Compare commits

...

75 Commits

Author SHA1 Message Date
Sergey M․
7dacceae75 release 2017.09.11 2017-09-11 03:30:33 +07:00
Sergey M․
43df248f10 [ChangeLog] Actualize 2017-09-11 03:27:43 +07:00
Sergey M․
f12a6e88b2 [rutube:playlist] Fix suitable (closes #14166) 2017-09-11 03:23:00 +07:00
Sergey M․
806498cf2f release 2017.09.10 2017-09-10 22:16:55 +07:00
Sergey M․
b98339b54b [ChangeLog] Actualize 2017-09-10 22:15:55 +07:00
Sergey M․
bf6ec2fea9 [fox] Fix extraction (#14147) 2017-09-10 22:08:32 +07:00
Sergey M․
c3dd44e085 [rutube] Use bool_or_none 2017-09-10 19:09:27 +07:00
Sergey M․
c7e327c4d4 [utils] Introduce bool_or_none 2017-09-10 19:08:39 +07:00
Sergey M․
48b813748d [rutube] Rework and generalize playlist extractors (closes #13565) 2017-09-10 18:40:33 +07:00
luceatnobis
debed8d759 [rutube:playlist] Add extractor (closes #13534) 2017-09-10 18:40:33 +07:00
kayb94
51aee72d16 [README.md] Clarify how to run extractor specific test cases 2017-09-08 22:13:17 +07:00
Olivier Bilodeau
931edb2ada [radiocanada] Add fallback for title extraction 2017-09-08 21:53:24 +07:00
Sergey M․
5113b69124 [abcnews,chilloutsoze,cracked,vice,vk] Use dedicated YouTube embeds extraction routines 2017-09-06 00:50:25 +07:00
Sergey M․
66c9fa36c1 [youtube] Separate methods for embeds extraction 2017-09-06 00:48:37 +07:00
Sergey M․
c5c9bf0c12 [YoutubeDL] Ensure dir existence for each requested format (closes #14116) 2017-09-05 23:31:34 +07:00
Sergey M․
880fa66f4f [redtube] Fix formats extraction (closes #14122) 2017-09-05 22:45:49 +07:00
Sergey M․
6348671c4a [arte] Relax unavailability check (closes #14112) 2017-09-04 23:08:40 +07:00
Sergey M․
efc57145c1 [manyvids] Improve (closes #14059) 2017-09-03 17:32:23 +07:00
John D
e9b865267a [manyvids] Add support for preview videos (closes #14053) 2017-09-03 17:31:53 +07:00
Sergey M․
bc35f07537 [vidme:user] Make tests only matching (closes #14054) 2017-09-03 17:03:51 +07:00
theychx
0b4a8eb3ac [vidme:user] Relax _VALID_URLs 2017-09-03 17:03:45 +07:00
Sergey M․
c1c1585b31 [bpb] Improve (closes #14086) 2017-09-03 16:43:33 +07:00
Timendum
0cbb841ba9 [bpb] Fix extraction (closes #14043) 2017-09-03 16:39:12 +07:00
Sergey M
d7c7100e3d [soundcloud] Simplify and add test (closes #14093) 2017-09-03 16:29:58 +07:00
Tatsuyuki Ishi
73602bcd0c [soundcloud] Fix download URL with private tracks 2017-09-03 16:28:34 +07:00
Sergey M․
23b2df82c7 [aliexpress:live] Fix issues (closes #13698, closes #13707) 2017-09-03 16:05:31 +07:00
dubber0
503115540d [aliexpress:live] Add extractor 2017-09-03 16:05:00 +07:00
Sergey M․
64f0e30b93 [viidea] Capture and output lecture error message (#14099) 2017-09-02 15:44:49 +07:00
Sergey M․
a3431e1224 [radiocanada] Skip unsupported platforms (closes #14100) 2017-09-02 15:33:54 +07:00
Sergey M․
a2022b0c40 release 2017.09.02 2017-09-02 01:08:32 +07:00
Sergey M․
8681ed7fc8 [ChangeLog] Actualize 2017-09-02 01:04:22 +07:00
Sergey M․
8d81f3e36d [youtube] Force old layout for each webpage (closes #14083) 2017-09-02 00:58:19 +07:00
Sergey M․
7998520933 [youtube] Fix upload date extraction (closes #14065) 2017-08-31 00:47:58 +07:00
Sergey M․
5b4bfbfc3b [charlierose] Add support for episodes (closes #14062) 2017-08-30 23:50:33 +07:00
Sergey M․
53647dfd0a [bbccouk] Add support for w-prefixed ids (closes #14056) 2017-08-30 05:27:56 +07:00
Yen Chi Hsuan
22f65a9efc Merge pull request #14048 from ryandesign/patch-1
Fix build failures with old cp and zip
2017-08-28 11:22:27 +08:00
Ryan Schmidt
c75c384fb6 Fix build failures with old cp and zip 2017-08-27 18:07:09 -05:00
Sergey M․
1b41da488d [googledrive] Extend _VALID_URL (closes #9785) 2017-08-28 00:50:41 +07:00
Sergey M․
fea82c1780 [googledrive] Add support for source format (closes #14046) 2017-08-28 00:39:22 +07:00
Sergey M․
3902cdd0e3 [pornhd] Fix extraction (closes #14005) 2017-08-27 22:37:26 +07:00
Sergey M․
2cfa7cbdd0 release 2017.08.27.1 2017-08-27 06:09:29 +07:00
Sergey M․
cc0412ef91 [ChangeLog] Actualize 2017-08-27 06:06:49 +07:00
Sergey M․
1c9c8de29e [youtube] Fix extraction with --youtube-skip-dash-manifest enabled (closes #14037) 2017-08-27 06:06:39 +07:00
Sergey M․
f031b76065 release 2017.08.27 2017-08-27 04:28:04 +07:00
Sergey M․
62c06c593d [ChangeLog] Actualize 2017-08-27 04:27:19 +07:00
Sergey M․
ff17be3ac9 [extractor/generic] Extract from LD-JSON last of all
Previous sources may contain several formats, e.g. http://tamasha.com/v/PgGZ
2017-08-27 03:31:40 +07:00
Sergey M․
1ed4549942 [extractor/common] Extract format id from label attribute of source tag for HTML5 videos (#14034) 2017-08-27 03:27:05 +07:00
Sergey M․
dd121cc1ca [extractor/common] Extract height from res attribute of source tag for HTML5 videos (closes #14034) 2017-08-27 03:12:56 +07:00
Sergey M․
a3c3a1e128 [http] Rework HTTP downloader
* Simplify code and split into separate routines to facilitate maintaining
* Make retry mechanism work on errors during actual download not only during connection establishment phase
* Retry on ECONNRESET and ETIMEDOUT during reading data from network
* Retry on content too short and various timeout errors
* Show error description on retry
* Closes #506, closes #809, closes #2849, closes #4240, closes #6023, closes #8625, closes #9483
2017-08-27 02:22:30 +07:00
Sergey M․
085d9dd9be [rai] Fix audio formats extraction (closes #14024) 2017-08-26 22:02:49 +07:00
Vijay Singh
151978f38a [mixcloud] Fix extraction (closes #14020) 2017-08-26 19:32:57 +07:00
Sergey M․
c7121fa7b8 [youtube] Fix controversy videos extraction (closes #14027, closes #14029) 2017-08-26 15:38:38 +07:00
Vijay Singh
745968bc72 [mixcloud] Fix extraction (closes #14015) 2017-08-24 22:28:44 +07:00
Sergey M․
df235dbba8 release 2017.08.23 2017-08-23 23:23:13 +07:00
Sergey M․
c4bdc68113 [ChangeLog] Actualize 2017-08-23 23:21:19 +07:00
Sergey M․
5bae33485c [toutv] PEP 8 2017-08-23 22:50:00 +07:00
Sergey M․
0830f3e048 [cbc:watch] Bypass geo-restriction (closes #13993) 2017-08-23 22:45:45 +07:00
Sergey M․
8d7a24aff6 [toutv] Relax DRM check (closes #13994) 2017-08-23 22:28:09 +07:00
Sergey M․
37d9af306a [googledrive] Simplify and carry long lines (#13638) 2017-08-23 00:33:53 +07:00
Sergey M․
e01c3d2ef7 [extractor/common] Introduce _parse_xml 2017-08-23 00:32:41 +07:00
Parmjit Virk
05915e379a [googledrive] Add support for subtitles (fixes #13619) 2017-08-22 23:48:59 +07:00
Yen Chi Hsuan
7b67b60773 Merge pull request #13669 from bmwiedemann/master
[build] Override timestamps in zip file
2017-08-22 21:51:20 +08:00
Sergey M․
8d9c2a681a [pornhub] Relax uploader regex (closes #13906, closes #13975) 2017-08-21 23:06:27 +07:00
Alan Yee
903d4d1625 [README.md] Switch to HTTPS URLs 2017-08-20 23:35:39 +07:00
Luca Steeb
8239c6791a [bandcamp:album] Extract track titles 2017-08-20 23:32:33 +07:00
Sergey M․
b359e977b9 [extractor/common] Make HLS and DASH extraction non fatal in _parse_html5_media_entries (closes #13970) 2017-08-20 14:16:58 +07:00
Bernhard M. Wiedemann
305d99f0bd [build] Override timestamps in zip file
to make build reproducible.
See https://reproducible-builds.org/ for why this is good

Copying files to not interfere with freshness detection.
2017-08-19 21:43:48 +02:00
Sergey M․
d3d45e0a45 [bbccouk] Add support for events URLs (closes #13893) 2017-08-19 23:54:15 +07:00
Yen Chi Hsuan
381ad4f309 [liveleak] Support multi-video pages (closes #6542) 2017-08-19 22:48:00 +08:00
Yen Chi Hsuan
e2481b9b6e [ChangeLog] Fix 2017-08-19 22:28:58 +08:00
Yen Chi Hsuan
09747ba766 [liveleak] Support another liveleak embedding pattern (closes #13336) 2017-08-19 22:28:13 +08:00
Yen Chi Hsuan
f8f18f332f [cda] Fix extraction (closes #13935) 2017-08-19 21:44:47 +08:00
Yen Chi Hsuan
95f3f7c20a [utils] Fix unescapeHTML for misformed string like "&a"" (#13935) 2017-08-19 21:40:53 +08:00
Sergey M․
f5469da9e6 [laola1tv] Add support for tv.ittf.com (closes #13965) 2017-08-19 19:48:20 +07:00
Sergey M․
d14d9d8903 [mixcloud] Fix extraction (closes #13958) 2017-08-18 23:31:42 +07:00
45 changed files with 1289 additions and 489 deletions

View File

@@ -6,8 +6,8 @@
---
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.08.18*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.08.18**
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.09.11*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.09.11**
### Before submitting an *issue* make sure you have:
- [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@@ -35,7 +35,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl
[debug] User config: []
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
[debug] youtube-dl version 2017.08.18
[debug] youtube-dl version 2017.09.11
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
[debug] Proxy map: {}

View File

@@ -3,7 +3,7 @@
$ youtube-dl -v <your command line>
[debug] System config: []
[debug] User config: []
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
[debug] Command-line args: [u'-v', u'https://www.youtube.com/watch?v=BaW_jenozKcj']
[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
[debug] youtube-dl version 2015.12.06
[debug] Git HEAD: 135392e
@@ -34,7 +34,7 @@ For bug reports, this means that your report should contain the *complete* outpu
If your server has multiple IPs or you suspect censorship, adding `--call-home` may be a good idea to get more diagnostics. If the error is `ERROR: Unable to extract ...` and you cannot reproduce it from multiple countries, add `--dump-pages` (warning: this will yield a rather large output, redirect it to the file `log.txt` by adding `>log.txt 2>&1` to your command-line) or upload the `.dump` files you get when you add `--write-pages` [somewhere](https://gist.github.com/).
**Site support requests must contain an example URL**. An example URL is a URL you might want to download, like `http://www.youtube.com/watch?v=BaW_jenozKc`. There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. `http://www.youtube.com/`) is *not* an example URL.
**Site support requests must contain an example URL**. An example URL is a URL you might want to download, like `https://www.youtube.com/watch?v=BaW_jenozKc`. There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. `https://www.youtube.com/`) is *not* an example URL.
### Are you using the latest version?
@@ -70,7 +70,7 @@ It may sound strange, but some bug reports we receive are completely unrelated t
# DEVELOPER INSTRUCTIONS
Most users do not need to build youtube-dl and can [download the builds](http://rg3.github.io/youtube-dl/download.html) or get them from their distribution.
Most users do not need to build youtube-dl and can [download the builds](https://rg3.github.io/youtube-dl/download.html) or get them from their distribution.
To run youtube-dl as a developer, you don't need to build anything either. Simply execute
@@ -82,6 +82,8 @@ To run the test, simply invoke your favorite test runner, or execute a test file
python test/test_download.py
nosetests
See item 6 of [new extractor tutorial](#adding-support-for-a-new-site) for how to run extractor specific test cases.
If you want to create a build of youtube-dl yourself, you'll need
* python
@@ -118,7 +120,7 @@ After you have ensured this site is distributing its content legally, you can fo
class YourExtractorIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?yourextractor\.com/watch/(?P<id>[0-9]+)'
_TEST = {
'url': 'http://yourextractor.com/watch/42',
'url': 'https://yourextractor.com/watch/42',
'md5': 'TODO: md5 sum of the first 10241 bytes of the video file (use --test)',
'info_dict': {
'id': '42',
@@ -149,10 +151,10 @@ After you have ensured this site is distributing its content legally, you can fo
}
```
5. Add an import in [`youtube_dl/extractor/extractors.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/extractors.py).
6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc.
6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc. Note that tests with `only_matching` key in test's dict are not counted in.
7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L74-L252). Add tests and code for as many as you want.
8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](https://pypi.python.org/pypi/flake8). Also make sure your code works under all [Python](http://www.python.org/) versions claimed supported by youtube-dl, namely 2.6, 2.7, and 3.2+.
9. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this:
8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](https://pypi.python.org/pypi/flake8). Also make sure your code works under all [Python](https://www.python.org/) versions claimed supported by youtube-dl, namely 2.6, 2.7, and 3.2+.
9. When the tests pass, [add](https://git-scm.com/docs/git-add) the new files and [commit](https://git-scm.com/docs/git-commit) them and [push](https://git-scm.com/docs/git-push) the result, like this:
$ git add youtube_dl/extractor/extractors.py
$ git add youtube_dl/extractor/yourextractor.py

View File

@@ -1,3 +1,100 @@
version 2017.09.11
Extractors
* [rutube:playlist] Fix suitable (#14166)
version 2017.09.10
Core
+ [utils] Introduce bool_or_none
* [YoutubeDL] Ensure dir existence for each requested format (#14116)
Extractors
* [fox] Fix extraction (#14147)
* [rutube] Use bool_or_none
* [rutube] Rework and generalize playlist extractors (#13565)
+ [rutube:playlist] Add support for playlists (#13534, #13565)
+ [radiocanada] Add fallback for title extraction (#14145)
* [vk] Use dedicated YouTube embeds extraction routine
* [vice] Use dedicated YouTube embeds extraction routine
* [cracked] Use dedicated YouTube embeds extraction routine
* [chilloutzone] Use dedicated YouTube embeds extraction routine
* [abcnews] Use dedicated YouTube embeds extraction routine
* [youtube] Separate methods for embeds extraction
* [redtube] Fix formats extraction (#14122)
* [arte] Relax unavailability check (#14112)
+ [manyvids] Add support for preview videos from manyvids.com (#14053, #14059)
* [vidme:user] Relax URL regular expression (#14054)
* [bpb] Fix extraction (#14043, #14086)
* [soundcloud] Fix download URL with private tracks (#14093)
* [aliexpress:live] Add support for live.aliexpress.com (#13698, #13707)
* [viidea] Capture and output lecture error message (#14099)
* [radiocanada] Skip unsupported platforms (#14100)
version 2017.09.02
Extractors
* [youtube] Force old layout for each webpage (#14068, #14072, #14074, #14076,
#14077, #14079, #14082, #14083, #14094, #14095, #14096)
* [youtube] Fix upload date extraction (#14065)
+ [charlierose] Add support for episodes (#14062)
+ [bbccouk] Add support for w-prefixed ids (#14056)
* [googledrive] Extend URL regular expression (#9785)
+ [googledrive] Add support for source format (#14046)
* [pornhd] Fix extraction (#14005)
version 2017.08.27.1
Extractors
* [youtube] Fix extraction with --youtube-skip-dash-manifest enabled (#14037)
version 2017.08.27
Core
+ [extractor/common] Extract height and format id for HTML5 videos (#14034)
* [downloader/http] Rework HTTP downloader (#506, #809, #2849, #4240, #6023,
#8625, #9483)
* Simplify code and split into separate routines to facilitate maintaining
* Make retry mechanism work on errors during actual download not only
during connection establishment phase
* Retry on ECONNRESET and ETIMEDOUT during reading data from network
* Retry on content too short
* Show error description on retry
Extractors
* [generic] Lower preference for extraction from LD-JSON
* [rai] Fix audio formats extraction (#14024)
* [youtube] Fix controversy videos extraction (#14027, #14029)
* [mixcloud] Fix extraction (#14015, #14020)
version 2017.08.23
Core
+ [extractor/common] Introduce _parse_xml
* [extractor/common] Make HLS and DASH extraction in_parse_html5_media_entries
non fatal (#13970)
* [utils] Fix unescapeHTML for misformed string like "&a&quot;" (#13935)
Extractors
* [cbc:watch] Bypass geo restriction (#13993)
* [toutv] Relax DRM check (#13994)
+ [googledrive] Add support for subtitles (#13619, #13638)
* [pornhub] Relax uploader regular expression (#13906, #13975)
* [bandcamp:album] Extract track titles (#13962)
+ [bbccouk] Add support for events URLs (#13893)
+ [liveleak] Support multi-video pages (#6542)
+ [liveleak] Support another liveleak embedding pattern (#13336)
* [cda] Fix extraction (#13935)
+ [laola1tv] Add support for tv.ittf.com (#13965)
* [mixcloud] Fix extraction (#13958, #13974, #13980, #14003)
version 2017.08.18
Core
@@ -118,7 +215,7 @@ Extractors
* [youku:show] Fix playlist extraction (#13248)
+ [dispeak] Recognize sevt subdomain (#13276)
* [adn] Improve error reporting (#13663)
* [crunchyroll] Relax series and season regex (#13659)
* [crunchyroll] Relax series and season regular expression (#13659)
+ [spiegel:article] Add support for nexx iframe embeds (#13029)
+ [nexx:embed] Add support for iframe embeds
* [nexx] Improve JS embed extraction

View File

@@ -46,8 +46,15 @@ tar: youtube-dl.tar.gz
pypi-files: youtube-dl.bash-completion README.txt youtube-dl.1 youtube-dl.fish
youtube-dl: youtube_dl/*.py youtube_dl/*/*.py
zip --quiet youtube-dl youtube_dl/*.py youtube_dl/*/*.py
zip --quiet --junk-paths youtube-dl youtube_dl/__main__.py
mkdir -p zip
for d in youtube_dl youtube_dl/downloader youtube_dl/extractor youtube_dl/postprocessor ; do \
mkdir -p zip/$$d ;\
cp -pPR $$d/*.py zip/$$d/ ;\
done
touch -t 200001010101 zip/youtube_dl/*.py zip/youtube_dl/*/*.py
mv zip/youtube_dl/__main__.py zip/
cd zip ; zip -q ../youtube-dl youtube_dl/*.py youtube_dl/*/*.py __main__.py
rm -rf zip
echo '#!$(PYTHON)' > youtube-dl
cat youtube-dl.zip >> youtube-dl
rm youtube-dl.zip

View File

@@ -25,7 +25,7 @@ If you do not have curl, you can alternatively use a recent wget:
sudo wget https://yt-dl.org/downloads/latest/youtube-dl -O /usr/local/bin/youtube-dl
sudo chmod a+rx /usr/local/bin/youtube-dl
Windows users can [download an .exe file](https://yt-dl.org/latest/youtube-dl.exe) and place it in any location on their [PATH](http://en.wikipedia.org/wiki/PATH_%28variable%29) except for `%SYSTEMROOT%\System32` (e.g. **do not** put in `C:\Windows\System32`).
Windows users can [download an .exe file](https://yt-dl.org/latest/youtube-dl.exe) and place it in any location on their [PATH](https://en.wikipedia.org/wiki/PATH_%28variable%29) except for `%SYSTEMROOT%\System32` (e.g. **do not** put in `C:\Windows\System32`).
You can also use pip:
@@ -33,7 +33,7 @@ You can also use pip:
This command will update youtube-dl if you have already installed it. See the [pypi page](https://pypi.python.org/pypi/youtube_dl) for more information.
OS X users can install youtube-dl with [Homebrew](http://brew.sh/):
OS X users can install youtube-dl with [Homebrew](https://brew.sh/):
brew install youtube-dl
@@ -458,7 +458,7 @@ You can also use `--config-location` if you want to use custom configuration fil
### Authentication with `.netrc` file
You may also want to configure automatic credentials storage for extractors that support authentication (by providing login and password with `--username` and `--password`) in order not to pass credentials as command line arguments on every youtube-dl execution and prevent tracking plain text passwords in the shell command history. You can achieve this using a [`.netrc` file](http://stackoverflow.com/tags/.netrc/info) on a per extractor basis. For that you will need to create a `.netrc` file in your `$HOME` and restrict permissions to read/write by only you:
You may also want to configure automatic credentials storage for extractors that support authentication (by providing login and password with `--username` and `--password`) in order not to pass credentials as command line arguments on every youtube-dl execution and prevent tracking plain text passwords in the shell command history. You can achieve this using a [`.netrc` file](https://stackoverflow.com/tags/.netrc/info) on a per extractor basis. For that you will need to create a `.netrc` file in your `$HOME` and restrict permissions to read/write by only you:
```
touch $HOME/.netrc
chmod a-rwx,u+rw $HOME/.netrc
@@ -485,7 +485,7 @@ The `-o` option allows users to indicate a template for the output file names.
**tl;dr:** [navigate me to examples](#output-template-examples).
The basic usage is not to set any template arguments when downloading a single file, like in `youtube-dl -o funny_video.flv "http://some/video"`. However, it may contain special sequences that will be replaced when downloading each video. The special sequences may be formatted according to [python string formatting operations](https://docs.python.org/2/library/stdtypes.html#string-formatting). For example, `%(NAME)s` or `%(NAME)05d`. To clarify, that is a percent symbol followed by a name in parentheses, followed by a formatting operations. Allowed names along with sequence type are:
The basic usage is not to set any template arguments when downloading a single file, like in `youtube-dl -o funny_video.flv "https://some/video"`. However, it may contain special sequences that will be replaced when downloading each video. The special sequences may be formatted according to [python string formatting operations](https://docs.python.org/2/library/stdtypes.html#string-formatting). For example, `%(NAME)s` or `%(NAME)05d`. To clarify, that is a percent symbol followed by a name in parentheses, followed by a formatting operations. Allowed names along with sequence type are:
- `id` (string): Video identifier
- `title` (string): Video title
@@ -603,7 +603,7 @@ $ youtube-dl -o '%(uploader)s/%(playlist)s/%(playlist_index)s - %(title)s.%(ext)
$ youtube-dl -u user -p password -o '~/MyVideos/%(playlist)s/%(chapter_number)s - %(chapter)s/%(title)s.%(ext)s' https://www.udemy.com/java-tutorial/
# Download entire series season keeping each series and each season in separate directory under C:/MyVideos
$ youtube-dl -o "C:/MyVideos/%(series)s/%(season_number)s - %(season)s/%(episode_number)s - %(episode)s.%(ext)s" http://videomore.ru/kino_v_detalayah/5_sezon/367617
$ youtube-dl -o "C:/MyVideos/%(series)s/%(season_number)s - %(season)s/%(episode_number)s - %(episode)s.%(ext)s" https://videomore.ru/kino_v_detalayah/5_sezon/367617
# Stream the video being downloaded to stdout
$ youtube-dl -o - BaW_jenozKc
@@ -716,17 +716,17 @@ $ youtube-dl --dateafter 20000101 --datebefore 20091231
### How do I update youtube-dl?
If you've followed [our manual installation instructions](http://rg3.github.io/youtube-dl/download.html), you can simply run `youtube-dl -U` (or, on Linux, `sudo youtube-dl -U`).
If you've followed [our manual installation instructions](https://rg3.github.io/youtube-dl/download.html), you can simply run `youtube-dl -U` (or, on Linux, `sudo youtube-dl -U`).
If you have used pip, a simple `sudo pip install -U youtube-dl` is sufficient to update.
If you have installed youtube-dl using a package manager like *apt-get* or *yum*, use the standard system update mechanism to update. Note that distribution packages are often outdated. As a rule of thumb, youtube-dl releases at least once a month, and often weekly or even daily. Simply go to http://yt-dl.org/ to find out the current version. Unfortunately, there is nothing we youtube-dl developers can do if your distribution serves a really outdated version. You can (and should) complain to your distribution in their bugtracker or support forum.
If you have installed youtube-dl using a package manager like *apt-get* or *yum*, use the standard system update mechanism to update. Note that distribution packages are often outdated. As a rule of thumb, youtube-dl releases at least once a month, and often weekly or even daily. Simply go to https://yt-dl.org to find out the current version. Unfortunately, there is nothing we youtube-dl developers can do if your distribution serves a really outdated version. You can (and should) complain to your distribution in their bugtracker or support forum.
As a last resort, you can also uninstall the version installed by your package manager and follow our manual installation instructions. For that, remove the distribution's package, with a line like
sudo apt-get remove -y youtube-dl
Afterwards, simply follow [our manual installation instructions](http://rg3.github.io/youtube-dl/download.html):
Afterwards, simply follow [our manual installation instructions](https://rg3.github.io/youtube-dl/download.html):
```
sudo wget https://yt-dl.org/latest/youtube-dl -O /usr/local/bin/youtube-dl
@@ -766,11 +766,11 @@ Apparently YouTube requires you to pass a CAPTCHA test if you download too much.
youtube-dl works fine on its own on most sites. However, if you want to convert video/audio, you'll need [avconv](https://libav.org/) or [ffmpeg](https://www.ffmpeg.org/). On some sites - most notably YouTube - videos can be retrieved in a higher quality format without sound. youtube-dl will detect whether avconv/ffmpeg is present and automatically pick the best option.
Videos or video formats streamed via RTMP protocol can only be downloaded when [rtmpdump](https://rtmpdump.mplayerhq.hu/) is installed. Downloading MMS and RTSP videos requires either [mplayer](http://mplayerhq.hu/) or [mpv](https://mpv.io/) to be installed.
Videos or video formats streamed via RTMP protocol can only be downloaded when [rtmpdump](https://rtmpdump.mplayerhq.hu/) is installed. Downloading MMS and RTSP videos requires either [mplayer](https://mplayerhq.hu/) or [mpv](https://mpv.io/) to be installed.
### I have downloaded a video but how can I play it?
Once the video is fully downloaded, use any video player, such as [mpv](https://mpv.io/), [vlc](http://www.videolan.org/) or [mplayer](http://www.mplayerhq.hu/).
Once the video is fully downloaded, use any video player, such as [mpv](https://mpv.io/), [vlc](https://www.videolan.org/) or [mplayer](https://www.mplayerhq.hu/).
### I extracted a video URL with `-g`, but it does not play on another machine / in my web browser.
@@ -845,10 +845,10 @@ Use the `-o` to specify an [output template](#output-template), for example `-o
### How do I download a video starting with a `-`?
Either prepend `http://www.youtube.com/watch?v=` or separate the ID from the options with `--`:
Either prepend `https://www.youtube.com/watch?v=` or separate the ID from the options with `--`:
youtube-dl -- -wNyEUrxzFU
youtube-dl "http://www.youtube.com/watch?v=-wNyEUrxzFU"
youtube-dl "https://www.youtube.com/watch?v=-wNyEUrxzFU"
### How do I pass cookies to youtube-dl?
@@ -862,9 +862,9 @@ Passing cookies to youtube-dl is a good way to workaround login when a particula
### How do I stream directly to media player?
You will first need to tell youtube-dl to stream media to stdout with `-o -`, and also tell your media player to read from stdin (it must be capable of this for streaming) and then pipe former to latter. For example, streaming to [vlc](http://www.videolan.org/) can be achieved with:
You will first need to tell youtube-dl to stream media to stdout with `-o -`, and also tell your media player to read from stdin (it must be capable of this for streaming) and then pipe former to latter. For example, streaming to [vlc](https://www.videolan.org/) can be achieved with:
youtube-dl -o - "http://www.youtube.com/watch?v=BaW_jenozKcj" | vlc -
youtube-dl -o - "https://www.youtube.com/watch?v=BaW_jenozKcj" | vlc -
### How do I download only new videos from a playlist?
@@ -884,7 +884,7 @@ When youtube-dl detects an HLS video, it can download it either with the built-i
When youtube-dl knows that one particular downloader works better for a given website, that downloader will be picked. Otherwise, youtube-dl will pick the best downloader for general compatibility, which at the moment happens to be ffmpeg. This choice may change in future versions of youtube-dl, with improvements of the built-in downloader and/or ffmpeg.
In particular, the generic extractor (used when your website is not in the [list of supported sites by youtube-dl](http://rg3.github.io/youtube-dl/supportedsites.html) cannot mandate one specific downloader.
In particular, the generic extractor (used when your website is not in the [list of supported sites by youtube-dl](https://rg3.github.io/youtube-dl/supportedsites.html) cannot mandate one specific downloader.
If you put either `--hls-prefer-native` or `--hls-prefer-ffmpeg` into your configuration, a different subset of videos will fail to download correctly. Instead, it is much better to [file an issue](https://yt-dl.org/bug) or a pull request which details why the native or the ffmpeg HLS downloader is a better choice for your use case.
@@ -910,7 +910,7 @@ Feel free to bump the issue from time to time by writing a small comment ("Issue
### How can I detect whether a given URL is supported by youtube-dl?
For one, have a look at the [list of supported sites](docs/supportedsites.md). Note that it can sometimes happen that the site changes its URL scheme (say, from http://example.com/video/1234567 to http://example.com/v/1234567 ) and youtube-dl reports an URL of a service in that list as unsupported. In that case, simply report a bug.
For one, have a look at the [list of supported sites](docs/supportedsites.md). Note that it can sometimes happen that the site changes its URL scheme (say, from https://example.com/video/1234567 to https://example.com/v/1234567 ) and youtube-dl reports an URL of a service in that list as unsupported. In that case, simply report a bug.
It is *not* possible to detect whether a URL is supported or not. That's because youtube-dl contains a generic extractor which matches **all** URLs. You may be tempted to disable, exclude, or remove the generic extractor, but the generic extractor not only allows users to extract videos from lots of websites that embed a video from another service, but may also be used to extract video from a service that it's hosting itself. Therefore, we neither recommend nor support disabling, excluding, or removing the generic extractor.
@@ -924,7 +924,7 @@ youtube-dl is an open-source project manned by too few volunteers, so we'd rathe
# DEVELOPER INSTRUCTIONS
Most users do not need to build youtube-dl and can [download the builds](http://rg3.github.io/youtube-dl/download.html) or get them from their distribution.
Most users do not need to build youtube-dl and can [download the builds](https://rg3.github.io/youtube-dl/download.html) or get them from their distribution.
To run youtube-dl as a developer, you don't need to build anything either. Simply execute
@@ -936,6 +936,8 @@ To run the test, simply invoke your favorite test runner, or execute a test file
python test/test_download.py
nosetests
See item 6 of [new extractor tutorial](#adding-support-for-a-new-site) for how to run extractor specific test cases.
If you want to create a build of youtube-dl yourself, you'll need
* python
@@ -972,7 +974,7 @@ After you have ensured this site is distributing its content legally, you can fo
class YourExtractorIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?yourextractor\.com/watch/(?P<id>[0-9]+)'
_TEST = {
'url': 'http://yourextractor.com/watch/42',
'url': 'https://yourextractor.com/watch/42',
'md5': 'TODO: md5 sum of the first 10241 bytes of the video file (use --test)',
'info_dict': {
'id': '42',
@@ -1003,10 +1005,10 @@ After you have ensured this site is distributing its content legally, you can fo
}
```
5. Add an import in [`youtube_dl/extractor/extractors.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/extractors.py).
6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc.
6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc. Note that tests with `only_matching` key in test's dict are not counted in.
7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L74-L252). Add tests and code for as many as you want.
8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](https://pypi.python.org/pypi/flake8). Also make sure your code works under all [Python](http://www.python.org/) versions claimed supported by youtube-dl, namely 2.6, 2.7, and 3.2+.
9. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this:
8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](https://pypi.python.org/pypi/flake8). Also make sure your code works under all [Python](https://www.python.org/) versions claimed supported by youtube-dl, namely 2.6, 2.7, and 3.2+.
9. When the tests pass, [add](https://git-scm.com/docs/git-add) the new files and [commit](https://git-scm.com/docs/git-commit) them and [push](https://git-scm.com/docs/git-push) the result, like this:
$ git add youtube_dl/extractor/extractors.py
$ git add youtube_dl/extractor/yourextractor.py
@@ -1162,7 +1164,7 @@ import youtube_dl
ydl_opts = {}
with youtube_dl.YoutubeDL(ydl_opts) as ydl:
ydl.download(['http://www.youtube.com/watch?v=BaW_jenozKc'])
ydl.download(['https://www.youtube.com/watch?v=BaW_jenozKc'])
```
Most likely, you'll want to use various options. For a list of options available, have a look at [`youtube_dl/YoutubeDL.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/YoutubeDL.py#L129-L279). For a start, if you want to intercept youtube-dl's output, set a `logger` object.
@@ -1201,19 +1203,19 @@ ydl_opts = {
'progress_hooks': [my_hook],
}
with youtube_dl.YoutubeDL(ydl_opts) as ydl:
ydl.download(['http://www.youtube.com/watch?v=BaW_jenozKc'])
ydl.download(['https://www.youtube.com/watch?v=BaW_jenozKc'])
```
# BUGS
Bugs and suggestions should be reported at: <https://github.com/rg3/youtube-dl/issues>. Unless you were prompted to or there is another pertinent reason (e.g. GitHub fails to accept the bug report), please do not send bug reports via personal email. For discussions, join us in the IRC channel [#youtube-dl](irc://chat.freenode.net/#youtube-dl) on freenode ([webchat](http://webchat.freenode.net/?randomnick=1&channels=youtube-dl)).
Bugs and suggestions should be reported at: <https://github.com/rg3/youtube-dl/issues>. Unless you were prompted to or there is another pertinent reason (e.g. GitHub fails to accept the bug report), please do not send bug reports via personal email. For discussions, join us in the IRC channel [#youtube-dl](irc://chat.freenode.net/#youtube-dl) on freenode ([webchat](https://webchat.freenode.net/?randomnick=1&channels=youtube-dl)).
**Please include the full output of youtube-dl when run with `-v`**, i.e. **add** `-v` flag to **your command line**, copy the **whole** output and post it in the issue body wrapped in \`\`\` for better formatting. It should look similar to this:
```
$ youtube-dl -v <your command line>
[debug] System config: []
[debug] User config: []
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
[debug] Command-line args: [u'-v', u'https://www.youtube.com/watch?v=BaW_jenozKcj']
[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
[debug] youtube-dl version 2015.12.06
[debug] Git HEAD: 135392e
@@ -1244,7 +1246,7 @@ For bug reports, this means that your report should contain the *complete* outpu
If your server has multiple IPs or you suspect censorship, adding `--call-home` may be a good idea to get more diagnostics. If the error is `ERROR: Unable to extract ...` and you cannot reproduce it from multiple countries, add `--dump-pages` (warning: this will yield a rather large output, redirect it to the file `log.txt` by adding `>log.txt 2>&1` to your command-line) or upload the `.dump` files you get when you add `--write-pages` [somewhere](https://gist.github.com/).
**Site support requests must contain an example URL**. An example URL is a URL you might want to download, like `http://www.youtube.com/watch?v=BaW_jenozKc`. There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. `http://www.youtube.com/`) is *not* an example URL.
**Site support requests must contain an example URL**. An example URL is a URL you might want to download, like `https://www.youtube.com/watch?v=BaW_jenozKc`. There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. `https://www.youtube.com/`) is *not* an example URL.
### Are you using the latest version?

View File

@@ -38,6 +38,7 @@
- **afreecatv**: afreecatv.com
- **afreecatv:global**: afreecatv.com
- **AirMozilla**
- **AliExpressLive**
- **AlJazeera**
- **Allocine**
- **AlphaPorno**
@@ -363,6 +364,7 @@
- **IPrima**
- **iqiyi**: 爱奇艺
- **Ir90Tv**
- **ITTF**
- **ITV**
- **ivi**: ivi.ru
- **ivi:compilation**: ivi.ru compilations
@@ -419,6 +421,7 @@
- **limelight:channel_list**
- **LiTV**
- **LiveLeak**
- **LiveLeakEmbed**
- **livestream**
- **livestream:original**
- **LnkGo**
@@ -435,6 +438,7 @@
- **MakerTV**
- **mangomolo:live**
- **mangomolo:video**
- **ManyVids**
- **MatchTV**
- **MDR**: MDR.DE and KiKA
- **media.ccc.de**
@@ -699,6 +703,7 @@
- **rutube:embed**: Rutube embedded videos
- **rutube:movie**: Rutube movies
- **rutube:person**: Rutube person videos
- **rutube:playlist**: Rutube playlists
- **RUTV**: RUTV.RU
- **Ruutu**
- **Ruv**

View File

@@ -279,6 +279,7 @@ class TestUtil(unittest.TestCase):
self.assertEqual(unescapeHTML('&#47;'), '/')
self.assertEqual(unescapeHTML('&eacute;'), 'é')
self.assertEqual(unescapeHTML('&#2013266066;'), '&#2013266066;')
self.assertEqual(unescapeHTML('&a&quot;'), '&a"')
# HTML5 entities
self.assertEqual(unescapeHTML('&period;&apos;'), '.\'')

View File

@@ -1710,12 +1710,17 @@ class YoutubeDL(object):
if filename is None:
return
try:
dn = os.path.dirname(sanitize_path(encodeFilename(filename)))
if dn and not os.path.exists(dn):
os.makedirs(dn)
except (OSError, IOError) as err:
self.report_error('unable to create directory ' + error_to_compat_str(err))
def ensure_dir_exists(path):
try:
dn = os.path.dirname(path)
if dn and not os.path.exists(dn):
os.makedirs(dn)
return True
except (OSError, IOError) as err:
self.report_error('unable to create directory ' + error_to_compat_str(err))
return False
if not ensure_dir_exists(sanitize_path(encodeFilename(filename))):
return
if self.params.get('writedescription', False):
@@ -1853,8 +1858,11 @@ class YoutubeDL(object):
for f in requested_formats:
new_info = dict(info_dict)
new_info.update(f)
fname = self.prepare_filename(new_info)
fname = prepend_extension(fname, 'f%s' % f['format_id'], new_info['ext'])
fname = prepend_extension(
self.prepare_filename(new_info),
'f%s' % f['format_id'], new_info['ext'])
if not ensure_dir_exists(fname):
return
downloaded.append(fname)
partial_success = dl(fname, new_info)
success = success and partial_success

View File

@@ -304,11 +304,11 @@ class FileDownloader(object):
"""Report attempt to resume at given byte."""
self.to_screen('[download] Resuming download at byte %s' % resume_len)
def report_retry(self, count, retries):
def report_retry(self, err, count, retries):
"""Report retry in case of HTTP error 5xx"""
self.to_screen(
'[download] Got server HTTP error. Retrying (attempt %d of %s)...'
% (count, self.format_retries(retries)))
'[download] Got server HTTP error: %s. Retrying (attempt %d of %s)...'
% (error_to_compat_str(err), count, self.format_retries(retries)))
def report_file_already_downloaded(self, file_name):
"""Report file has already been fully downloaded."""

View File

@@ -22,8 +22,16 @@ from ..utils import (
class HttpFD(FileDownloader):
def real_download(self, filename, info_dict):
url = info_dict['url']
tmpfilename = self.temp_name(filename)
stream = None
class DownloadContext(dict):
__getattr__ = dict.get
__setattr__ = dict.__setitem__
__delattr__ = dict.__delitem__
ctx = DownloadContext()
ctx.filename = filename
ctx.tmpfilename = self.temp_name(filename)
ctx.stream = None
# Do not include the Accept-Encoding header
headers = {'Youtubedl-no-compression': 'True'}
@@ -38,46 +46,51 @@ class HttpFD(FileDownloader):
if is_test:
request.add_header('Range', 'bytes=0-%s' % str(self._TEST_FILE_SIZE - 1))
# Establish possible resume length
if os.path.isfile(encodeFilename(tmpfilename)):
resume_len = os.path.getsize(encodeFilename(tmpfilename))
else:
resume_len = 0
ctx.open_mode = 'wb'
ctx.resume_len = 0
open_mode = 'wb'
if resume_len != 0:
if self.params.get('continuedl', True):
self.report_resuming_byte(resume_len)
request.add_header('Range', 'bytes=%d-' % resume_len)
open_mode = 'ab'
else:
resume_len = 0
if self.params.get('continuedl', True):
# Establish possible resume length
if os.path.isfile(encodeFilename(ctx.tmpfilename)):
ctx.resume_len = os.path.getsize(encodeFilename(ctx.tmpfilename))
count = 0
retries = self.params.get('retries', 0)
while count <= retries:
class SucceedDownload(Exception):
pass
class RetryDownload(Exception):
def __init__(self, source_error):
self.source_error = source_error
def establish_connection():
if ctx.resume_len != 0:
self.report_resuming_byte(ctx.resume_len)
request.add_header('Range', 'bytes=%d-' % ctx.resume_len)
ctx.open_mode = 'ab'
# Establish connection
try:
data = self.ydl.urlopen(request)
ctx.data = self.ydl.urlopen(request)
# When trying to resume, Content-Range HTTP header of response has to be checked
# to match the value of requested Range HTTP header. This is due to a webservers
# that don't support resuming and serve a whole file with no Content-Range
# set in response despite of requested Range (see
# https://github.com/rg3/youtube-dl/issues/6057#issuecomment-126129799)
if resume_len > 0:
content_range = data.headers.get('Content-Range')
if ctx.resume_len > 0:
content_range = ctx.data.headers.get('Content-Range')
if content_range:
content_range_m = re.search(r'bytes (\d+)-', content_range)
# Content-Range is present and matches requested Range, resume is possible
if content_range_m and resume_len == int(content_range_m.group(1)):
break
if content_range_m and ctx.resume_len == int(content_range_m.group(1)):
return
# Content-Range is either not present or invalid. Assuming remote webserver is
# trying to send the whole file, resume is not possible, so wiping the local file
# and performing entire redownload
self.report_unable_to_resume()
resume_len = 0
open_mode = 'wb'
break
ctx.resume_len = 0
ctx.open_mode = 'wb'
return
except (compat_urllib_error.HTTPError, ) as err:
if (err.code < 500 or err.code >= 600) and err.code != 416:
# Unexpected HTTP error
@@ -86,15 +99,15 @@ class HttpFD(FileDownloader):
# Unable to resume (requested range not satisfiable)
try:
# Open the connection again without the range header
data = self.ydl.urlopen(basic_request)
content_length = data.info()['Content-Length']
ctx.data = self.ydl.urlopen(basic_request)
content_length = ctx.data.info()['Content-Length']
except (compat_urllib_error.HTTPError, ) as err:
if err.code < 500 or err.code >= 600:
raise
else:
# Examine the reported length
if (content_length is not None and
(resume_len - 100 < int(content_length) < resume_len + 100)):
(ctx.resume_len - 100 < int(content_length) < ctx.resume_len + 100)):
# The file had already been fully downloaded.
# Explanation to the above condition: in issue #175 it was revealed that
# YouTube sometimes adds or removes a few bytes from the end of the file,
@@ -102,152 +115,184 @@ class HttpFD(FileDownloader):
# I decided to implement a suggested change and consider the file
# completely downloaded if the file size differs less than 100 bytes from
# the one in the hard drive.
self.report_file_already_downloaded(filename)
self.try_rename(tmpfilename, filename)
self.report_file_already_downloaded(ctx.filename)
self.try_rename(ctx.tmpfilename, ctx.filename)
self._hook_progress({
'filename': filename,
'filename': ctx.filename,
'status': 'finished',
'downloaded_bytes': resume_len,
'total_bytes': resume_len,
'downloaded_bytes': ctx.resume_len,
'total_bytes': ctx.resume_len,
})
return True
raise SucceedDownload()
else:
# The length does not match, we start the download over
self.report_unable_to_resume()
resume_len = 0
open_mode = 'wb'
break
except socket.error as e:
if e.errno != errno.ECONNRESET:
ctx.resume_len = 0
ctx.open_mode = 'wb'
return
raise RetryDownload(err)
except socket.error as err:
if err.errno != errno.ECONNRESET:
# Connection reset is no problem, just retry
raise
raise RetryDownload(err)
# Retry
count += 1
if count <= retries:
self.report_retry(count, retries)
def download():
data_len = ctx.data.info().get('Content-length', None)
if count > retries:
self.report_error('giving up after %s retries' % retries)
return False
# Range HTTP header may be ignored/unsupported by a webserver
# (e.g. extractor/scivee.py, extractor/bambuser.py).
# However, for a test we still would like to download just a piece of a file.
# To achieve this we limit data_len to _TEST_FILE_SIZE and manually control
# block size when downloading a file.
if is_test and (data_len is None or int(data_len) > self._TEST_FILE_SIZE):
data_len = self._TEST_FILE_SIZE
data_len = data.info().get('Content-length', None)
# Range HTTP header may be ignored/unsupported by a webserver
# (e.g. extractor/scivee.py, extractor/bambuser.py).
# However, for a test we still would like to download just a piece of a file.
# To achieve this we limit data_len to _TEST_FILE_SIZE and manually control
# block size when downloading a file.
if is_test and (data_len is None or int(data_len) > self._TEST_FILE_SIZE):
data_len = self._TEST_FILE_SIZE
if data_len is not None:
data_len = int(data_len) + resume_len
min_data_len = self.params.get('min_filesize')
max_data_len = self.params.get('max_filesize')
if min_data_len is not None and data_len < min_data_len:
self.to_screen('\r[download] File is smaller than min-filesize (%s bytes < %s bytes). Aborting.' % (data_len, min_data_len))
return False
if max_data_len is not None and data_len > max_data_len:
self.to_screen('\r[download] File is larger than max-filesize (%s bytes > %s bytes). Aborting.' % (data_len, max_data_len))
return False
byte_counter = 0 + resume_len
block_size = self.params.get('buffersize', 1024)
start = time.time()
# measure time over whole while-loop, so slow_down() and best_block_size() work together properly
now = None # needed for slow_down() in the first loop run
before = start # start measuring
while True:
# Download and write
data_block = data.read(block_size if not is_test else min(block_size, data_len - byte_counter))
byte_counter += len(data_block)
# exit loop when download is finished
if len(data_block) == 0:
break
# Open destination file just in time
if stream is None:
try:
(stream, tmpfilename) = sanitize_open(tmpfilename, open_mode)
assert stream is not None
filename = self.undo_temp_name(tmpfilename)
self.report_destination(filename)
except (OSError, IOError) as err:
self.report_error('unable to open for writing: %s' % str(err))
if data_len is not None:
data_len = int(data_len) + ctx.resume_len
min_data_len = self.params.get('min_filesize')
max_data_len = self.params.get('max_filesize')
if min_data_len is not None and data_len < min_data_len:
self.to_screen('\r[download] File is smaller than min-filesize (%s bytes < %s bytes). Aborting.' % (data_len, min_data_len))
return False
if max_data_len is not None and data_len > max_data_len:
self.to_screen('\r[download] File is larger than max-filesize (%s bytes > %s bytes). Aborting.' % (data_len, max_data_len))
return False
if self.params.get('xattr_set_filesize', False) and data_len is not None:
byte_counter = 0 + ctx.resume_len
block_size = self.params.get('buffersize', 1024)
start = time.time()
# measure time over whole while-loop, so slow_down() and best_block_size() work together properly
now = None # needed for slow_down() in the first loop run
before = start # start measuring
def retry(e):
if ctx.tmpfilename != '-':
ctx.stream.close()
ctx.stream = None
ctx.resume_len = os.path.getsize(encodeFilename(ctx.tmpfilename))
raise RetryDownload(e)
while True:
try:
# Download and write
data_block = ctx.data.read(block_size if not is_test else min(block_size, data_len - byte_counter))
# socket.timeout is a subclass of socket.error but may not have
# errno set
except socket.timeout as e:
retry(e)
except socket.error as e:
if e.errno not in (errno.ECONNRESET, errno.ETIMEDOUT):
raise
retry(e)
byte_counter += len(data_block)
# exit loop when download is finished
if len(data_block) == 0:
break
# Open destination file just in time
if ctx.stream is None:
try:
write_xattr(tmpfilename, 'user.ytdl.filesize', str(data_len).encode('utf-8'))
except (XAttrUnavailableError, XAttrMetadataError) as err:
self.report_error('unable to set filesize xattr: %s' % str(err))
ctx.stream, ctx.tmpfilename = sanitize_open(
ctx.tmpfilename, ctx.open_mode)
assert ctx.stream is not None
ctx.filename = self.undo_temp_name(ctx.tmpfilename)
self.report_destination(ctx.filename)
except (OSError, IOError) as err:
self.report_error('unable to open for writing: %s' % str(err))
return False
try:
stream.write(data_block)
except (IOError, OSError) as err:
if self.params.get('xattr_set_filesize', False) and data_len is not None:
try:
write_xattr(ctx.tmpfilename, 'user.ytdl.filesize', str(data_len).encode('utf-8'))
except (XAttrUnavailableError, XAttrMetadataError) as err:
self.report_error('unable to set filesize xattr: %s' % str(err))
try:
ctx.stream.write(data_block)
except (IOError, OSError) as err:
self.to_stderr('\n')
self.report_error('unable to write data: %s' % str(err))
return False
# Apply rate limit
self.slow_down(start, now, byte_counter - ctx.resume_len)
# end measuring of one loop run
now = time.time()
after = now
# Adjust block size
if not self.params.get('noresizebuffer', False):
block_size = self.best_block_size(after - before, len(data_block))
before = after
# Progress message
speed = self.calc_speed(start, now, byte_counter - ctx.resume_len)
if data_len is None:
eta = None
else:
eta = self.calc_eta(start, time.time(), data_len - ctx.resume_len, byte_counter - ctx.resume_len)
self._hook_progress({
'status': 'downloading',
'downloaded_bytes': byte_counter,
'total_bytes': data_len,
'tmpfilename': ctx.tmpfilename,
'filename': ctx.filename,
'eta': eta,
'speed': speed,
'elapsed': now - start,
})
if is_test and byte_counter == data_len:
break
if ctx.stream is None:
self.to_stderr('\n')
self.report_error('unable to write data: %s' % str(err))
self.report_error('Did not get any data blocks')
return False
if ctx.tmpfilename != '-':
ctx.stream.close()
# Apply rate limit
self.slow_down(start, now, byte_counter - resume_len)
if data_len is not None and byte_counter != data_len:
err = ContentTooShortError(byte_counter, int(data_len))
if count <= retries:
retry(err)
raise err
# end measuring of one loop run
now = time.time()
after = now
self.try_rename(ctx.tmpfilename, ctx.filename)
# Adjust block size
if not self.params.get('noresizebuffer', False):
block_size = self.best_block_size(after - before, len(data_block))
before = after
# Progress message
speed = self.calc_speed(start, now, byte_counter - resume_len)
if data_len is None:
eta = None
else:
eta = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len)
# Update file modification time
if self.params.get('updatetime', True):
info_dict['filetime'] = self.try_utime(ctx.filename, ctx.data.info().get('last-modified', None))
self._hook_progress({
'status': 'downloading',
'downloaded_bytes': byte_counter,
'total_bytes': data_len,
'tmpfilename': tmpfilename,
'filename': filename,
'eta': eta,
'speed': speed,
'elapsed': now - start,
'total_bytes': byte_counter,
'filename': ctx.filename,
'status': 'finished',
'elapsed': time.time() - start,
})
if is_test and byte_counter == data_len:
break
return True
if stream is None:
self.to_stderr('\n')
self.report_error('Did not get any data blocks')
return False
if tmpfilename != '-':
stream.close()
while count <= retries:
try:
establish_connection()
download()
return True
except RetryDownload as e:
count += 1
if count <= retries:
self.report_retry(e.source_error, count, retries)
continue
except SucceedDownload:
return True
if data_len is not None and byte_counter != data_len:
raise ContentTooShortError(byte_counter, int(data_len))
self.try_rename(tmpfilename, filename)
# Update file modification time
if self.params.get('updatetime', True):
info_dict['filetime'] = self.try_utime(filename, data.info().get('last-modified', None))
self._hook_progress({
'downloaded_bytes': byte_counter,
'total_bytes': byte_counter,
'filename': filename,
'status': 'finished',
'elapsed': time.time() - start,
})
return True
self.report_error('giving up after %s retries' % retries)
return False

View File

@@ -7,6 +7,7 @@ import time
from .amp import AMPIE
from .common import InfoExtractor
from .youtube import YoutubeIE
from ..compat import compat_urlparse
@@ -108,9 +109,7 @@ class AbcNewsIE(InfoExtractor):
r'window\.abcnvideo\.url\s*=\s*"([^"]+)"', webpage, 'video URL')
full_video_url = compat_urlparse.urljoin(url, video_url)
youtube_url = self._html_search_regex(
r'<iframe[^>]+src="(https://www\.youtube\.com/embed/[^"]+)"',
webpage, 'YouTube URL', default=None)
youtube_url = YoutubeIE._extract_url(webpage)
timestamp = None
date_str = self._html_search_regex(
@@ -140,7 +139,7 @@ class AbcNewsIE(InfoExtractor):
}
if youtube_url:
entries = [entry, self.url_result(youtube_url, 'Youtube')]
entries = [entry, self.url_result(youtube_url, ie=YoutubeIE.ie_key())]
return self.playlist_result(entries)
return entry

View File

@@ -0,0 +1,53 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
float_or_none,
try_get,
)
class AliExpressLiveIE(InfoExtractor):
_VALID_URL = r'https?://live\.aliexpress\.com/live/(?P<id>\d+)'
_TEST = {
'url': 'https://live.aliexpress.com/live/2800002704436634',
'md5': 'e729e25d47c5e557f2630eaf99b740a5',
'info_dict': {
'id': '2800002704436634',
'ext': 'mp4',
'title': 'CASIMA7.22',
'thumbnail': r're:http://.*\.jpg',
'uploader': 'CASIMA Official Store',
'timestamp': 1500717600,
'upload_date': '20170722',
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
data = self._parse_json(
self._search_regex(
r'(?s)runParams\s*=\s*({.+?})\s*;?\s*var',
webpage, 'runParams'),
video_id)
title = data['title']
formats = self._extract_m3u8_formats(
data['replyStreamUrl'], video_id, 'mp4',
entry_protocol='m3u8_native', m3u8_id='hls')
return {
'id': video_id,
'title': title,
'thumbnail': data.get('coverUrl'),
'uploader': try_get(
data, lambda x: x['followBar']['name'], compat_str),
'timestamp': float_or_none(data.get('startTimeLong'), scale=1000),
'formats': formats,
}

View File

@@ -82,7 +82,7 @@ class ArteTVBaseIE(InfoExtractor):
vsr = player_info['VSR']
if not vsr and not player_info.get('VRU'):
if not vsr:
raise ExtractorError(
'Video %s is not available' % player_info.get('VID') or video_id,
expected=True)

View File

@@ -242,7 +242,12 @@ class BandcampAlbumIE(InfoExtractor):
raise ExtractorError('The page doesn\'t contain any tracks')
# Only tracks with duration info have songs
entries = [
self.url_result(compat_urlparse.urljoin(url, t_path), ie=BandcampIE.ie_key())
self.url_result(
compat_urlparse.urljoin(url, t_path),
ie=BandcampIE.ie_key(),
video_title=self._search_regex(
r'<span\b[^>]+\bitemprop=["\']name["\'][^>]*>([^<]+)',
elem_content, 'track title', fatal=False))
for elem_content, t_path in track_elements
if self._html_search_meta('duration', elem_content, default=None)]

View File

@@ -29,7 +29,7 @@ from ..compat import (
class BBCCoUkIE(InfoExtractor):
IE_NAME = 'bbc.co.uk'
IE_DESC = 'BBC iPlayer'
_ID_REGEX = r'[pb][\da-z]{7}'
_ID_REGEX = r'[pbw][\da-z]{7}'
_VALID_URL = r'''(?x)
https?://
(?:www\.)?bbc\.co\.uk/
@@ -37,7 +37,8 @@ class BBCCoUkIE(InfoExtractor):
programmes/(?!articles/)|
iplayer(?:/[^/]+)?/(?:episode/|playlist/)|
music/(?:clips|audiovideo/popular)[/#]|
radio/player/
radio/player/|
events/[^/]+/play/[^/]+/
)
(?P<id>%s)(?!/(?:episodes|broadcasts|clips))
''' % _ID_REGEX
@@ -232,6 +233,9 @@ class BBCCoUkIE(InfoExtractor):
}, {
'url': 'https://www.bbc.co.uk/music/audiovideo/popular#p055bc55',
'only_matching': True,
}, {
'url': 'http://www.bbc.co.uk/programmes/w3csv1y9',
'only_matching': True,
}]
_USP_RE = r'/([^/]+?)\.ism(?:\.hlsv2\.ism)?/[^/]+\.m3u8'

View File

@@ -33,13 +33,18 @@ class BpbIE(InfoExtractor):
title = self._html_search_regex(
r'<h2 class="white">(.*?)</h2>', webpage, 'title')
video_info_dicts = re.findall(
r"({\s*src:\s*'http://film\.bpb\.de/[^}]+})", webpage)
r"({\s*src\s*:\s*'https?://film\.bpb\.de/[^}]+})", webpage)
formats = []
for video_info in video_info_dicts:
video_info = self._parse_json(video_info, video_id, transform_source=js_to_json)
quality = video_info['quality']
video_url = video_info['src']
video_info = self._parse_json(
video_info, video_id, transform_source=js_to_json, fatal=False)
if not video_info:
continue
video_url = video_info.get('src')
if not video_url:
continue
quality = 'high' if '_high' in video_url else 'low'
formats.append({
'url': video_url,
'preference': 10 if quality == 'high' else 0,

View File

@@ -200,6 +200,7 @@ class CBCWatchBaseIE(InfoExtractor):
'media': 'http://search.yahoo.com/mrss/',
'clearleap': 'http://www.clearleap.com/namespace/clearleap/1.0/',
}
_GEO_COUNTRIES = ['CA']
def _call_api(self, path, video_id):
url = path if path.startswith('http') else self._API_BASE_URL + path
@@ -287,6 +288,11 @@ class CBCWatchBaseIE(InfoExtractor):
class CBCWatchVideoIE(CBCWatchBaseIE):
IE_NAME = 'cbc.ca:watch:video'
_VALID_URL = r'https?://api-cbc\.cloud\.clearleap\.com/cloffice/client/web/play/?\?.*?\bcontentId=(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
_TEST = {
# geo-restricted to Canada, bypassable
'url': 'https://api-cbc.cloud.clearleap.com/cloffice/client/web/play/?contentId=3c84472a-1eea-4dee-9267-2655d5055dcf&categoryId=ebc258f5-ee40-4cca-b66b-ba6bd55b7235',
'only_matching': True,
}
def _real_extract(self, url):
video_id = self._match_id(url)
@@ -323,9 +329,10 @@ class CBCWatchIE(CBCWatchBaseIE):
IE_NAME = 'cbc.ca:watch'
_VALID_URL = r'https?://watch\.cbc\.ca/(?:[^/]+/)+(?P<id>[0-9a-f-]+)'
_TESTS = [{
# geo-restricted to Canada, bypassable
'url': 'http://watch.cbc.ca/doc-zone/season-6/customer-disservice/38e815a-009e3ab12e4',
'info_dict': {
'id': '38e815a-009e3ab12e4',
'id': '9673749a-5e77-484c-8b62-a1092a6b5168',
'ext': 'mp4',
'title': 'Customer (Dis)Service',
'description': 'md5:8bdd6913a0fe03d4b2a17ebe169c7c87',
@@ -337,8 +344,8 @@ class CBCWatchIE(CBCWatchBaseIE):
'skip_download': True,
'format': 'bestvideo',
},
'skip': 'Geo-restricted to Canada',
}, {
# geo-restricted to Canada, bypassable
'url': 'http://watch.cbc.ca/arthur/all/1ed4b385-cd84-49cf-95f0-80f004680057',
'info_dict': {
'id': '1ed4b385-cd84-49cf-95f0-80f004680057',
@@ -346,7 +353,6 @@ class CBCWatchIE(CBCWatchBaseIE):
'description': 'Arthur, the sweetest 8-year-old aardvark, and his pals solve all kinds of problems with humour, kindness and teamwork.',
},
'playlist_mincount': 30,
'skip': 'Geo-restricted to Canada',
}]
def _real_extract(self, url):

View File

@@ -124,7 +124,7 @@ class CDAIE(InfoExtractor):
}
def extract_format(page, version):
json_str = self._search_regex(
json_str = self._html_search_regex(
r'player_data=(\\?["\'])(?P<player_data>.+?)\1', page,
'%s player_json' % version, fatal=False, group='player_data')
if not json_str:

View File

@@ -5,7 +5,7 @@ from ..utils import remove_end
class CharlieRoseIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?charlierose\.com/video(?:s|/player)/(?P<id>\d+)'
_VALID_URL = r'https?://(?:www\.)?charlierose\.com/(?:video|episode)(?:s|/player)/(?P<id>\d+)'
_TESTS = [{
'url': 'https://charlierose.com/videos/27996',
'md5': 'fda41d49e67d4ce7c2411fd2c4702e09',
@@ -24,6 +24,9 @@ class CharlieRoseIE(InfoExtractor):
}, {
'url': 'https://charlierose.com/videos/27996',
'only_matching': True,
}, {
'url': 'https://charlierose.com/episodes/30887?autoplay=true',
'only_matching': True,
}]
_PLAYER_BASE = 'https://charlierose.com/video/player/%s'

View File

@@ -5,6 +5,7 @@ import base64
import json
from .common import InfoExtractor
from .youtube import YoutubeIE
from ..utils import (
clean_html,
ExtractorError
@@ -70,11 +71,9 @@ class ChilloutzoneIE(InfoExtractor):
# If nativePlatform is None a fallback mechanism is used (i.e. youtube embed)
if native_platform is None:
youtube_url = self._html_search_regex(
r'<iframe.* src="((?:https?:)?//(?:[^.]+\.)?youtube\.com/.+?)"',
webpage, 'fallback video URL', default=None)
if youtube_url is not None:
return self.url_result(youtube_url, ie='Youtube')
youtube_url = YoutubeIE._extract_url(webpage)
if youtube_url:
return self.url_result(youtube_url, ie=YoutubeIE.ie_key())
# Non Fallback: Decide to use native source (e.g. youtube or vimeo) or
# the own CDN

View File

@@ -27,6 +27,7 @@ from ..compat import (
compat_urllib_parse_urlencode,
compat_urllib_request,
compat_urlparse,
compat_xml_parse_error,
)
from ..downloader.f4m import remove_encrypted_media
from ..utils import (
@@ -646,15 +647,29 @@ class InfoExtractor(object):
def _download_xml(self, url_or_request, video_id,
note='Downloading XML', errnote='Unable to download XML',
transform_source=None, fatal=True, encoding=None, data=None, headers={}, query={}):
transform_source=None, fatal=True, encoding=None,
data=None, headers={}, query={}):
"""Return the xml as an xml.etree.ElementTree.Element"""
xml_string = self._download_webpage(
url_or_request, video_id, note, errnote, fatal=fatal, encoding=encoding, data=data, headers=headers, query=query)
url_or_request, video_id, note, errnote, fatal=fatal,
encoding=encoding, data=data, headers=headers, query=query)
if xml_string is False:
return xml_string
return self._parse_xml(
xml_string, video_id, transform_source=transform_source,
fatal=fatal)
def _parse_xml(self, xml_string, video_id, transform_source=None, fatal=True):
if transform_source:
xml_string = transform_source(xml_string)
return compat_etree_fromstring(xml_string.encode('utf-8'))
try:
return compat_etree_fromstring(xml_string.encode('utf-8'))
except compat_xml_parse_error as ve:
errmsg = '%s: Failed to parse XML ' % video_id
if fatal:
raise ExtractorError(errmsg, cause=ve)
else:
self.report_warning(errmsg + str(ve))
def _download_json(self, url_or_request, video_id,
note='Downloading JSON metadata',
@@ -2123,11 +2138,11 @@ class InfoExtractor(object):
formats = self._extract_m3u8_formats(
full_url, video_id, ext='mp4',
entry_protocol=m3u8_entry_protocol, m3u8_id=m3u8_id,
preference=preference)
preference=preference, fatal=False)
elif ext == 'mpd':
is_plain_url = False
formats = self._extract_mpd_formats(
full_url, video_id, mpd_id=mpd_id)
full_url, video_id, mpd_id=mpd_id, fatal=False)
else:
is_plain_url = True
formats = [{
@@ -2169,6 +2184,12 @@ class InfoExtractor(object):
f = parse_content_type(source_attributes.get('type'))
is_plain_url, formats = _media_formats(src, media_type, f)
if is_plain_url:
# res attribute is not standard but seen several times
# in the wild
f.update({
'height': int_or_none(source_attributes.get('res')),
'format_id': source_attributes.get('label'),
})
f.update(formats[0])
media_info['formats'].append(f)
else:

View File

@@ -3,6 +3,7 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from .youtube import YoutubeIE
from ..utils import (
parse_iso8601,
str_to_int,
@@ -41,11 +42,9 @@ class CrackedIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
youtube_url = self._search_regex(
r'<iframe[^>]+src="((?:https?:)?//www\.youtube\.com/embed/[^"]+)"',
webpage, 'youtube url', default=None)
youtube_url = YoutubeIE._extract_url(webpage)
if youtube_url:
return self.url_result(youtube_url, 'Youtube')
return self.url_result(youtube_url, ie=YoutubeIE.ie_key())
video_url = self._html_search_regex(
[r'var\s+CK_vidSrc\s*=\s*"([^"]+)"', r'<video\s+src="([^"]+)"'],

View File

@@ -45,6 +45,7 @@ from .anvato import AnvatoIE
from .anysex import AnySexIE
from .aol import AolIE
from .allocine import AllocineIE
from .aliexpress import AliExpressLiveIE
from .aparat import AparatIE
from .appleconnect import AppleConnectIE
from .appletrailers import (
@@ -509,6 +510,7 @@ from .la7 import LA7IE
from .laola1tv import (
Laola1TvEmbedIE,
Laola1TvIE,
ITTFIE,
)
from .lci import LCIIE
from .lcp import (
@@ -536,7 +538,10 @@ from .limelight import (
LimelightChannelListIE,
)
from .litv import LiTVIE
from .liveleak import LiveLeakIE
from .liveleak import (
LiveLeakIE,
LiveLeakEmbedIE,
)
from .livestream import (
LivestreamIE,
LivestreamOriginalIE,
@@ -559,6 +564,7 @@ from .mangomolo import (
MangomoloVideoIE,
MangomoloLiveIE,
)
from .manyvids import ManyVidsIE
from .matchtv import MatchTVIE
from .mdr import MDRIE
from .mediaset import MediasetIE
@@ -893,6 +899,7 @@ from .rutube import (
RutubeEmbedIE,
RutubeMovieIE,
RutubePersonIE,
RutubePlaylistIE,
)
from .rutv import RUTVIE
from .ruutu import RuutuIE

View File

@@ -3,56 +3,99 @@ from __future__ import unicode_literals
from .adobepass import AdobePassIE
from ..utils import (
smuggle_url,
update_url_query,
int_or_none,
parse_age_limit,
parse_duration,
try_get,
unified_timestamp,
)
class FOXIE(AdobePassIE):
_VALID_URL = r'https?://(?:www\.)?fox\.com/watch/(?P<id>[0-9]+)'
_TEST = {
'url': 'http://www.fox.com/watch/255180355939/7684182528',
_VALID_URL = r'https?://(?:www\.)?fox\.com/watch/(?P<id>[\da-fA-F]+)'
_TESTS = [{
# clip
'url': 'https://www.fox.com/watch/4b765a60490325103ea69888fb2bd4e8/',
'md5': 'ebd296fcc41dd4b19f8115d8461a3165',
'info_dict': {
'id': '255180355939',
'id': '4b765a60490325103ea69888fb2bd4e8',
'ext': 'mp4',
'title': 'Official Trailer: Gotham',
'description': 'Tracing the rise of the great DC Comics Super-Villains and vigilantes, Gotham reveals an entirely new chapter that has never been told.',
'duration': 129,
'timestamp': 1400020798,
'upload_date': '20140513',
'uploader': 'NEWA-FNG-FOXCOM',
'title': 'Aftermath: Bruce Wayne Develops Into The Dark Knight',
'description': 'md5:549cd9c70d413adb32ce2a779b53b486',
'duration': 102,
'timestamp': 1504291893,
'upload_date': '20170901',
'creator': 'FOX',
'series': 'Gotham',
},
'add_ie': ['ThePlatform'],
}
'params': {
'skip_download': True,
},
}, {
# episode, geo-restricted
'url': 'https://www.fox.com/watch/087036ca7f33c8eb79b08152b4dd75c1/',
'only_matching': True,
}, {
# episode, geo-restricted, tv provided required
'url': 'https://www.fox.com/watch/30056b295fb57f7452aeeb4920bc3024/',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
settings = self._parse_json(self._search_regex(
r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);',
webpage, 'drupal settings'), video_id)
fox_pdk_player = settings['fox_pdk_player']
release_url = fox_pdk_player['release_url']
query = {
'mbr': 'true',
'switch': 'http'
}
if fox_pdk_player.get('access') == 'locked':
ap_p = settings['foxAdobePassProvider']
rating = ap_p.get('videoRating')
if rating == 'n/a':
rating = None
resource = self._get_mvpd_resource('fbc-fox', None, ap_p['videoGUID'], rating)
query['auth'] = self._extract_mvpd_auth(url, video_id, 'fbc-fox', resource)
video = self._download_json(
'https://api.fox.com/fbc-content/v1_4/video/%s' % video_id,
video_id, headers={
'apikey': 'abdcbed02c124d393b39e818a4312055',
'Content-Type': 'application/json',
'Referer': url,
})
info = self._search_json_ld(webpage, video_id, fatal=False)
info.update({
'_type': 'url_transparent',
'ie_key': 'ThePlatform',
'url': smuggle_url(update_url_query(release_url, query), {'force_smil_url': True}),
title = video['name']
m3u8_url = self._download_json(
video['videoRelease']['url'], video_id)['playURL']
formats = self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4',
entry_protocol='m3u8_native', m3u8_id='hls')
self._sort_formats(formats)
description = video.get('description')
duration = int_or_none(video.get('durationInSeconds')) or int_or_none(
video.get('duration')) or parse_duration(video.get('duration'))
timestamp = unified_timestamp(video.get('datePublished'))
age_limit = parse_age_limit(video.get('contentRating'))
data = try_get(
video, lambda x: x['trackingData']['properties'], dict) or {}
creator = data.get('brand') or data.get('network') or video.get('network')
series = video.get('seriesName') or data.get(
'seriesName') or data.get('show')
season_number = int_or_none(video.get('seasonNumber'))
episode = video.get('name')
episode_number = int_or_none(video.get('episodeNumber'))
release_year = int_or_none(video.get('releaseYear'))
if data.get('authRequired'):
# TODO: AP
pass
return {
'id': video_id,
})
return info
'title': title,
'description': description,
'duration': duration,
'timestamp': timestamp,
'age_limit': age_limit,
'creator': creator,
'series': series,
'season_number': season_number,
'episode': episode,
'episode_number': episode_number,
'release_year': release_year,
'formats': formats,
}

View File

@@ -1519,14 +1519,27 @@ class GenericIE(InfoExtractor):
# LiveLeak embed
{
'url': 'http://www.wykop.pl/link/3088787/',
'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
'md5': '7619da8c820e835bef21a1efa2a0fc71',
'info_dict': {
'id': '874_1459135191',
'ext': 'mp4',
'title': 'Man shows poor quality of new apartment building',
'description': 'The wall is like a sand pile.',
'uploader': 'Lake8737',
}
},
'add_ie': [LiveLeakIE.ie_key()],
},
# Another LiveLeak embed pattern (#13336)
{
'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
'info_dict': {
'id': '2eb_1496309988',
'ext': 'mp4',
'title': 'Thief robs place where everyone was armed',
'description': 'md5:694d73ee79e535953cf2488562288eee',
'uploader': 'brazilwtf',
},
'add_ie': [LiveLeakIE.ie_key()],
},
# Duplicated embedded video URLs
{
@@ -2230,36 +2243,11 @@ class GenericIE(InfoExtractor):
if vid_me_embed_url is not None:
return self.url_result(vid_me_embed_url, 'Vidme')
# Look for embedded YouTube player
matches = re.findall(r'''(?x)
(?:
<iframe[^>]+?src=|
data-video-url=|
<embed[^>]+?src=|
embedSWF\(?:\s*|
<object[^>]+data=|
new\s+SWFObject\(
)
(["\'])
(?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
(?:embed|v|p)/.+?)
\1''', webpage)
if matches:
# Look for YouTube embeds
youtube_urls = YoutubeIE._extract_urls(webpage)
if youtube_urls:
return self.playlist_from_matches(
matches, video_id, video_title, lambda m: unescapeHTML(m[1]))
# Look for lazyYT YouTube embed
matches = re.findall(
r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
if matches:
return self.playlist_from_matches(matches, video_id, video_title, lambda m: unescapeHTML(m))
# Look for Wordpress "YouTube Video Importer" plugin
matches = re.findall(r'''(?x)<div[^>]+
class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
if matches:
return self.playlist_from_matches(matches, video_id, video_title, lambda m: m[-1])
youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
matches = DailymotionIE._extract_urls(webpage)
if matches:
@@ -2757,9 +2745,9 @@ class GenericIE(InfoExtractor):
self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
# Look for LiveLeak embeds
liveleak_url = LiveLeakIE._extract_url(webpage)
if liveleak_url:
return self.url_result(liveleak_url, 'LiveLeak')
liveleak_urls = LiveLeakIE._extract_urls(webpage)
if liveleak_urls:
return self.playlist_from_matches(liveleak_urls, video_id, video_title)
# Look for 3Q SDN embeds
threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
@@ -2858,12 +2846,6 @@ class GenericIE(InfoExtractor):
merged[k] = v
return merged
# Looking for http://schema.org/VideoObject
json_ld = self._search_json_ld(
webpage, video_id, default={}, expected_type='VideoObject')
if json_ld.get('url'):
return merge_dicts(json_ld, info_dict)
# Look for HTML5 media
entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
if entries:
@@ -2882,6 +2864,12 @@ class GenericIE(InfoExtractor):
jwplayer_data, video_id, require_title=False, base_url=url)
return merge_dicts(info, info_dict)
# Looking for http://schema.org/VideoObject
json_ld = self._search_json_ld(
webpage, video_id, default={}, expected_type='VideoObject')
if json_ld.get('url'):
return merge_dicts(json_ld, info_dict)
def check_video(vurl):
if YoutubeIE.suitable(vurl):
return True

View File

@@ -4,26 +4,61 @@ import re
from .common import InfoExtractor
from ..utils import (
determine_ext,
ExtractorError,
int_or_none,
lowercase_escape,
update_url_query,
)
class GoogleDriveIE(InfoExtractor):
_VALID_URL = r'https?://(?:(?:docs|drive)\.google\.com/(?:uc\?.*?id=|file/d/)|video\.google\.com/get_player\?.*?docid=)(?P<id>[a-zA-Z0-9_-]{28,})'
_VALID_URL = r'''(?x)
https?://
(?:
(?:docs|drive)\.google\.com/
(?:
(?:uc|open)\?.*?id=|
file/d/
)|
video\.google\.com/get_player\?.*?docid=
)
(?P<id>[a-zA-Z0-9_-]{28,})
'''
_TESTS = [{
'url': 'https://drive.google.com/file/d/0ByeS4oOUV-49Zzh4R1J6R09zazQ/edit?pli=1',
'md5': 'd109872761f7e7ecf353fa108c0dbe1e',
'md5': '5c602afbbf2c1db91831f5d82f678554',
'info_dict': {
'id': '0ByeS4oOUV-49Zzh4R1J6R09zazQ',
'ext': 'mp4',
'title': 'Big Buck Bunny.mp4',
'duration': 45,
}
}, {
# video can't be watched anonymously due to view count limit reached,
# but can be downloaded (see https://github.com/rg3/youtube-dl/issues/14046)
'url': 'https://drive.google.com/file/d/0B-vUyvmDLdWDcEt4WjBqcmI2XzQ/view',
'md5': 'bfbd670d03a470bb1e6d4a257adec12e',
'info_dict': {
'id': '0B-vUyvmDLdWDcEt4WjBqcmI2XzQ',
'ext': 'mp4',
'title': 'Annabelle Creation (2017)- Z.V1 [TH].MP4',
}
}, {
# video id is longer than 28 characters
'url': 'https://drive.google.com/file/d/1ENcQ_jeCuj7y19s66_Ou9dRP4GKGsodiDQ/edit',
'info_dict': {
'id': '1ENcQ_jeCuj7y19s66_Ou9dRP4GKGsodiDQ',
'ext': 'mp4',
'title': 'Andreea Banica feat Smiley - Hooky Song (Official Video).mp4',
'duration': 189,
},
'only_matching': True,
}, {
'url': 'https://drive.google.com/open?id=0B2fjwgkl1A_CX083Tkowdmt6d28',
'only_matching': True,
}, {
'url': 'https://drive.google.com/uc?id=0B2fjwgkl1A_CX083Tkowdmt6d28',
'only_matching': True,
}]
_FORMATS_EXT = {
@@ -44,6 +79,13 @@ class GoogleDriveIE(InfoExtractor):
'46': 'webm',
'59': 'mp4',
}
_BASE_URL_CAPTIONS = 'https://drive.google.com/timedtext'
_CAPTIONS_ENTRY_TAG = {
'subtitles': 'track',
'automatic_captions': 'target',
}
_caption_formats_ext = []
_captions_xml = None
@staticmethod
def _extract_url(webpage):
@@ -53,54 +95,183 @@ class GoogleDriveIE(InfoExtractor):
if mobj:
return 'https://drive.google.com/file/d/%s' % mobj.group('id')
def _download_subtitles_xml(self, video_id, subtitles_id, hl):
if self._captions_xml:
return
self._captions_xml = self._download_xml(
self._BASE_URL_CAPTIONS, video_id, query={
'id': video_id,
'vid': subtitles_id,
'hl': hl,
'v': video_id,
'type': 'list',
'tlangs': '1',
'fmts': '1',
'vssids': '1',
}, note='Downloading subtitles XML',
errnote='Unable to download subtitles XML', fatal=False)
if self._captions_xml:
for f in self._captions_xml.findall('format'):
if f.attrib.get('fmt_code') and not f.attrib.get('default'):
self._caption_formats_ext.append(f.attrib['fmt_code'])
def _get_captions_by_type(self, video_id, subtitles_id, caption_type,
origin_lang_code=None):
if not subtitles_id or not caption_type:
return
captions = {}
for caption_entry in self._captions_xml.findall(
self._CAPTIONS_ENTRY_TAG[caption_type]):
caption_lang_code = caption_entry.attrib.get('lang_code')
if not caption_lang_code:
continue
caption_format_data = []
for caption_format in self._caption_formats_ext:
query = {
'vid': subtitles_id,
'v': video_id,
'fmt': caption_format,
'lang': (caption_lang_code if origin_lang_code is None
else origin_lang_code),
'type': 'track',
'name': '',
'kind': '',
}
if origin_lang_code is not None:
query.update({'tlang': caption_lang_code})
caption_format_data.append({
'url': update_url_query(self._BASE_URL_CAPTIONS, query),
'ext': caption_format,
})
captions[caption_lang_code] = caption_format_data
return captions
def _get_subtitles(self, video_id, subtitles_id, hl):
if not subtitles_id or not hl:
return
self._download_subtitles_xml(video_id, subtitles_id, hl)
if not self._captions_xml:
return
return self._get_captions_by_type(video_id, subtitles_id, 'subtitles')
def _get_automatic_captions(self, video_id, subtitles_id, hl):
if not subtitles_id or not hl:
return
self._download_subtitles_xml(video_id, subtitles_id, hl)
if not self._captions_xml:
return
track = self._captions_xml.find('track')
if track is None:
return
origin_lang_code = track.attrib.get('lang_code')
if not origin_lang_code:
return
return self._get_captions_by_type(
video_id, subtitles_id, 'automatic_captions', origin_lang_code)
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(
'http://docs.google.com/file/d/%s' % video_id, video_id)
reason = self._search_regex(r'"reason"\s*,\s*"([^"]+)', webpage, 'reason', default=None)
if reason:
raise ExtractorError(reason)
title = self._search_regex(r'"title"\s*,\s*"([^"]+)', webpage, 'title')
title = self._search_regex(
r'"title"\s*,\s*"([^"]+)', webpage, 'title',
default=None) or self._og_search_title(webpage)
duration = int_or_none(self._search_regex(
r'"length_seconds"\s*,\s*"([^"]+)', webpage, 'length seconds', default=None))
fmt_stream_map = self._search_regex(
r'"fmt_stream_map"\s*,\s*"([^"]+)', webpage, 'fmt stream map').split(',')
fmt_list = self._search_regex(r'"fmt_list"\s*,\s*"([^"]+)', webpage, 'fmt_list').split(',')
resolutions = {}
for fmt in fmt_list:
mobj = re.search(
r'^(?P<format_id>\d+)/(?P<width>\d+)[xX](?P<height>\d+)', fmt)
if mobj:
resolutions[mobj.group('format_id')] = (
int(mobj.group('width')), int(mobj.group('height')))
r'"length_seconds"\s*,\s*"([^"]+)', webpage, 'length seconds',
default=None))
formats = []
for fmt_stream in fmt_stream_map:
fmt_stream_split = fmt_stream.split('|')
if len(fmt_stream_split) < 2:
continue
format_id, format_url = fmt_stream_split[:2]
f = {
'url': lowercase_escape(format_url),
'format_id': format_id,
'ext': self._FORMATS_EXT[format_id],
}
resolution = resolutions.get(format_id)
if resolution:
f.update({
'width': resolution[0],
'height': resolution[1],
fmt_stream_map = self._search_regex(
r'"fmt_stream_map"\s*,\s*"([^"]+)', webpage,
'fmt stream map', default='').split(',')
fmt_list = self._search_regex(
r'"fmt_list"\s*,\s*"([^"]+)', webpage,
'fmt_list', default='').split(',')
if fmt_stream_map and fmt_list:
resolutions = {}
for fmt in fmt_list:
mobj = re.search(
r'^(?P<format_id>\d+)/(?P<width>\d+)[xX](?P<height>\d+)', fmt)
if mobj:
resolutions[mobj.group('format_id')] = (
int(mobj.group('width')), int(mobj.group('height')))
for fmt_stream in fmt_stream_map:
fmt_stream_split = fmt_stream.split('|')
if len(fmt_stream_split) < 2:
continue
format_id, format_url = fmt_stream_split[:2]
f = {
'url': lowercase_escape(format_url),
'format_id': format_id,
'ext': self._FORMATS_EXT[format_id],
}
resolution = resolutions.get(format_id)
if resolution:
f.update({
'width': resolution[0],
'height': resolution[1],
})
formats.append(f)
source_url = update_url_query(
'https://drive.google.com/uc', {
'id': video_id,
'export': 'download',
})
urlh = self._request_webpage(
source_url, video_id, note='Requesting source file',
errnote='Unable to request source file', fatal=False)
if urlh:
def add_source_format(src_url):
formats.append({
'url': src_url,
'ext': determine_ext(title, 'mp4').lower(),
'format_id': 'source',
'quality': 1,
})
formats.append(f)
if urlh.headers.get('Content-Disposition'):
add_source_format(source_url)
else:
confirmation_webpage = self._webpage_read_content(
urlh, url, video_id, note='Downloading confirmation page',
errnote='Unable to confirm download', fatal=False)
if confirmation_webpage:
confirm = self._search_regex(
r'confirm=([^&"\']+)', confirmation_webpage,
'confirmation code', fatal=False)
if confirm:
add_source_format(update_url_query(source_url, {
'confirm': confirm,
}))
if not formats:
reason = self._search_regex(
r'"reason"\s*,\s*"([^"]+)', webpage, 'reason', default=None)
if reason:
raise ExtractorError(reason, expected=True)
self._sort_formats(formats)
hl = self._search_regex(
r'"hl"\s*,\s*"([^"]+)', webpage, 'hl', default=None)
subtitles_id = None
ttsurl = self._search_regex(
r'"ttsurl"\s*,\s*"([^"]+)', webpage, 'ttsurl', default=None)
if ttsurl:
# the video Id for subtitles will be the last value in the ttsurl
# query string
subtitles_id = ttsurl.encode('utf-8').decode(
'unicode_escape').split('=')[-1]
return {
'id': video_id,
'title': title,
'thumbnail': self._og_search_thumbnail(webpage, default=None),
'duration': duration,
'formats': formats,
'subtitles': self.extract_subtitles(video_id, subtitles_id, hl),
'automatic_captions': self.extract_automatic_captions(
video_id, subtitles_id, hl),
}

View File

@@ -215,3 +215,21 @@ class Laola1TvIE(Laola1TvEmbedIE):
'formats': formats,
'is_live': is_live,
}
class ITTFIE(InfoExtractor):
_VALID_URL = r'https?://tv\.ittf\.com/video/[^/]+/(?P<id>\d+)'
_TEST = {
'url': 'https://tv.ittf.com/video/peng-wang-wei-matsudaira-kenta/951802',
'only_matching': True,
}
def _real_extract(self, url):
return self.url_result(
update_url_query('https://www.laola1.tv/titanplayer.php', {
'videoid': self._match_id(url),
'type': 'V',
'lang': 'en',
'portal': 'int',
'customer': 1024,
}), Laola1TvEmbedIE.ie_key())

View File

@@ -72,15 +72,20 @@ class LiveLeakIE(InfoExtractor):
'params': {
'skip_download': True,
},
}, {
'url': 'https://www.liveleak.com/view?i=677_1439397581',
'info_dict': {
'id': '677_1439397581',
'title': 'Fuel Depot in China Explosion caught on video',
},
'playlist_count': 3,
}]
@staticmethod
def _extract_url(webpage):
mobj = re.search(
r'<iframe[^>]+src="https?://(?:\w+\.)?liveleak\.com/ll_embed\?(?:.*?)i=(?P<id>[\w_]+)(?:.*)',
def _extract_urls(webpage):
return re.findall(
r'<iframe[^>]+src="(https?://(?:\w+\.)?liveleak\.com/ll_embed\?[^"]*[if]=[\w_]+[^"]+)"',
webpage)
if mobj:
return 'http://www.liveleak.com/view?i=%s' % mobj.group('id')
def _real_extract(self, url):
video_id = self._match_id(url)
@@ -111,23 +116,54 @@ class LiveLeakIE(InfoExtractor):
'age_limit': age_limit,
}
info_dict = entries[0]
for idx, info_dict in enumerate(entries):
for a_format in info_dict['formats']:
if not a_format.get('height'):
a_format['height'] = int_or_none(self._search_regex(
r'([0-9]+)p\.mp4', a_format['url'], 'height label',
default=None))
for a_format in info_dict['formats']:
if not a_format.get('height'):
a_format['height'] = int_or_none(self._search_regex(
r'([0-9]+)p\.mp4', a_format['url'], 'height label',
default=None))
self._sort_formats(info_dict['formats'])
self._sort_formats(info_dict['formats'])
# Don't append entry ID for one-video pages to keep backward compatibility
if len(entries) > 1:
info_dict['id'] = '%s_%s' % (video_id, idx + 1)
else:
info_dict['id'] = video_id
info_dict.update({
'id': video_id,
'title': video_title,
'description': video_description,
'uploader': video_uploader,
'age_limit': age_limit,
'thumbnail': video_thumbnail,
})
info_dict.update({
'title': video_title,
'description': video_description,
'uploader': video_uploader,
'age_limit': age_limit,
'thumbnail': video_thumbnail,
})
return info_dict
return self.playlist_result(entries, video_id, video_title)
class LiveLeakEmbedIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?liveleak\.com/ll_embed\?.*?\b(?P<kind>[if])=(?P<id>[\w_]+)'
# See generic.py for actual test cases
_TESTS = [{
'url': 'https://www.liveleak.com/ll_embed?i=874_1459135191',
'only_matching': True,
}, {
'url': 'https://www.liveleak.com/ll_embed?f=ab065df993c1',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
kind, video_id = mobj.group('kind', 'id')
if kind == 'f':
webpage = self._download_webpage(url, video_id)
liveleak_url = self._search_regex(
r'logourl\s*:\s*(?P<q1>[\'"])(?P<url>%s)(?P=q1)' % LiveLeakIE._VALID_URL,
webpage, 'LiveLeak URL', group='url')
elif kind == 'i':
liveleak_url = 'http://www.liveleak.com/view?i=%s' % video_id
return self.url_result(liveleak_url, ie=LiveLeakIE.ie_key())

View File

@@ -0,0 +1,48 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import int_or_none
class ManyVidsIE(InfoExtractor):
_VALID_URL = r'(?i)https?://(?:www\.)?manyvids\.com/video/(?P<id>\d+)'
_TEST = {
'url': 'https://www.manyvids.com/Video/133957/everthing-about-me/',
'md5': '03f11bb21c52dd12a05be21a5c7dcc97',
'info_dict': {
'id': '133957',
'ext': 'mp4',
'title': 'everthing about me (Preview)',
'view_count': int,
'like_count': int,
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_url = self._search_regex(
r'data-(?:video-filepath|meta-video)\s*=s*(["\'])(?P<url>(?:(?!\1).)+)\1',
webpage, 'video URL', group='url')
title = '%s (Preview)' % self._html_search_regex(
r'<h2[^>]+class="m-a-0"[^>]*>([^<]+)', webpage, 'title')
like_count = int_or_none(self._search_regex(
r'data-likes=["\'](\d+)', webpage, 'like count', default=None))
view_count = int_or_none(self._html_search_regex(
r'(?s)<span[^>]+class="views-wrapper"[^>]*>(.+?)</span', webpage,
'view count', default=None))
return {
'id': video_id,
'title': title,
'view_count': view_count,
'like_count': like_count,
'formats': [{
'url': video_url,
}],
}

View File

@@ -91,12 +91,14 @@ class MixcloudIE(InfoExtractor):
if js_url:
js = self._download_webpage(js_url, track_id, fatal=False)
if js:
key = self._search_regex(
r'player\s*:\s*{.*?\bvalue\s*:\s*(["\'])(?P<key>(?:(?!\1).)+)\1',
js, 'key', default=None, group='key')
if key and isinstance(key, compat_str):
self._keys.insert(0, key)
self._current_key = key
KEY_RE_TEMPLATE = r'player\s*:\s*{.*?\b%s\s*:\s*(["\'])(?P<key>(?:(?!\1).)+)\1'
for key_name in ('value', 'key_value', 'key_value.*?', '.*?value.*?'):
key = self._search_regex(
KEY_RE_TEMPLATE % key_name, js, 'key',
default=None, group='key')
if key and isinstance(key, compat_str):
self._keys.insert(0, key)
self._current_key = key
message = self._html_search_regex(
r'(?s)<div[^>]+class="global-message cloudcast-disabled-notice-light"[^>]*>(.+?)<(?:a|/div)',

View File

@@ -54,7 +54,7 @@ class PornHdIE(InfoExtractor):
r'<title>(.+?) - .*?[Pp]ornHD.*?</title>'], webpage, 'title')
sources = self._parse_json(js_to_json(self._search_regex(
r"(?s)sources'?\s*:\s*(\{.+?\})\s*\}[;,)]",
r"(?s)sources'?\s*[:=]\s*(\{.+?\})",
webpage, 'sources', default='{}')), video_id)
if not sources:
@@ -82,7 +82,8 @@ class PornHdIE(InfoExtractor):
view_count = int_or_none(self._html_search_regex(
r'(\d+) views\s*<', webpage, 'view count', fatal=False))
thumbnail = self._search_regex(
r"'poster'\s*:\s*'([^']+)'", webpage, 'thumbnail', fatal=False)
r"poster'?\s*:\s*([\"'])(?P<url>(?:(?!\1).)+)\1", webpage,
'thumbnail', fatal=False, group='url')
return {
'id': video_id,

View File

@@ -186,7 +186,7 @@ class PornHubIE(InfoExtractor):
title, thumbnail, duration = [None] * 3
video_uploader = self._html_search_regex(
r'(?s)From:&nbsp;.+?<(?:a href="/users/|a href="/channels/|span class="username)[^>]+>(.+?)<',
r'(?s)From:&nbsp;.+?<(?:a\b[^>]+\bhref=["\']/(?:user|channel)s/|span\b[^>]+\bclass=["\']username)[^>]+>(.+?)<',
webpage, 'uploader', fatal=False)
view_count = self._extract_count(

View File

@@ -20,20 +20,37 @@ from ..utils import (
class RadioCanadaIE(InfoExtractor):
IE_NAME = 'radiocanada'
_VALID_URL = r'(?:radiocanada:|https?://ici\.radio-canada\.ca/widgets/mediaconsole/)(?P<app_code>[^:/]+)[:/](?P<id>[0-9]+)'
_TEST = {
'url': 'http://ici.radio-canada.ca/widgets/mediaconsole/medianet/7184272',
'info_dict': {
'id': '7184272',
'ext': 'mp4',
'title': 'Le parcours du tireur capté sur vidéo',
'description': 'Images des caméras de surveillance fournies par la GRC montrant le parcours du tireur d\'Ottawa',
'upload_date': '20141023',
_TESTS = [
{
'url': 'http://ici.radio-canada.ca/widgets/mediaconsole/medianet/7184272',
'info_dict': {
'id': '7184272',
'ext': 'mp4',
'title': 'Le parcours du tireur capté sur vidéo',
'description': 'Images des caméras de surveillance fournies par la GRC montrant le parcours du tireur d\'Ottawa',
'upload_date': '20141023',
},
'params': {
# m3u8 download
'skip_download': True,
}
},
'params': {
# m3u8 download
'skip_download': True,
},
}
{
# empty Title
'url': 'http://ici.radio-canada.ca/widgets/mediaconsole/medianet/7754998/',
'info_dict': {
'id': '7754998',
'ext': 'mp4',
'title': 'letelejournal22h',
'description': 'INTEGRALE WEB 22H-TJ',
'upload_date': '20170720',
},
'params': {
# m3u8 download
'skip_download': True,
},
}
]
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})
@@ -59,6 +76,7 @@ class RadioCanadaIE(InfoExtractor):
device_types.append('android')
formats = []
error = None
# TODO: extract f4m formats
# f4m formats can be extracted using flashhd device_type but they produce unplayable file
for device_type in device_types:
@@ -84,8 +102,8 @@ class RadioCanadaIE(InfoExtractor):
if not v_url:
continue
if v_url == 'null':
raise ExtractorError('%s said: %s' % (
self.IE_NAME, xpath_text(v_data, 'message')), expected=True)
error = xpath_text(v_data, 'message')
continue
ext = determine_ext(v_url)
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
@@ -129,6 +147,9 @@ class RadioCanadaIE(InfoExtractor):
formats.extend(self._extract_f4m_formats(
base_url + '/manifest.f4m', video_id,
f4m_id='hds', fatal=False))
if not formats and error:
raise ExtractorError(
'%s said: %s' % (self.IE_NAME, error), expected=True)
self._sort_formats(formats)
subtitles = {}
@@ -141,7 +162,7 @@ class RadioCanadaIE(InfoExtractor):
return {
'id': video_id,
'title': get_meta('Title'),
'title': get_meta('Title') or get_meta('AV-nomEmission'),
'description': get_meta('Description') or get_meta('ShortDescription'),
'thumbnail': get_meta('imageHR') or get_meta('imageMR') or get_meta('imageBR'),
'duration': int_or_none(get_meta('length')),

View File

@@ -345,11 +345,11 @@ class RaiIE(RaiBaseIE):
media_type = media['type']
if 'Audio' in media_type:
relinker_info = {
'formats': {
'formats': [{
'format_id': media.get('formatoAudio'),
'url': media['audioUrl'],
'ext': media.get('formatoAudio'),
}
}]
}
elif 'Video' in media_type:
relinker_info = self._extract_relinker_info(media['mediaUri'], content_id)

View File

@@ -3,6 +3,7 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
ExtractorError,
int_or_none,
@@ -62,7 +63,23 @@ class RedTubeIE(InfoExtractor):
'format_id': format_id,
'height': int_or_none(format_id),
})
else:
medias = self._parse_json(
self._search_regex(
r'mediaDefinition\s*:\s*(\[.+?\])', webpage,
'media definitions', default='{}'),
video_id, fatal=False)
if medias and isinstance(medias, list):
for media in medias:
format_url = media.get('videoUrl')
if not format_url or not isinstance(format_url, compat_str):
continue
format_id = media.get('quality')
formats.append({
'url': format_url,
'format_id': format_id,
'height': int_or_none(format_id),
})
if not formats:
video_url = self._html_search_regex(
r'<source src="(.+?)" type="video/mp4">', webpage, 'video URL')
formats.append({'url': video_url})
@@ -73,7 +90,7 @@ class RedTubeIE(InfoExtractor):
r'<span[^>]+class="added-time"[^>]*>ADDED ([^<]+)<',
webpage, 'upload date', fatal=False))
duration = int_or_none(self._search_regex(
r'videoDuration\s*:\s*(\d+)', webpage, 'duration', fatal=False))
r'videoDuration\s*:\s*(\d+)', webpage, 'duration', default=None))
view_count = str_to_int(self._search_regex(
r'<span[^>]*>VIEWS</span></td>\s*<td>([\d,.]+)',
webpage, 'view count', fatal=False))

View File

@@ -7,43 +7,84 @@ import itertools
from .common import InfoExtractor
from ..compat import (
compat_str,
compat_parse_qs,
compat_urllib_parse_urlparse,
)
from ..utils import (
determine_ext,
unified_strdate,
bool_or_none,
int_or_none,
try_get,
unified_timestamp,
)
class RutubeIE(InfoExtractor):
class RutubeBaseIE(InfoExtractor):
def _extract_video(self, video, video_id=None, require_title=True):
title = video['title'] if require_title else video.get('title')
age_limit = video.get('is_adult')
if age_limit is not None:
age_limit = 18 if age_limit is True else 0
uploader_id = try_get(video, lambda x: x['author']['id'])
category = try_get(video, lambda x: x['category']['name'])
return {
'id': video.get('id') or video_id,
'title': title,
'description': video.get('description'),
'thumbnail': video.get('thumbnail_url'),
'duration': int_or_none(video.get('duration')),
'uploader': try_get(video, lambda x: x['author']['name']),
'uploader_id': compat_str(uploader_id) if uploader_id else None,
'timestamp': unified_timestamp(video.get('created_ts')),
'category': [category] if category else None,
'age_limit': age_limit,
'view_count': int_or_none(video.get('hits')),
'comment_count': int_or_none(video.get('comments_count')),
'is_live': bool_or_none(video.get('is_livestream')),
}
class RutubeIE(RutubeBaseIE):
IE_NAME = 'rutube'
IE_DESC = 'Rutube videos'
_VALID_URL = r'https?://rutube\.ru/(?:video|(?:play/)?embed)/(?P<id>[\da-z]{32})'
_TESTS = [{
'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
'md5': '79938ade01294ef7e27574890d0d3769',
'info_dict': {
'id': '3eac3b4561676c17df9132a9a1e62e3e',
'ext': 'mp4',
'ext': 'flv',
'title': 'Раненный кенгуру забежал в аптеку',
'description': 'http://www.ntdtv.ru ',
'duration': 80,
'uploader': 'NTDRussian',
'uploader_id': '29790',
'timestamp': 1381943602,
'upload_date': '20131016',
'age_limit': 0,
},
'params': {
# It requires ffmpeg (m3u8 download)
'skip_download': True,
},
}, {
'url': 'http://rutube.ru/play/embed/a10e53b86e8f349080f718582ce4c661',
'only_matching': True,
}, {
'url': 'http://rutube.ru/embed/a10e53b86e8f349080f718582ce4c661',
'only_matching': True,
}, {
'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/?pl_id=4252',
'only_matching': True,
}, {
'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_type=source',
'only_matching': True,
}]
@classmethod
def suitable(cls, url):
return False if RutubePlaylistIE.suitable(url) else super(RutubeIE, cls).suitable(url)
@staticmethod
def _extract_urls(webpage):
return [mobj.group('url') for mobj in re.finditer(
@@ -52,12 +93,12 @@ class RutubeIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
video = self._download_json(
'http://rutube.ru/api/video/%s/?format=json' % video_id,
video_id, 'Downloading video JSON')
# Some videos don't have the author field
author = video.get('author') or {}
info = self._extract_video(video, video_id)
options = self._download_json(
'http://rutube.ru/api/play/options/%s/?format=json' % video_id,
@@ -79,19 +120,8 @@ class RutubeIE(InfoExtractor):
})
self._sort_formats(formats)
return {
'id': video['id'],
'title': video['title'],
'description': video['description'],
'duration': video['duration'],
'view_count': video['hits'],
'formats': formats,
'thumbnail': video['thumbnail_url'],
'uploader': author.get('name'),
'uploader_id': compat_str(author['id']) if author else None,
'upload_date': unified_strdate(video['created_ts']),
'age_limit': 18 if video['is_adult'] else 0,
}
info['formats'] = formats
return info
class RutubeEmbedIE(InfoExtractor):
@@ -103,7 +133,8 @@ class RutubeEmbedIE(InfoExtractor):
'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=',
'info_dict': {
'id': 'a10e53b86e8f349080f718582ce4c661',
'ext': 'mp4',
'ext': 'flv',
'timestamp': 1387830582,
'upload_date': '20131223',
'uploader_id': '297833',
'description': 'Видео группы ★http://vk.com/foxkidsreset★ музей Fox Kids и Jetix<br/><br/> восстановлено и сделано в шикоформате subziro89 http://vk.com/subziro89',
@@ -111,7 +142,7 @@ class RutubeEmbedIE(InfoExtractor):
'title': 'Мистический городок Эйри в Индиан 5 серия озвучка subziro89',
},
'params': {
'skip_download': 'Requires ffmpeg',
'skip_download': True,
},
}, {
'url': 'http://rutube.ru/play/embed/8083783',
@@ -125,10 +156,51 @@ class RutubeEmbedIE(InfoExtractor):
canonical_url = self._html_search_regex(
r'<link\s+rel="canonical"\s+href="([^"]+?)"', webpage,
'Canonical URL')
return self.url_result(canonical_url, 'Rutube')
return self.url_result(canonical_url, RutubeIE.ie_key())
class RutubeChannelIE(InfoExtractor):
class RutubePlaylistBaseIE(RutubeBaseIE):
def _next_page_url(self, page_num, playlist_id, *args, **kwargs):
return self._PAGE_TEMPLATE % (playlist_id, page_num)
def _entries(self, playlist_id, *args, **kwargs):
next_page_url = None
for pagenum in itertools.count(1):
page = self._download_json(
next_page_url or self._next_page_url(
pagenum, playlist_id, *args, **kwargs),
playlist_id, 'Downloading page %s' % pagenum)
results = page.get('results')
if not results or not isinstance(results, list):
break
for result in results:
video_url = result.get('video_url')
if not video_url or not isinstance(video_url, compat_str):
continue
entry = self._extract_video(result, require_title=False)
entry.update({
'_type': 'url',
'url': video_url,
'ie_key': RutubeIE.ie_key(),
})
yield entry
next_page_url = page.get('next')
if not next_page_url or not page.get('has_next'):
break
def _extract_playlist(self, playlist_id, *args, **kwargs):
return self.playlist_result(
self._entries(playlist_id, *args, **kwargs),
playlist_id, kwargs.get('playlist_name'))
def _real_extract(self, url):
return self._extract_playlist(self._match_id(url))
class RutubeChannelIE(RutubePlaylistBaseIE):
IE_NAME = 'rutube:channel'
IE_DESC = 'Rutube channels'
_VALID_URL = r'https?://rutube\.ru/tags/video/(?P<id>\d+)'
@@ -142,27 +214,8 @@ class RutubeChannelIE(InfoExtractor):
_PAGE_TEMPLATE = 'http://rutube.ru/api/tags/video/%s/?page=%s&format=json'
def _extract_videos(self, channel_id, channel_title=None):
entries = []
for pagenum in itertools.count(1):
page = self._download_json(
self._PAGE_TEMPLATE % (channel_id, pagenum),
channel_id, 'Downloading page %s' % pagenum)
results = page['results']
if not results:
break
entries.extend(self.url_result(result['video_url'], 'Rutube') for result in results)
if not page['has_next']:
break
return self.playlist_result(entries, channel_id, channel_title)
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
channel_id = mobj.group('id')
return self._extract_videos(channel_id)
class RutubeMovieIE(RutubeChannelIE):
class RutubeMovieIE(RutubePlaylistBaseIE):
IE_NAME = 'rutube:movie'
IE_DESC = 'Rutube movies'
_VALID_URL = r'https?://rutube\.ru/metainfo/tv/(?P<id>\d+)'
@@ -176,11 +229,11 @@ class RutubeMovieIE(RutubeChannelIE):
movie = self._download_json(
self._MOVIE_TEMPLATE % movie_id, movie_id,
'Downloading movie JSON')
movie_name = movie['name']
return self._extract_videos(movie_id, movie_name)
return self._extract_playlist(
movie_id, playlist_name=movie.get('name'))
class RutubePersonIE(RutubeChannelIE):
class RutubePersonIE(RutubePlaylistBaseIE):
IE_NAME = 'rutube:person'
IE_DESC = 'Rutube person videos'
_VALID_URL = r'https?://rutube\.ru/video/person/(?P<id>\d+)'
@@ -193,3 +246,37 @@ class RutubePersonIE(RutubeChannelIE):
}]
_PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'
class RutubePlaylistIE(RutubePlaylistBaseIE):
IE_NAME = 'rutube:playlist'
IE_DESC = 'Rutube playlists'
_VALID_URL = r'https?://rutube\.ru/(?:video|(?:play/)?embed)/[\da-z]{32}/\?.*?\bpl_id=(?P<id>\d+)'
_TESTS = [{
'url': 'https://rutube.ru/video/cecd58ed7d531fc0f3d795d51cee9026/?pl_id=3097&pl_type=tag',
'info_dict': {
'id': '3097',
},
'playlist_count': 27,
}, {
'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_id=4252&pl_type=source',
'only_matching': True,
}]
_PAGE_TEMPLATE = 'http://rutube.ru/api/playlist/%s/%s/?page=%s&format=json'
@classmethod
def suitable(cls, url):
if not super(RutubePlaylistIE, cls).suitable(url):
return False
params = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
return params.get('pl_type', [None])[0] and int_or_none(params.get('pl_id', [None])[0])
def _next_page_url(self, page_num, playlist_id, item_kind):
return self._PAGE_TEMPLATE % (item_kind, playlist_id, page_num)
def _real_extract(self, url):
qs = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
playlist_kind = qs['pl_type'][0]
playlist_id = qs['pl_id'][0]
return self._extract_playlist(playlist_id, item_kind=playlist_kind)

View File

@@ -1,8 +1,8 @@
# coding: utf-8
from __future__ import unicode_literals
import re
import itertools
import re
from .common import (
InfoExtractor,
@@ -17,6 +17,7 @@ from ..utils import (
ExtractorError,
int_or_none,
unified_strdate,
update_url_query,
)
@@ -120,6 +121,21 @@ class SoundcloudIE(InfoExtractor):
'license': 'cc-by-sa',
},
},
# private link, downloadable format
{
'url': 'https://soundcloud.com/oriuplift/uponly-238-no-talking-wav/s-AyZUd',
'md5': '64a60b16e617d41d0bef032b7f55441e',
'info_dict': {
'id': '340344461',
'ext': 'wav',
'title': 'Uplifting Only 238 [No Talking] (incl. Alex Feed Guestmix) (Aug 31, 2017) [wav]',
'description': 'md5:fa20ee0fca76a3d6df8c7e57f3715366',
'uploader': 'Ori Uplift Music',
'upload_date': '20170831',
'duration': 7449,
'license': 'all-rights-reserved',
},
},
]
_CLIENT_ID = 'JlZIsxg2hY5WnBgtn3jfS0UYCl0K8DOg'
@@ -160,11 +176,13 @@ class SoundcloudIE(InfoExtractor):
'license': info.get('license'),
}
formats = []
query = {'client_id': self._CLIENT_ID}
if secret_token is not None:
query['secret_token'] = secret_token
if info.get('downloadable', False):
# We can build a direct link to the song
format_url = (
'https://api.soundcloud.com/tracks/{0}/download?client_id={1}'.format(
track_id, self._CLIENT_ID))
format_url = update_url_query(
'https://api.soundcloud.com/tracks/%s/download' % track_id, query)
formats.append({
'format_id': 'download',
'ext': info.get('original_format', 'mp3'),
@@ -176,10 +194,7 @@ class SoundcloudIE(InfoExtractor):
# We have to retrieve the url
format_dict = self._download_json(
'https://api.soundcloud.com/i1/tracks/%s/streams' % track_id,
track_id, 'Downloading track url', query={
'client_id': self._CLIENT_ID,
'secret_token': secret_token,
})
track_id, 'Downloading track url', query=query)
for key, stream_url in format_dict.items():
abr = int_or_none(self._search_regex(
@@ -216,7 +231,7 @@ class SoundcloudIE(InfoExtractor):
# cannot be always used, sometimes it can give an HTTP 404 error
formats.append({
'format_id': 'fallback',
'url': info['stream_url'] + '?client_id=' + self._CLIENT_ID,
'url': update_url_query(info['stream_url'], query),
'ext': ext,
})

View File

@@ -5,7 +5,6 @@ from .common import InfoExtractor
from ..utils import (
int_or_none,
js_to_json,
ExtractorError,
urlencode_postdata,
extract_attributes,
smuggle_url,
@@ -78,8 +77,10 @@ class TouTvIE(InfoExtractor):
def _real_extract(self, url):
path = self._match_id(url)
metadata = self._download_json('http://ici.tou.tv/presentation/%s' % path, path)
# IsDrm does not necessarily mean the video is DRM protected (see
# https://github.com/rg3/youtube-dl/issues/13994).
if metadata.get('IsDrm'):
raise ExtractorError('This video is DRM protected.', expected=True)
self.report_warning('This video is probably DRM protected.', path)
video_id = metadata['IdMedia']
details = metadata['Details']
title = details['OriginalTitle']

View File

@@ -7,6 +7,7 @@ import hashlib
import json
from .adobepass import AdobePassIE
from .youtube import YoutubeIE
from .common import InfoExtractor
from ..compat import compat_HTTPError
from ..utils import (
@@ -261,11 +262,9 @@ class ViceArticleIE(InfoExtractor):
if embed_code:
return _url_res('ooyala:%s' % embed_code, 'Ooyala')
youtube_url = self._html_search_regex(
r'<iframe[^>]+src="(.*youtube\.com/.*)"',
body, 'YouTube URL', default=None)
youtube_url = YoutubeIE._extract_url(body)
if youtube_url:
return _url_res(youtube_url, 'Youtube')
return _url_res(youtube_url, YoutubeIE.ie_key())
video_url = self._html_search_regex(
r'data-video-url="([^"]+)"',

View File

@@ -263,29 +263,35 @@ class VidmeListBaseIE(InfoExtractor):
class VidmeUserIE(VidmeListBaseIE):
IE_NAME = 'vidme:user'
_VALID_URL = r'https?://vid\.me/(?:e/)?(?P<id>[\da-zA-Z]{6,})(?!/likes)(?:[^\da-zA-Z]|$)'
_VALID_URL = r'https?://vid\.me/(?:e/)?(?P<id>[\da-zA-Z_-]{6,})(?!/likes)(?:[^\da-zA-Z_-]|$)'
_API_ITEM = 'list'
_TITLE = 'Videos'
_TEST = {
'url': 'https://vid.me/EFARCHIVE',
_TESTS = [{
'url': 'https://vid.me/MasakoX',
'info_dict': {
'id': '3834632',
'title': 'EFARCHIVE - %s' % _TITLE,
'id': '16112341',
'title': 'MasakoX - %s' % _TITLE,
},
'playlist_mincount': 238,
}
'playlist_mincount': 191,
}, {
'url': 'https://vid.me/unsQuare_netWork',
'only_matching': True,
}]
class VidmeUserLikesIE(VidmeListBaseIE):
IE_NAME = 'vidme:user:likes'
_VALID_URL = r'https?://vid\.me/(?:e/)?(?P<id>[\da-zA-Z]{6,})/likes'
_VALID_URL = r'https?://vid\.me/(?:e/)?(?P<id>[\da-zA-Z_-]{6,})/likes'
_API_ITEM = 'likes'
_TITLE = 'Likes'
_TEST = {
_TESTS = [{
'url': 'https://vid.me/ErinAlexis/likes',
'info_dict': {
'id': '6483530',
'title': 'ErinAlexis - %s' % _TITLE,
},
'playlist_mincount': 415,
}
}, {
'url': 'https://vid.me/Kaleidoscope-Ish/likes',
'only_matching': True,
}]

View File

@@ -4,12 +4,14 @@ import re
from .common import InfoExtractor
from ..compat import (
compat_urlparse,
compat_HTTPError,
compat_str,
compat_urlparse,
)
from ..utils import (
parse_duration,
ExtractorError,
js_to_json,
parse_duration,
parse_iso8601,
)
@@ -128,9 +130,16 @@ class ViideaIE(InfoExtractor):
base_url = self._proto_relative_url(cfg['livepipe'], 'http:')
lecture_data = self._download_json(
'%s/site/api/lecture/%s?format=json' % (base_url, lecture_id),
lecture_id)['lecture'][0]
try:
lecture_data = self._download_json(
'%s/site/api/lecture/%s?format=json' % (base_url, lecture_id),
lecture_id)['lecture'][0]
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
msg = self._parse_json(
e.cause.read().decode('utf-8'), lecture_id)
raise ExtractorError(msg['detail'], expected=True)
raise
lecture_info = {
'id': lecture_id,

View File

@@ -25,6 +25,7 @@ from ..utils import (
from .dailymotion import DailymotionIE
from .pladform import PladformIE
from .vimeo import VimeoIE
from .youtube import YoutubeIE
class VKBaseIE(InfoExtractor):
@@ -345,11 +346,9 @@ class VKIE(VKBaseIE):
if re.search(error_re, info_page):
raise ExtractorError(error_msg % video_id, expected=True)
youtube_url = self._search_regex(
r'<iframe[^>]+src="((?:https?:)?//www.youtube.com/embed/[^"]+)"',
info_page, 'youtube iframe', default=None)
youtube_url = YoutubeIE._extract_url(info_page)
if youtube_url:
return self.url_result(youtube_url, 'Youtube')
return self.url_result(youtube_url, ie=YoutubeIE.ie_key())
vimeo_url = VimeoIE._extract_url(url, info_page)
if vimeo_url is not None:

View File

@@ -16,6 +16,7 @@ from ..jsinterp import JSInterpreter
from ..swfinterp import SWFInterpreter
from ..compat import (
compat_chr,
compat_kwargs,
compat_parse_qs,
compat_urllib_parse_unquote,
compat_urllib_parse_unquote_plus,
@@ -245,6 +246,11 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
return True
def _download_webpage(self, *args, **kwargs):
kwargs.setdefault('query', {})['disable_polymer'] = 'true'
return super(YoutubeBaseInfoExtractor, self)._download_webpage(
*args, **compat_kwargs(kwargs))
def _real_initialize(self):
if self._downloader is None:
return
@@ -1003,6 +1009,27 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'Skipping DASH manifest',
],
},
{
# The following content has been identified by the YouTube community
# as inappropriate or offensive to some audiences.
'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
'info_dict': {
'id': '6SJNVb0GnPI',
'ext': 'mp4',
'title': 'Race Differences in Intelligence',
'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
'duration': 965,
'upload_date': '20140124',
'uploader': 'New Century Foundation',
'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
'license': 'Standard YouTube License',
'view_count': int,
},
'params': {
'skip_download': True,
},
},
{
# itag 212
'url': '1t24XAntNCY',
@@ -1347,6 +1374,43 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
playback_url, video_id, 'Marking watched',
'Unable to mark watched', fatal=False)
@staticmethod
def _extract_urls(webpage):
# Embedded YouTube player
entries = [
unescapeHTML(mobj.group('url'))
for mobj in re.finditer(r'''(?x)
(?:
<iframe[^>]+?src=|
data-video-url=|
<embed[^>]+?src=|
embedSWF\(?:\s*|
<object[^>]+data=|
new\s+SWFObject\(
)
(["\'])
(?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
(?:embed|v|p)/.+?)
\1''', webpage)]
# lazyYT YouTube embed
entries.extend(list(map(
unescapeHTML,
re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
# Wordpress "YouTube Video Importer" plugin
matches = re.findall(r'''(?x)<div[^>]+
class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
entries.extend(m[-1] for m in matches)
return entries
@staticmethod
def _extract_url(webpage):
urls = YoutubeIE._extract_urls(webpage)
return urls[0] if urls else None
@classmethod
def extract_id(cls, url):
mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
@@ -1437,9 +1501,14 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
if dash_mpd and dash_mpd[0] not in dash_mpds:
dash_mpds.append(dash_mpd[0])
is_live = None
view_count = None
def extract_view_count(v_info):
return int_or_none(try_get(v_info, lambda x: x['view_count'][0]))
# Get video info
embed_webpage = None
is_live = None
if re.search(r'player-age-gate-content">', video_webpage) is not None:
age_gate = True
# We simulate the access to the video from www.youtube.com/v/{video_id}
@@ -1509,6 +1578,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
continue
get_video_info = compat_parse_qs(video_info_webpage)
add_dash_mpd(get_video_info)
if view_count is None:
view_count = extract_view_count(get_video_info)
if not video_info:
video_info = get_video_info
if 'token' in get_video_info:
@@ -1592,10 +1663,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
return self.playlist_result(entries, video_id, video_title, video_description)
self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
if 'view_count' in video_info:
view_count = int(video_info['view_count'][0])
else:
view_count = None
if view_count is None:
view_count = extract_view_count(video_info)
# Check for "rental" videos
if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
@@ -1639,10 +1708,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
if not upload_date:
upload_date = self._search_regex(
[r'(?s)id="eow-date.*?>(.*?)</span>',
r'id="watch-uploader-info".*?>.*?(?:Published|Uploaded|Streamed live|Started) on (.+?)</strong>'],
r'(?:id="watch-uploader-info".*?>.*?|["\']simpleText["\']\s*:\s*["\'])(?:Published|Uploaded|Streamed live|Started) on (.+?)[<"\']'],
video_webpage, 'upload date', default=None)
if upload_date:
upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
upload_date = unified_strdate(upload_date)
video_license = self._html_search_regex(
@@ -2028,7 +2095,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
|
(%(playlist_id)s)
)""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
_TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s&disable_polymer=true'
_TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s'
_VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&amp;[^"]*?index=(?P<index>\d+)(?:[^>]+>(?P<title>[^<]+))?'
IE_NAME = 'youtube:playlist'
_TESTS = [{

View File

@@ -596,7 +596,7 @@ def unescapeHTML(s):
assert type(s) == compat_str
return re.sub(
r'&([^;]+;)', lambda m: _htmlentity_transform(m.group(1)), s)
r'&([^&;]+;)', lambda m: _htmlentity_transform(m.group(1)), s)
def get_subprocess_encoding():
@@ -1815,6 +1815,10 @@ def float_or_none(v, scale=1, invscale=1, default=None):
return default
def bool_or_none(v, default=None):
return v if isinstance(v, bool) else default
def strip_or_none(v):
return None if v is None else v.strip()

View File

@@ -1,3 +1,3 @@
from __future__ import unicode_literals
__version__ = '2017.08.18'
__version__ = '2017.09.11'