage')
m_rest = re.search(r'<media:content url="(?P<url>.*?)" path="(?P<path>.*?)"', webpage)
video_url = m_rest.group('url')
video_path = m_rest.group('path')
if m_rest is None:
raise ExtractorError(u'Unable to extract video url')
items_json = self._search_regex(r'YVIDEO_INIT_ITEMS = ({.*?});$',
webpage, u'items', flags=re.MULTILINE)
items = json.loads(items_json)
info = items['mediaItems']['query']['results']['mediaObj'][0]
meta = info['meta']
else: # We have to use a different method if another id is defined
long_id = m_id.group('new_id')
info_url = 'http://video.query.yahoo.com/v1/public/yql?q=SELECT%20*%20FROM%20yahoo.media.video.streams%20WHERE%20id%3D%22' + long_id + '%22%20AND%20format%3D%22mp4%2Cflv%22%20AND%20protocol%3D%22rtmp%2Chttp%22%20AND%20plrs%3D%2286Gj0vCaSzV_Iuf6hNylf2%22%20AND%20acctid%3D%22389%22%20AND%20plidl%3D%22%22%20AND%20pspid%3D%22792700001%22%20AND%20offnetwork%3D%22false%22%20AND%20site%3D%22ivy%22%20AND%20lang%3D%22en-US%22%20AND%20region%3D%22US%22%20AND%20override%3D%22none%22%3B&env=prod&format=json&callback=YUI.Env.JSONP.yui_3_8_1_1_1368368376830_335'
webpage = self._download_webpage(info_url, video_id, u'Downloading info json')
json_str = re.search(r'YUI.Env.JSONP.yui.*?\((.*?)\);', webpage).group(1)
info = json.loads(json_str)
res = info[u'query'][u'results'][u'mediaObj'][0]
stream = res[u'streams'][0]
video_path = stream[u'path']
video_url = stream[u'host']
meta = res[u'meta']
video_title = meta[u'title']
video_description = meta[u'description']
video_thumb = meta[u'thumbnail']
video_date = None # I can't find it
formats = []
for s in info['streams']:
format_info = {
'width': s.get('width'),
'height': s.get('height'),
'bitrate': s.get('bitrate'),
}
host = s['host']
path = s['path']
if host.startswith('rtmp'):
format_info.update({
'url': host,
'play_path': path,
'ext': 'flv',
})
else:
format_url = compat_urlparse.urljoin(host, path)
format_info['url'] = format_url
format_info['ext'] = determine_ext(format_url)
formats.append(format_info)
formats = sorted(formats, key=lambda f:(f['height'], f['width']))
info = {
'id': video_id,
'title': meta['title'],
'formats': formats,
'description': clean_html(meta['description']),
'thumbnail': meta['thumbnail'],
}
# TODO: Remove when #980 has been merged
info.update(formats[-1])
return info
info_dict = {
'id': video_id,
'url': video_url,
'play_path': video_path,
'title':video_title,
'description': video_description,
'thumbnail': video_thumb,
'upload_date': video_date,
'ext': 'flv',
}
return info_dict
class YahooSearchIE(SearchInfoExtractor):
IE_DESC = u'Yahoo screen search'

View File

@@ -51,6 +51,7 @@ class YouPornIE(InfoExtractor):
req = compat_urllib_request.Request(url)
req.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(req, video_id)
age_limit = self._rta_search(webpage)
# Get JSON parameters
json_params = self._search_regex(r'var currentVideo = new Video\((.*)\);', webpage, u'JSON parameters')
@@ -115,7 +116,8 @@ class YouPornIE(InfoExtractor):
'ext': extension,
'format': format,
'thumbnail': thumbnail,
'description': video_description
'description': video_description,
'age_limit': age_limit,
})
if self._downloader.params.get('listformats', None):

View File

@@ -23,9 +23,11 @@ from ..utils import (
compat_urllib_error,
compat_urllib_parse,
compat_urllib_request,
compat_urlparse,
compat_str,
clean_html,
get_cachedir,
get_element_by_id,
ExtractorError,
unescapeHTML,
@@ -361,7 +363,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
u"info_dict": {
u"upload_date": u"20120506",
u"title": u"Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]",
u"description": u"md5:bdac09887d209a4ed54b8f76b2bdaa8b",
u"description": u"md5:5b292926389560516e384ac437c0ec07",
u"uploader": u"Icona Pop",
u"uploader_id": u"IconaPop"
}
@@ -378,21 +380,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
u"uploader_id": u"justintimberlakeVEVO"
}
},
{
u'url': u'https://www.youtube.com/watch?v=TGi3HqYrWHE',
u'file': u'TGi3HqYrWHE.mp4',
u'note': u'm3u8 video',
u'info_dict': {
u'title': u'Triathlon - Men - London 2012 Olympic Games',
u'description': u'- Men - TR02 - Triathlon - 07 August 2012 - London 2012 Olympic Games',
u'uploader': u'olympic',
u'upload_date': u'20120807',
u'uploader_id': u'olympic',
},
u'params': {
u'skip_download': True,
},
},
]
@@ -435,8 +422,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
# Read from filesystem cache
func_id = '%s_%s_%d' % (player_type, player_id, slen)
assert os.path.basename(func_id) == func_id
cache_dir = self._downloader.params.get('cachedir',
u'~/.youtube-dl/cache')
cache_dir = get_cachedir(self._downloader.params)
cache_enabled = cache_dir is not None
if cache_enabled:
@@ -1051,12 +1037,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
if player_url is not None:
try:
if player_url not in self._player_cache:
player_id = (player_url, len(s))
if player_id not in self._player_cache:
func = self._extract_signature_function(
video_id, player_url, len(s)
)
self._player_cache[player_url] = func
func = self._player_cache[player_url]
self._player_cache[player_id] = func
func = self._player_cache[player_id]
if self._downloader.params.get('youtube_print_sig_code'):
self._print_sig_code(func, len(s))
return func(s)
@@ -1067,6 +1054,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
self._downloader.report_warning(
u'Warning: Falling back to static signature algorithm')
return self._static_decrypt_signature(
s, video_id, player_url, age_gate)
@@ -1098,9 +1086,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
elif len(s) == 84:
return s[78:70:-1] + s[14] + s[69:37:-1] + s[70] + s[36:14:-1] + s[80] + s[:14][::-1]
elif len(s) == 83:
return s[81:64:-1] + s[82] + s[63:52:-1] + s[45] + s[51:45:-1] + s[1] + s[44:1:-1] + s[0]
return s[80:63:-1] + s[0] + s[62:0:-1] + s[63]
elif len(s) == 82:
return s[80:73:-1] + s[81] + s[72:54:-1] + s[2] + s[53:43:-1] + s[0] + s[42:2:-1] + s[43] + s[1] + s[54]
return s[80:37:-1] + s[7] + s[36:7:-1] + s[0] + s[6:0:-1] + s[37]
elif len(s) == 81:
return s[56] + s[79:56:-1] + s[41] + s[55:41:-1] + s[80] + s[40:34:-1] + s[0] + s[33:29:-1] + s[34] + s[28:9:-1] + s[29] + s[8:0:-1] + s[9]
elif len(s) == 80:
@@ -1128,6 +1116,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
'lang': lang,
'v': video_id,
'fmt': self._downloader.params.get('subtitlesformat'),
'name': l[0],
})
url = u'http://www.youtube.com/api/timedtext?' + params
sub_lang_list[lang] = url
@@ -1262,9 +1251,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
return url_map
def _real_extract(self, url):
if re.match(r'(?:https?://)?[^/]+/watch\?feature=[a-z_]+$', url):
self._downloader.report_warning(u'Did you forget to quote the URL? Remember that & is a meta-character in most shells, so you want to put the URL in quotes, like youtube-dl \'http://www.youtube.com/watch?feature=foo&v=BaW_jenozKc\' (or simply youtube-dl BaW_jenozKc ).')
# Extract original video URL from URL with redirection, like age verification, using next_url parameter
mobj = re.search(self._NEXT_URL_RE, url)
if mobj:
@@ -1347,9 +1333,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
self._downloader.report_warning(u'unable to extract uploader nickname')
# title
if 'title' not in video_info:
raise ExtractorError(u'Unable to extract video title')
video_title = compat_urllib_parse.unquote_plus(video_info['title'][0])
if 'title' in video_info:
video_title = compat_urllib_parse.unquote_plus(video_info['title'][0])
else:
self._downloader.report_warning(u'Unable to extract video title')
video_title = u'_'
# thumbnail image
# We try first to get a high quality image:
@@ -1359,7 +1347,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
video_thumbnail = m_thumb.group(1)
elif 'thumbnail_url' not in video_info:
self._downloader.report_warning(u'unable to extract video thumbnail')
video_thumbnail = ''
video_thumbnail = None
else: # don't panic if we can't find it
video_thumbnail = compat_urllib_parse.unquote_plus(video_info['thumbnail_url'][0])
@@ -1404,6 +1392,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
args = info['args']
# Easy way to know if the 's' value is in url_encoded_fmt_stream_map
# this signatures are encrypted
if 'url_encoded_fmt_stream_map' not in args:
raise ValueError(u'No stream_map present') # caught below
m_s = re.search(r'[&,]s=', args['url_encoded_fmt_stream_map'])
if m_s is not None:
self.to_screen(u'%s: Encrypted signatures detected.' % video_id)
@@ -1479,7 +1469,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
return
else:
raise ExtractorError(u'no conn or url_encoded_fmt_stream_map information found in video info')
raise ExtractorError(u'no conn, hlsvp or url_encoded_fmt_stream_map information found in video info')
results = []
for format_param, video_real_url in video_url_list:
@@ -1503,7 +1493,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
'description': video_description,
'player_url': player_url,
'subtitles': video_subtitles,
'duration': video_duration
'duration': video_duration,
'age_limit': 18 if age_gate else 0,
})
return results
@@ -1537,9 +1528,19 @@ class YoutubePlaylistIE(InfoExtractor):
mobj = re.match(self._VALID_URL, url, re.VERBOSE)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
playlist_id = mobj.group(1) or mobj.group(2)
# Check if it's a video-specific URL
query_dict = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
if 'v' in query_dict:
video_id = query_dict['v'][0]
if self._downloader.params.get('noplaylist'):
self.to_screen(u'Downloading just video %s because of --no-playlist' % video_id)
return self.url_result('https://www.youtube.com/watch?v=' + video_id, 'Youtube')
else:
self.to_screen(u'Downloading playlist PL%s - add --no-playlist to just download video %s' % (playlist_id, video_id))
# Download playlist videos from API
playlist_id = mobj.group(1) or mobj.group(2)
videos = []
for page_num in itertools.count(1):
@@ -1634,7 +1635,7 @@ class YoutubeChannelIE(InfoExtractor):
class YoutubeUserIE(InfoExtractor):
IE_DESC = u'YouTube.com user videos (URL or "ytuser" keyword)'
_VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/(?:user/)?)|ytuser:)(?!feed/)([A-Za-z0-9_-]+)'
_VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/(?:user/)?(?!(?:attribution_link|watch)(?:$|[^a-z_A-Z0-9-])))|ytuser:)(?!feed/)([A-Za-z0-9_-]+)'
_TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s'
_GDATA_PAGE_SIZE = 50
_GDATA_URL = 'http://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d&alt=json'
@@ -1827,3 +1828,18 @@ class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
webpage = self._download_webpage('https://www.youtube.com/my_favorites', 'Youtube Favourites videos')
playlist_id = self._search_regex(r'list=(.+?)["&]', webpage, u'favourites playlist id')
return self.url_result(playlist_id, 'YoutubePlaylist')
class YoutubeTruncatedURLIE(InfoExtractor):
IE_NAME = 'youtube:truncated_url'
IE_DESC = False # Do not list
_VALID_URL = r'(?:https?://)?[^/]+/watch\?feature=[a-z_]+$'
def _real_extract(self, url):
raise ExtractorError(
u'Did you forget to quote the URL? Remember that & is a meta '
u'character in most shells, so you want to put the URL in quotes, '
u'like youtube-dl '
u'\'http://www.youtube.com/watch?feature=foo&v=BaW_jenozKc\''
u' (or simply youtube-dl BaW_jenozKc ).',
expected=True)

View File

@@ -2,16 +2,14 @@ import re
from .common import InfoExtractor
from ..utils import (
determine_ext,
ExtractorError,
unescapeHTML,
)
class ZDFIE(InfoExtractor):
_VALID_URL = r'^http://www\.zdf\.de\/ZDFmediathek\/(.*beitrag\/video\/)(?P<video_id>[^/\?]+)(?:\?.*)?'
_TITLE = r'<h1(?: class="beitragHeadline")?>(?P<title>.*)</h1>'
_VALID_URL = r'^http://www\.zdf\.de\/ZDFmediathek(?P<hash>#)?\/(.*beitrag\/video\/)(?P<video_id>[^/\?]+)(?:\?.*)?'
_MEDIA_STREAM = r'<a href="(?P<video_url>.+(?P<media_type>.streaming).+/zdf/(?P<quality>[^\/]+)/[^"]*)".+class="play".+>'
_MMS_STREAM = r'href="(?P<video_url>mms://[^"]*)"'
_RTSP_STREAM = r'(?P<video_url>rtsp://[^"]*.mp4)'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
@@ -19,6 +17,9 @@ class ZDFIE(InfoExtractor):
raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group('video_id')
if mobj.group('hash'):
url = url.replace(u'#', u'', 1)
html = self._download_webpage(url, video_id)
streams = [m.groupdict() for m in re.finditer(self._MEDIA_STREAM, html)]
if streams is None:
@@ -27,39 +28,48 @@ class ZDFIE(InfoExtractor):
# s['media_type'] == 'wstreaming' -> use 'Windows Media Player' and mms url
# s['media_type'] == 'hstreaming' -> use 'Quicktime' and rtsp url
# choose first/default media type and highest quality for now
for s in streams: #find 300 - dsl1000mbit
if s['quality'] == '300' and s['media_type'] == 'wstreaming':
stream_=s
break
for s in streams: #find veryhigh - dsl2000mbit
if s['quality'] == 'veryhigh' and s['media_type'] == 'wstreaming': # 'hstreaming' - rtsp is not working
stream_=s
break
if stream_ is None:
def stream_pref(s):
TYPE_ORDER = ['ostreaming', 'hstreaming', 'wstreaming']
try:
type_pref = TYPE_ORDER.index(s['media_type'])
except ValueError:
type_pref = 999
QUALITY_ORDER = ['veryhigh', '300']
try:
quality_pref = QUALITY_ORDER.index(s['quality'])
except ValueError:
quality_pref = 999
return (type_pref, quality_pref)
sorted_streams = sorted(streams, key=stream_pref)
if not sorted_streams:
raise ExtractorError(u'No stream found.')
stream = sorted_streams[0]
media_link = self._download_webpage(stream_['video_url'], video_id,'Get stream URL')
media_link = self._download_webpage(
stream['video_url'],
video_id,
u'Get stream URL')
self.report_extraction(video_id)
mobj = re.search(self._TITLE, html)
MMS_STREAM = r'href="(?P<video_url>mms://[^"]*)"'
RTSP_STREAM = r'(?P<video_url>rtsp://[^"]*.mp4)'
mobj = re.search(self._MEDIA_STREAM, media_link)
if mobj is None:
raise ExtractorError(u'Cannot extract title')
title = unescapeHTML(mobj.group('title'))
mobj = re.search(self._MMS_STREAM, media_link)
if mobj is None:
mobj = re.search(self._RTSP_STREAM, media_link)
mobj = re.search(RTSP_STREAM, media_link)
if mobj is None:
raise ExtractorError(u'Cannot extract mms:// or rtsp:// URL')
mms_url = mobj.group('video_url')
video_url = mobj.group('video_url')
mobj = re.search('(.*)[.](?P<ext>[^.]+)', mms_url)
if mobj is None:
raise ExtractorError(u'Cannot extract extention')
ext = mobj.group('ext')
title = self._html_search_regex(
r'<h1(?: class="beitragHeadline")?>(.*?)</h1>',
html, u'title')
return [{'id': video_id,
'url': mms_url,
'title': title,
'ext': ext
}]
return {
'id': video_id,
'url': video_url,
'title': title,
'ext': determine_ext(video_url)
}

View File

@@ -1,6 +1,9 @@
import io
import json
import traceback
import hashlib
import subprocess
import sys
from zipimport import zipimporter
from .utils import *
@@ -34,7 +37,7 @@ def rsa_verify(message, signature, key):
if signature != sha256(message).digest(): return False
return True
def update_self(to_screen, verbose, filename):
def update_self(to_screen, verbose):
"""Update the program file with the latest version from the repository"""
UPDATE_URL = "http://rg3.github.io/youtube-dl/update/"
@@ -42,7 +45,6 @@ def update_self(to_screen, verbose, filename):
JSON_URL = UPDATE_URL + 'versions.json'
UPDATES_RSA_KEY = (0x9d60ee4d8f805312fdb15a62f87b95bd66177b91df176765d13514a0f1754bcd2057295c5b6f1d35daa6742c3ffc9a82d3e118861c207995a8031e151d863c9927e304576bc80692bc8e094896fcf11b66f3e29e04e3a71e9a11558558acea1840aec37fc396fb6b65dc81a1c4144e03bd1c011de62e3f1357b327d08426fe93, 65537)
if not isinstance(globals().get('__loader__'), zipimporter) and not hasattr(sys, "frozen"):
to_screen(u'It looks like you installed youtube-dl with a package manager, pip, setup.py or a tarball. Please use that to update.')
return
@@ -75,11 +77,18 @@ def update_self(to_screen, verbose, filename):
to_screen(u'ERROR: the versions file signature is invalid. Aborting.')
return
to_screen(u'Updating to version ' + versions_info['latest'] + '...')
version = versions_info['versions'][versions_info['latest']]
version_id = versions_info['latest']
to_screen(u'Updating to version ' + version_id + '...')
version = versions_info['versions'][version_id]
print_notes(to_screen, versions_info['versions'])
filename = sys.argv[0]
# Py2EXE: Filename could be different
if hasattr(sys, "frozen") and not os.path.isfile(filename):
if os.path.isfile(filename + u'.exe'):
filename += u'.exe'
if not os.access(filename, os.W_OK):
to_screen(u'ERROR: no write permissions on %s' % filename)
return
@@ -116,16 +125,18 @@ def update_self(to_screen, verbose, filename):
try:
bat = os.path.join(directory, 'youtube-dl-updater.bat')
b = open(bat, 'w')
b.write("""
echo Updating youtube-dl...
with io.open(bat, 'w') as batfile:
batfile.write(u"""
@echo off
echo Waiting for file handle to be closed ...
ping 127.0.0.1 -n 5 -w 1000 > NUL
move /Y "%s.new" "%s"
del "%s"
\n""" %(exe, exe, bat))
b.close()
move /Y "%s.new" "%s" > NUL
echo Updated youtube-dl to version %s.
start /b "" cmd /c del "%%~f0"&exit /b"
\n""" % (exe, exe, version_id))
os.startfile(bat)
subprocess.Popen([bat]) # Continues to run in the background
return # Do not show premature success messages
except (IOError, OSError) as err:
if verbose: to_screen(compat_str(traceback.format_exc()))
to_screen(u'ERROR: unable to overwrite current version')

View File

@@ -175,7 +175,7 @@ def compat_ord(c):
compiled_regex_type = type(re.compile(''))
std_headers = {
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20100101 Firefox/10.0',
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20100101 Firefox/10.0 (Chrome)',
'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
'Accept-Encoding': 'gzip, deflate',
@@ -824,3 +824,105 @@ def intlist_to_bytes(xs):
return ''.join([chr(x) for x in xs])
else:
return bytes(xs)
def get_cachedir(params={}):
cache_root = os.environ.get('XDG_CACHE_HOME',
os.path.expanduser('~/.cache'))
return params.get('cachedir', os.path.join(cache_root, 'youtube-dl'))
# Cross-platform file locking
if sys.platform == 'win32':
import ctypes.wintypes
import msvcrt
class OVERLAPPED(ctypes.Structure):
_fields_ = [
('Internal', ctypes.wintypes.LPVOID),
('InternalHigh', ctypes.wintypes.LPVOID),
('Offset', ctypes.wintypes.DWORD),
('OffsetHigh', ctypes.wintypes.DWORD),
('hEvent', ctypes.wintypes.HANDLE),
]
kernel32 = ctypes.windll.kernel32
LockFileEx = kernel32.LockFileEx
LockFileEx.argtypes = [
ctypes.wintypes.HANDLE, # hFile
ctypes.wintypes.DWORD, # dwFlags
ctypes.wintypes.DWORD, # dwReserved
ctypes.wintypes.DWORD, # nNumberOfBytesToLockLow
ctypes.wintypes.DWORD, # nNumberOfBytesToLockHigh
ctypes.POINTER(OVERLAPPED) # Overlapped
]
LockFileEx.restype = ctypes.wintypes.BOOL
UnlockFileEx = kernel32.UnlockFileEx
UnlockFileEx.argtypes = [
ctypes.wintypes.HANDLE, # hFile
ctypes.wintypes.DWORD, # dwReserved
ctypes.wintypes.DWORD, # nNumberOfBytesToLockLow
ctypes.wintypes.DWORD, # nNumberOfBytesToLockHigh
ctypes.POINTER(OVERLAPPED) # Overlapped
]
UnlockFileEx.restype = ctypes.wintypes.BOOL
whole_low = 0xffffffff
whole_high = 0x7fffffff
def _lock_file(f, exclusive):
overlapped = OVERLAPPED()
overlapped.Offset = 0
overlapped.OffsetHigh = 0
overlapped.hEvent = 0
f._lock_file_overlapped_p = ctypes.pointer(overlapped)
handle = msvcrt.get_osfhandle(f.fileno())
if not LockFileEx(handle, 0x2 if exclusive else 0x0, 0,
whole_low, whole_high, f._lock_file_overlapped_p):
raise OSError('Locking file failed: %r' % ctypes.FormatError())
def _unlock_file(f):
assert f._lock_file_overlapped_p
handle = msvcrt.get_osfhandle(f.fileno())
if not UnlockFileEx(handle, 0,
whole_low, whole_high, f._lock_file_overlapped_p):
raise OSError('Unlocking file failed: %r' % ctypes.FormatError())
else:
import fcntl
def _lock_file(f, exclusive):
fcntl.lockf(f, fcntl.LOCK_EX if exclusive else fcntl.LOCK_SH)
def _unlock_file(f):
fcntl.lockf(f, fcntl.LOCK_UN)
class locked_file(object):
def __init__(self, filename, mode, encoding=None):
assert mode in ['r', 'a', 'w']
self.f = io.open(filename, mode, encoding=encoding)
self.mode = mode
def __enter__(self):
exclusive = self.mode != 'r'
try:
_lock_file(self.f, exclusive)
except IOError:
self.f.close()
raise
return self
def __exit__(self, etype, value, traceback):
try:
_unlock_file(self.f)
finally:
self.f.close()
def __iter__(self):
return iter(self.f)
def write(self, *args):
return self.f.write(*args)
def read(self, *args):
return self.f.read(*args)

View File

@@ -1,2 +1,2 @@
__version__ = '2013.09.24.2'
__version__ = '2013.10.09'