Compare commits
69 Commits
2017.02.21
...
2017.02.27
Author | SHA1 | Date | |
---|---|---|---|
ef48a1175d | |||
c6184bcf7b | |||
18abb74376 | |||
dbc01fdb6f | |||
f264c62334 | |||
0dc5a86a32 | |||
0e879f432a | |||
892b47ab6c | |||
fdeea72611 | |||
7fd4655256 | |||
fd5c4aab59 | |||
8878789f11 | |||
a5cf17989b | |||
b3aec47665 | |||
9d0c08a02c | |||
e498758b9c | |||
5fc8d89361 | |||
d374d943f3 | |||
103f8c8d36 | |||
922ab7840b | |||
831217291a | |||
db182c63fb | |||
eeb0a95684 | |||
231bcd0b6b | |||
204efc8509 | |||
5d3a51e1b9 | |||
ad3033037c | |||
f3bc281239 | |||
441d7a32e5 | |||
51ed496307 | |||
68f17a9c2d | |||
39e7277ed1 | |||
42dcdbe11c | |||
6b097cff27 | |||
f2f7961820 | |||
be5df5ee31 | |||
f2980fddeb | |||
0f57447de7 | |||
19f3821821 | |||
8e1409fd80 | |||
050f143c12 | |||
fafc2bf5a9 | |||
b3175982c3 | |||
89db639dfe | |||
d0d9ade486 | |||
28572a1a0b | |||
0f3d41b44d | |||
d5fd9a3be3 | |||
ada77fa544 | |||
9e03aa75c7 | |||
30eaa3a702 | |||
c59f703610 | |||
bc61c80c14 | |||
345b24538b | |||
63a29b6118 | |||
b5869560a4 | |||
527ef85fe9 | |||
58ad6995cd | |||
a86e416088 | |||
71e9577b94 | |||
0d427c8304 | |||
139d8ac106 | |||
abd29a2ced | |||
31615ac279 | |||
fc320a40d9 | |||
7345d6d465 | |||
86466a8b6f | |||
33dc173cdc | |||
3444844b04 |
6
.github/ISSUE_TEMPLATE.md
vendored
6
.github/ISSUE_TEMPLATE.md
vendored
@ -6,8 +6,8 @@
|
||||
|
||||
---
|
||||
|
||||
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.02.21*. 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 Issues with outdated version will be rejected.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 **2017.02.21**
|
||||
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.02.27*. 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 Issues with outdated version will be rejected.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 **2017.02.27**
|
||||
|
||||
### Before submitting an *issue* make sure you have:
|
||||
- [ ] At least skimmed through [README](https://github.com/rg3/youtube-dl/blob/master/README.md) and **most notably** [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
|
||||
@ -35,7 +35,7 @@ $ youtube-dl -v <your command line>
|
||||
[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 2017.02.21
|
||||
[debug] youtube-dl version 2017.02.27
|
||||
[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: {}
|
||||
|
73
ChangeLog
73
ChangeLog
@ -1,3 +1,76 @@
|
||||
version 2017.02.27
|
||||
|
||||
Core
|
||||
* [downloader/common] Limit displaying 2 digits after decimal point in sleep
|
||||
interval message (#12183)
|
||||
+ [extractor/common] Add preference to _parse_html5_media_entries
|
||||
|
||||
Extractors
|
||||
+ [npo] Add support for zapp.nl
|
||||
+ [npo] Add support for hetklokhuis.nl (#12293)
|
||||
- [scivee] Remove extractor (#9315)
|
||||
+ [cda] Decode download URL (#12255)
|
||||
+ [crunchyroll] Improve uploader extraction (#12267)
|
||||
+ [youtube] Raise GeoRestrictedError
|
||||
+ [dailymotion] Raise GeoRestrictedError
|
||||
+ [mdr] Recognize more URL patterns (#12169)
|
||||
+ [tvigle] Raise GeoRestrictedError
|
||||
* [vevo] Fix extraction for videos with the new streams/streamsV3 format
|
||||
(#11719)
|
||||
+ [freshlive] Add support for freshlive.tv (#12175)
|
||||
+ [xhamster] Capture and output videoClosed error (#12263)
|
||||
+ [etonline] Add support for etonline.com (#12236)
|
||||
+ [njpwworld] Add support for njpwworld.com (#11561)
|
||||
* [amcnetworks] Relax URL regular expression (#12127)
|
||||
|
||||
|
||||
version 2017.02.24.1
|
||||
|
||||
Extractors
|
||||
* [noco] Modernize
|
||||
* [noco] Switch login URL to https (#12246)
|
||||
+ [thescene] Extract more metadata
|
||||
* [thescene] Fix extraction (#12235)
|
||||
+ [tubitv] Use geo bypass mechanism
|
||||
* [openload] Fix extraction (#10408)
|
||||
+ [ivi] Raise GeoRestrictedError
|
||||
|
||||
|
||||
version 2017.02.24
|
||||
|
||||
Core
|
||||
* [options] Hide deprecated options from --help
|
||||
* [options] Deprecate --autonumber-size
|
||||
+ [YoutubeDL] Add support for string formatting operations in output template
|
||||
(#5185, #5748, #6841, #9929, #9966 #9978, #12189)
|
||||
|
||||
Extractors
|
||||
+ [lynda:course] Add webpage extraction fallback (#12238)
|
||||
* [go] Sign all uplynk URLs and use geo bypass only for free videos
|
||||
(#12087, #12210)
|
||||
+ [skylinewebcams] Add support for skylinewebcams.com (#12221)
|
||||
+ [instagram] Add support for multi video posts (#12226)
|
||||
+ [crunchyroll] Extract playlist entries ids
|
||||
* [mgtv] Fix extraction
|
||||
+ [sohu] Raise GeoRestrictedError
|
||||
+ [leeco] Raise GeoRestrictedError and use geo bypass mechanism
|
||||
|
||||
|
||||
version 2017.02.22
|
||||
|
||||
Extractors
|
||||
* [crunchyroll] Fix descriptions with double quotes (#12124)
|
||||
* [dailymotion] Make comment count optional (#12209)
|
||||
+ [vidzi] Add support for vidzi.cc (#12213)
|
||||
+ [24video] Add support for 24video.tube (#12217)
|
||||
+ [crackle] Use geo bypass mechanism
|
||||
+ [viewster] Use geo verification headers
|
||||
+ [tfo] Improve geo restriction detection and use geo bypass mechanism
|
||||
+ [telequebec] Use geo bypass mechanism
|
||||
+ [limelight] Extract PlaylistService errors and improve geo restriction
|
||||
detection
|
||||
|
||||
|
||||
version 2017.02.21
|
||||
|
||||
Core
|
||||
|
148
README.md
148
README.md
@ -217,21 +217,11 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
|
||||
--id Use only video ID in file name
|
||||
-o, --output TEMPLATE Output filename template, see the "OUTPUT
|
||||
TEMPLATE" for all the info
|
||||
--autonumber-size NUMBER Specify the number of digits in
|
||||
%(autonumber)s when it is present in output
|
||||
filename template or --auto-number option
|
||||
is given (default is 5)
|
||||
--autonumber-start NUMBER Specify the start value for %(autonumber)s
|
||||
(default is 1)
|
||||
--restrict-filenames Restrict filenames to only ASCII
|
||||
characters, and avoid "&" and spaces in
|
||||
filenames
|
||||
-A, --auto-number [deprecated; use -o
|
||||
"%(autonumber)s-%(title)s.%(ext)s" ] Number
|
||||
downloaded files starting from 00000
|
||||
-t, --title [deprecated] Use title in file name
|
||||
(default)
|
||||
-l, --literal [deprecated] Alias of --title
|
||||
-w, --no-overwrites Do not overwrite files
|
||||
-c, --continue Force resume of partially downloaded files.
|
||||
By default, youtube-dl will resume
|
||||
@ -486,87 +476,89 @@ 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 have the format `%(NAME)s`. To clarify, that is a percent symbol followed by a name in parentheses, followed by a lowercase S. Allowed names are:
|
||||
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:
|
||||
|
||||
- `id`: Video identifier
|
||||
- `title`: Video title
|
||||
- `url`: Video URL
|
||||
- `ext`: Video filename extension
|
||||
- `alt_title`: A secondary title of the video
|
||||
- `display_id`: An alternative identifier for the video
|
||||
- `uploader`: Full name of the video uploader
|
||||
- `license`: License name the video is licensed under
|
||||
- `creator`: The creator of the video
|
||||
- `release_date`: The date (YYYYMMDD) when the video was released
|
||||
- `timestamp`: UNIX timestamp of the moment the video became available
|
||||
- `upload_date`: Video upload date (YYYYMMDD)
|
||||
- `uploader_id`: Nickname or id of the video uploader
|
||||
- `location`: Physical location where the video was filmed
|
||||
- `duration`: Length of the video in seconds
|
||||
- `view_count`: How many users have watched the video on the platform
|
||||
- `like_count`: Number of positive ratings of the video
|
||||
- `dislike_count`: Number of negative ratings of the video
|
||||
- `repost_count`: Number of reposts of the video
|
||||
- `average_rating`: Average rating give by users, the scale used depends on the webpage
|
||||
- `comment_count`: Number of comments on the video
|
||||
- `age_limit`: Age restriction for the video (years)
|
||||
- `format`: A human-readable description of the format
|
||||
- `format_id`: Format code specified by `--format`
|
||||
- `format_note`: Additional info about the format
|
||||
- `width`: Width of the video
|
||||
- `height`: Height of the video
|
||||
- `resolution`: Textual description of width and height
|
||||
- `tbr`: Average bitrate of audio and video in KBit/s
|
||||
- `abr`: Average audio bitrate in KBit/s
|
||||
- `acodec`: Name of the audio codec in use
|
||||
- `asr`: Audio sampling rate in Hertz
|
||||
- `vbr`: Average video bitrate in KBit/s
|
||||
- `fps`: Frame rate
|
||||
- `vcodec`: Name of the video codec in use
|
||||
- `container`: Name of the container format
|
||||
- `filesize`: The number of bytes, if known in advance
|
||||
- `filesize_approx`: An estimate for the number of bytes
|
||||
- `protocol`: The protocol that will be used for the actual download
|
||||
- `extractor`: Name of the extractor
|
||||
- `extractor_key`: Key name of the extractor
|
||||
- `epoch`: Unix epoch when creating the file
|
||||
- `autonumber`: Five-digit number that will be increased with each download, starting at zero
|
||||
- `playlist`: Name or id of the playlist that contains the video
|
||||
- `playlist_index`: Index of the video in the playlist padded with leading zeros according to the total length of the playlist
|
||||
- `playlist_id`: Playlist identifier
|
||||
- `playlist_title`: Playlist title
|
||||
- `id` (string): Video identifier
|
||||
- `title` (string): Video title
|
||||
- `url` (string): Video URL
|
||||
- `ext` (string): Video filename extension
|
||||
- `alt_title` (string): A secondary title of the video
|
||||
- `display_id` (string): An alternative identifier for the video
|
||||
- `uploader` (string): Full name of the video uploader
|
||||
- `license` (string): License name the video is licensed under
|
||||
- `creator` (string): The creator of the video
|
||||
- `release_date` (string): The date (YYYYMMDD) when the video was released
|
||||
- `timestamp` (numeric): UNIX timestamp of the moment the video became available
|
||||
- `upload_date` (string): Video upload date (YYYYMMDD)
|
||||
- `uploader_id` (string): Nickname or id of the video uploader
|
||||
- `location` (string): Physical location where the video was filmed
|
||||
- `duration` (numeric): Length of the video in seconds
|
||||
- `view_count` (numeric): How many users have watched the video on the platform
|
||||
- `like_count` (numeric): Number of positive ratings of the video
|
||||
- `dislike_count` (numeric): Number of negative ratings of the video
|
||||
- `repost_count` (numeric): Number of reposts of the video
|
||||
- `average_rating` (numeric): Average rating give by users, the scale used depends on the webpage
|
||||
- `comment_count` (numeric): Number of comments on the video
|
||||
- `age_limit` (numeric): Age restriction for the video (years)
|
||||
- `format` (string): A human-readable description of the format
|
||||
- `format_id` (string): Format code specified by `--format`
|
||||
- `format_note` (string): Additional info about the format
|
||||
- `width` (numeric): Width of the video
|
||||
- `height` (numeric): Height of the video
|
||||
- `resolution` (string): Textual description of width and height
|
||||
- `tbr` (numeric): Average bitrate of audio and video in KBit/s
|
||||
- `abr` (numeric): Average audio bitrate in KBit/s
|
||||
- `acodec` (string): Name of the audio codec in use
|
||||
- `asr` (numeric): Audio sampling rate in Hertz
|
||||
- `vbr` (numeric): Average video bitrate in KBit/s
|
||||
- `fps` (numeric): Frame rate
|
||||
- `vcodec` (string): Name of the video codec in use
|
||||
- `container` (string): Name of the container format
|
||||
- `filesize` (numeric): The number of bytes, if known in advance
|
||||
- `filesize_approx` (numeric): An estimate for the number of bytes
|
||||
- `protocol` (string): The protocol that will be used for the actual download
|
||||
- `extractor` (string): Name of the extractor
|
||||
- `extractor_key` (string): Key name of the extractor
|
||||
- `epoch` (numeric): Unix epoch when creating the file
|
||||
- `autonumber` (numeric): Five-digit number that will be increased with each download, starting at zero
|
||||
- `playlist` (string): Name or id of the playlist that contains the video
|
||||
- `playlist_index` (numeric): Index of the video in the playlist padded with leading zeros according to the total length of the playlist
|
||||
- `playlist_id` (string): Playlist identifier
|
||||
- `playlist_title` (string): Playlist title
|
||||
|
||||
|
||||
Available for the video that belongs to some logical chapter or section:
|
||||
- `chapter`: Name or title of the chapter the video belongs to
|
||||
- `chapter_number`: Number of the chapter the video belongs to
|
||||
- `chapter_id`: Id of the chapter the video belongs to
|
||||
- `chapter` (string): Name or title of the chapter the video belongs to
|
||||
- `chapter_number` (numeric): Number of the chapter the video belongs to
|
||||
- `chapter_id` (string): Id of the chapter the video belongs to
|
||||
|
||||
Available for the video that is an episode of some series or programme:
|
||||
- `series`: Title of the series or programme the video episode belongs to
|
||||
- `season`: Title of the season the video episode belongs to
|
||||
- `season_number`: Number of the season the video episode belongs to
|
||||
- `season_id`: Id of the season the video episode belongs to
|
||||
- `episode`: Title of the video episode
|
||||
- `episode_number`: Number of the video episode within a season
|
||||
- `episode_id`: Id of the video episode
|
||||
- `series` (string): Title of the series or programme the video episode belongs to
|
||||
- `season` (string): Title of the season the video episode belongs to
|
||||
- `season_number` (numeric): Number of the season the video episode belongs to
|
||||
- `season_id` (string): Id of the season the video episode belongs to
|
||||
- `episode` (string): Title of the video episode
|
||||
- `episode_number` (numeric): Number of the video episode within a season
|
||||
- `episode_id` (string): Id of the video episode
|
||||
|
||||
Available for the media that is a track or a part of a music album:
|
||||
- `track`: Title of the track
|
||||
- `track_number`: Number of the track within an album or a disc
|
||||
- `track_id`: Id of the track
|
||||
- `artist`: Artist(s) of the track
|
||||
- `genre`: Genre(s) of the track
|
||||
- `album`: Title of the album the track belongs to
|
||||
- `album_type`: Type of the album
|
||||
- `album_artist`: List of all artists appeared on the album
|
||||
- `disc_number`: Number of the disc or other physical medium the track belongs to
|
||||
- `release_year`: Year (YYYY) when the album was released
|
||||
- `track` (string): Title of the track
|
||||
- `track_number` (numeric): Number of the track within an album or a disc
|
||||
- `track_id` (string): Id of the track
|
||||
- `artist` (string): Artist(s) of the track
|
||||
- `genre` (string): Genre(s) of the track
|
||||
- `album` (string): Title of the album the track belongs to
|
||||
- `album_type` (string): Type of the album
|
||||
- `album_artist` (string): List of all artists appeared on the album
|
||||
- `disc_number` (numeric): Number of the disc or other physical medium the track belongs to
|
||||
- `release_year` (numeric): Year (YYYY) when the album was released
|
||||
|
||||
Each aforementioned sequence when referenced in an output template will be replaced by the actual value corresponding to the sequence name. Note that some of the sequences are not guaranteed to be present since they depend on the metadata obtained by a particular extractor. Such sequences will be replaced with `NA`.
|
||||
|
||||
For example for `-o %(title)s-%(id)s.%(ext)s` and an mp4 video with title `youtube-dl test video` and id `BaW_jenozKcj`, this will result in a `youtube-dl test video-BaW_jenozKcj.mp4` file created in the current directory.
|
||||
|
||||
For numeric sequences you can use numeric related formatting, for example, `%(view_count)05d` will result in a string with view count padded with zeros up to 5 characters, like in `00042`.
|
||||
|
||||
Output templates can also contain arbitrary hierarchical path, e.g. `-o '%(playlist)s/%(playlist_index)s - %(title)s.%(ext)s'` which will result in downloading each video in a directory corresponding to this path template. Any missing directory will be automatically created for you.
|
||||
|
||||
To use percent literals in an output template use `%%`. To output to stdout use `-o -`.
|
||||
|
@ -1,6 +1,7 @@
|
||||
from __future__ import unicode_literals, print_function
|
||||
|
||||
from inspect import getsource
|
||||
import io
|
||||
import os
|
||||
from os.path import dirname as dirn
|
||||
import sys
|
||||
@ -95,5 +96,5 @@ module_contents.append(
|
||||
|
||||
module_src = '\n'.join(module_contents) + '\n'
|
||||
|
||||
with open(lazy_extractors_filename, 'wt') as f:
|
||||
with io.open(lazy_extractors_filename, 'wt', encoding='utf-8') as f:
|
||||
f.write(module_src)
|
||||
|
@ -1,6 +1,6 @@
|
||||
#!/bin/bash
|
||||
|
||||
DOWNLOAD_TESTS="age_restriction|download|subtitles|write_annotations|iqiyi_sdk_interpreter"
|
||||
DOWNLOAD_TESTS="age_restriction|download|subtitles|write_annotations|iqiyi_sdk_interpreter|youtube_lists"
|
||||
|
||||
test_set=""
|
||||
multiprocess_args=""
|
||||
|
@ -239,6 +239,7 @@
|
||||
- **ESPN**
|
||||
- **ESPNArticle**
|
||||
- **EsriVideo**
|
||||
- **ETOnline**
|
||||
- **Europa**
|
||||
- **EveryonesMixtape**
|
||||
- **ExpoTV**
|
||||
@ -274,6 +275,7 @@
|
||||
- **francetvinfo.fr**
|
||||
- **Freesound**
|
||||
- **freespeech.org**
|
||||
- **FreshLive**
|
||||
- **Funimation**
|
||||
- **FunnyOrDie**
|
||||
- **Fusion**
|
||||
@ -310,6 +312,7 @@
|
||||
- **HellPorno**
|
||||
- **Helsinki**: helsinki.fi
|
||||
- **HentaiStigma**
|
||||
- **hetklokhuis**
|
||||
- **hgtv.com:show**
|
||||
- **HistoricFilms**
|
||||
- **history:topic**: History.com Topic
|
||||
@ -511,6 +514,7 @@
|
||||
- **Nintendo**
|
||||
- **njoy**: N-JOY
|
||||
- **njoy:embed**
|
||||
- **NJPWWorld**: 新日本プロレスワールド
|
||||
- **NobelPrize**
|
||||
- **Noco**
|
||||
- **Normalboots**
|
||||
@ -666,7 +670,6 @@
|
||||
- **savefrom.net**
|
||||
- **SBS**: sbs.com.au
|
||||
- **schooltv**
|
||||
- **SciVee**
|
||||
- **screen.yahoo:search**: Yahoo screen search
|
||||
- **Screencast**
|
||||
- **ScreencastOMatic**
|
||||
@ -680,6 +683,7 @@
|
||||
- **Shared**: shared.sx
|
||||
- **ShowRoomLive**
|
||||
- **Sina**
|
||||
- **SkylineWebcams**
|
||||
- **skynewsarabia:article**
|
||||
- **skynewsarabia:video**
|
||||
- **SkySports**
|
||||
|
5
setup.py
5
setup.py
@ -107,8 +107,8 @@ setup(
|
||||
url='https://github.com/rg3/youtube-dl',
|
||||
author='Ricardo Garcia',
|
||||
author_email='ytdl@yt-dl.org',
|
||||
maintainer='Philipp Hagemeister',
|
||||
maintainer_email='phihag@phihag.de',
|
||||
maintainer='Sergey M.',
|
||||
maintainer_email='dstftw@gmail.com',
|
||||
packages=[
|
||||
'youtube_dl',
|
||||
'youtube_dl.extractor', 'youtube_dl.downloader',
|
||||
@ -130,6 +130,7 @@ setup(
|
||||
'Programming Language :: Python :: 3.3',
|
||||
'Programming Language :: Python :: 3.4',
|
||||
'Programming Language :: Python :: 3.5',
|
||||
'Programming Language :: Python :: 3.6',
|
||||
],
|
||||
|
||||
cmdclass={'build_lazy_extractors': build_lazy_extractors},
|
||||
|
@ -526,6 +526,7 @@ class TestYoutubeDL(unittest.TestCase):
|
||||
'id': '1234',
|
||||
'ext': 'mp4',
|
||||
'width': None,
|
||||
'height': 1080,
|
||||
}
|
||||
|
||||
def fname(templ):
|
||||
@ -535,6 +536,19 @@ class TestYoutubeDL(unittest.TestCase):
|
||||
self.assertEqual(fname('%(id)s-%(width)s.%(ext)s'), '1234-NA.mp4')
|
||||
# Replace missing fields with 'NA'
|
||||
self.assertEqual(fname('%(uploader_date)s-%(id)s.%(ext)s'), 'NA-1234.mp4')
|
||||
self.assertEqual(fname('%(height)d.%(ext)s'), '1080.mp4')
|
||||
self.assertEqual(fname('%(height)6d.%(ext)s'), ' 1080.mp4')
|
||||
self.assertEqual(fname('%(height)-6d.%(ext)s'), '1080 .mp4')
|
||||
self.assertEqual(fname('%(height)06d.%(ext)s'), '001080.mp4')
|
||||
self.assertEqual(fname('%(height) 06d.%(ext)s'), ' 01080.mp4')
|
||||
self.assertEqual(fname('%(height) 06d.%(ext)s'), ' 01080.mp4')
|
||||
self.assertEqual(fname('%(height)0 6d.%(ext)s'), ' 01080.mp4')
|
||||
self.assertEqual(fname('%(height)0 6d.%(ext)s'), ' 01080.mp4')
|
||||
self.assertEqual(fname('%(height) 0 6d.%(ext)s'), ' 01080.mp4')
|
||||
self.assertEqual(fname('%%(height)06d.%(ext)s'), '%(height)06d.mp4')
|
||||
self.assertEqual(fname('%(width)06d.%(ext)s'), 'NA.mp4')
|
||||
self.assertEqual(fname('%(width)06d.%%(ext)s'), 'NA.%(ext)s')
|
||||
self.assertEqual(fname('%%(width)06d.%(ext)s'), '%(width)06d.mp4')
|
||||
|
||||
def test_format_note(self):
|
||||
ydl = YoutubeDL()
|
||||
|
@ -33,6 +33,7 @@ from .compat import (
|
||||
compat_get_terminal_size,
|
||||
compat_http_client,
|
||||
compat_kwargs,
|
||||
compat_numeric_types,
|
||||
compat_os_name,
|
||||
compat_str,
|
||||
compat_tokenize_tokenize,
|
||||
@ -327,11 +328,21 @@ class YoutubeDL(object):
|
||||
self.params.update(params)
|
||||
self.cache = Cache(self)
|
||||
|
||||
if self.params.get('cn_verification_proxy') is not None:
|
||||
self.report_warning('--cn-verification-proxy is deprecated. Use --geo-verification-proxy instead.')
|
||||
def check_deprecated(param, option, suggestion):
|
||||
if self.params.get(param) is not None:
|
||||
self.report_warning(
|
||||
'%s is deprecated. Use %s instead.' % (option, suggestion))
|
||||
return True
|
||||
return False
|
||||
|
||||
if check_deprecated('cn_verification_proxy', '--cn-verification-proxy', '--geo-verification-proxy'):
|
||||
if self.params.get('geo_verification_proxy') is None:
|
||||
self.params['geo_verification_proxy'] = self.params['cn_verification_proxy']
|
||||
|
||||
check_deprecated('autonumber_size', '--autonumber-size', 'output template with %(autonumber)0Nd, where N in the number of digits')
|
||||
check_deprecated('autonumber', '--auto-number', '-o "%(autonumber)s-%(title)s.%(ext)s"')
|
||||
check_deprecated('usetitle', '--title', '-o "%(title)s-%(id)s.%(ext)s"')
|
||||
|
||||
if params.get('bidi_workaround', False):
|
||||
try:
|
||||
import pty
|
||||
@ -593,10 +604,7 @@ class YoutubeDL(object):
|
||||
autonumber_size = self.params.get('autonumber_size')
|
||||
if autonumber_size is None:
|
||||
autonumber_size = 5
|
||||
autonumber_templ = '%0' + str(autonumber_size) + 'd'
|
||||
template_dict['autonumber'] = autonumber_templ % (self.params.get('autonumber_start', 1) - 1 + self._num_downloads)
|
||||
if template_dict.get('playlist_index') is not None:
|
||||
template_dict['playlist_index'] = '%0*d' % (len(str(template_dict['n_entries'])), template_dict['playlist_index'])
|
||||
template_dict['autonumber'] = self.params.get('autonumber_start', 1) - 1 + self._num_downloads
|
||||
if template_dict.get('resolution') is None:
|
||||
if template_dict.get('width') and template_dict.get('height'):
|
||||
template_dict['resolution'] = '%dx%d' % (template_dict['width'], template_dict['height'])
|
||||
@ -609,12 +617,61 @@ class YoutubeDL(object):
|
||||
compat_str(v),
|
||||
restricted=self.params.get('restrictfilenames'),
|
||||
is_id=(k == 'id'))
|
||||
template_dict = dict((k, sanitize(k, v))
|
||||
template_dict = dict((k, v if isinstance(v, compat_numeric_types) else sanitize(k, v))
|
||||
for k, v in template_dict.items()
|
||||
if v is not None and not isinstance(v, (list, tuple, dict)))
|
||||
template_dict = collections.defaultdict(lambda: 'NA', template_dict)
|
||||
|
||||
outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL)
|
||||
|
||||
# For fields playlist_index and autonumber convert all occurrences
|
||||
# of %(field)s to %(field)0Nd for backward compatibility
|
||||
field_size_compat_map = {
|
||||
'playlist_index': len(str(template_dict['n_entries'])),
|
||||
'autonumber': autonumber_size,
|
||||
}
|
||||
FIELD_SIZE_COMPAT_RE = r'(?<!%)%\((?P<field>autonumber|playlist_index)\)s'
|
||||
mobj = re.search(FIELD_SIZE_COMPAT_RE, outtmpl)
|
||||
if mobj:
|
||||
outtmpl = re.sub(
|
||||
FIELD_SIZE_COMPAT_RE,
|
||||
r'%%(\1)0%dd' % field_size_compat_map[mobj.group('field')],
|
||||
outtmpl)
|
||||
|
||||
NUMERIC_FIELDS = set((
|
||||
'width', 'height', 'tbr', 'abr', 'asr', 'vbr', 'fps', 'filesize', 'filesize_approx',
|
||||
'upload_year', 'upload_month', 'upload_day',
|
||||
'duration', 'view_count', 'like_count', 'dislike_count', 'repost_count',
|
||||
'average_rating', 'comment_count', 'age_limit',
|
||||
'start_time', 'end_time',
|
||||
'chapter_number', 'season_number', 'episode_number',
|
||||
'track_number', 'disc_number', 'release_year',
|
||||
'playlist_index',
|
||||
))
|
||||
|
||||
# Missing numeric fields used together with integer presentation types
|
||||
# in format specification will break the argument substitution since
|
||||
# string 'NA' is returned for missing fields. We will patch output
|
||||
# template for missing fields to meet string presentation type.
|
||||
for numeric_field in NUMERIC_FIELDS:
|
||||
if numeric_field not in template_dict:
|
||||
# As of [1] format syntax is:
|
||||
# %[mapping_key][conversion_flags][minimum_width][.precision][length_modifier]type
|
||||
# 1. https://docs.python.org/2/library/stdtypes.html#string-formatting
|
||||
FORMAT_RE = r'''(?x)
|
||||
(?<!%)
|
||||
%
|
||||
\({0}\) # mapping key
|
||||
(?:[#0\-+ ]+)? # conversion flags (optional)
|
||||
(?:\d+)? # minimum field width (optional)
|
||||
(?:\.\d+)? # precision (optional)
|
||||
[hlL]? # length modifier (optional)
|
||||
[diouxXeEfFgGcrs%] # conversion type
|
||||
'''
|
||||
outtmpl = re.sub(
|
||||
FORMAT_RE.format(numeric_field),
|
||||
r'%({0})s'.format(numeric_field), outtmpl)
|
||||
|
||||
tmpl = compat_expanduser(outtmpl)
|
||||
filename = tmpl % template_dict
|
||||
# Temporary fix for #4787
|
||||
|
@ -416,6 +416,9 @@ def _real_main(argv=None):
|
||||
'config_location': opts.config_location,
|
||||
'geo_bypass': opts.geo_bypass,
|
||||
'geo_bypass_country': opts.geo_bypass_country,
|
||||
# just for deprecation check
|
||||
'autonumber': opts.autonumber if opts.autonumber is True else None,
|
||||
'usetitle': opts.usetitle if opts.usetitle is True else None,
|
||||
}
|
||||
|
||||
with YoutubeDL(ydl_opts) as ydl:
|
||||
|
@ -2760,6 +2760,12 @@ else:
|
||||
compat_kwargs = lambda kwargs: kwargs
|
||||
|
||||
|
||||
try:
|
||||
compat_numeric_types = (int, float, long, complex)
|
||||
except NameError: # Python 3
|
||||
compat_numeric_types = (int, float, complex)
|
||||
|
||||
|
||||
if sys.version_info < (2, 7):
|
||||
def compat_socket_create_connection(address, timeout, source_address=None):
|
||||
host, port = address
|
||||
@ -2895,6 +2901,7 @@ __all__ = [
|
||||
'compat_input',
|
||||
'compat_itertools_count',
|
||||
'compat_kwargs',
|
||||
'compat_numeric_types',
|
||||
'compat_ord',
|
||||
'compat_os_name',
|
||||
'compat_parse_qs',
|
||||
|
@ -347,7 +347,10 @@ class FileDownloader(object):
|
||||
if min_sleep_interval:
|
||||
max_sleep_interval = self.params.get('max_sleep_interval', min_sleep_interval)
|
||||
sleep_interval = random.uniform(min_sleep_interval, max_sleep_interval)
|
||||
self.to_screen('[download] Sleeping %s seconds...' % sleep_interval)
|
||||
self.to_screen(
|
||||
'[download] Sleeping %s seconds...' % (
|
||||
int(sleep_interval) if sleep_interval.is_integer()
|
||||
else '%.2f' % sleep_interval))
|
||||
time.sleep(sleep_interval)
|
||||
|
||||
return self.real_download(filename, info_dict)
|
||||
|
@ -10,7 +10,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class AMCNetworksIE(ThePlatformIE):
|
||||
_VALID_URL = r'https?://(?:www\.)?(?:amc|bbcamerica|ifc|wetv)\.com/(?:movies/|shows/[^/]+/(?:full-episodes/)?[^/]+/episode-\d+(?:-(?:[^/]+/)?|/))(?P<id>[^/?#]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?(?:amc|bbcamerica|ifc|wetv)\.com/(?:movies|shows(?:/[^/]+)+)/(?P<id>[^/?#]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.ifc.com/shows/maron/season-04/episode-01/step-1',
|
||||
'md5': '',
|
||||
@ -44,6 +44,12 @@ class AMCNetworksIE(ThePlatformIE):
|
||||
}, {
|
||||
'url': 'http://www.bbcamerica.com/shows/doctor-who/full-episodes/the-power-of-the-daleks/episode-01-episode-1-color-version',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.wetv.com/shows/mama-june-from-not-to-hot/full-episode/season-01/thin-tervention',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.wetv.com/shows/la-hair/videos/season-05/episode-09-episode-9-2/episode-9-sneak-peek-3',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
@ -1,6 +1,7 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import codecs
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
@ -96,6 +97,10 @@ class CDAIE(InfoExtractor):
|
||||
if not video or 'file' not in video:
|
||||
self.report_warning('Unable to extract %s version information' % version)
|
||||
return
|
||||
if video['file'].startswith('uggc'):
|
||||
video['file'] = codecs.decode(video['file'], 'rot_13')
|
||||
if video['file'].endswith('adc.mp4'):
|
||||
video['file'] = video['file'].replace('adc.mp4', '.mp4')
|
||||
f = {
|
||||
'url': video['file'],
|
||||
}
|
||||
|
@ -2010,7 +2010,7 @@ class InfoExtractor(object):
|
||||
})
|
||||
return formats
|
||||
|
||||
def _parse_html5_media_entries(self, base_url, webpage, video_id, m3u8_id=None, m3u8_entry_protocol='m3u8', mpd_id=None):
|
||||
def _parse_html5_media_entries(self, base_url, webpage, video_id, m3u8_id=None, m3u8_entry_protocol='m3u8', mpd_id=None, preference=None):
|
||||
def absolute_url(video_url):
|
||||
return compat_urlparse.urljoin(base_url, video_url)
|
||||
|
||||
@ -2032,7 +2032,8 @@ class InfoExtractor(object):
|
||||
is_plain_url = False
|
||||
formats = self._extract_m3u8_formats(
|
||||
full_url, video_id, ext='mp4',
|
||||
entry_protocol=m3u8_entry_protocol, m3u8_id=m3u8_id)
|
||||
entry_protocol=m3u8_entry_protocol, m3u8_id=m3u8_id,
|
||||
preference=preference)
|
||||
elif ext == 'mpd':
|
||||
is_plain_url = False
|
||||
formats = self._extract_mpd_formats(
|
||||
|
@ -6,6 +6,7 @@ from ..utils import int_or_none
|
||||
|
||||
|
||||
class CrackleIE(InfoExtractor):
|
||||
_GEO_COUNTRIES = ['US']
|
||||
_VALID_URL = r'(?:crackle:|https?://(?:(?:www|m)\.)?crackle\.com/(?:playlist/\d+/|(?:[^/]+/)+))(?P<id>\d+)'
|
||||
_TEST = {
|
||||
'url': 'http://www.crackle.com/comedians-in-cars-getting-coffee/2498934',
|
||||
|
@ -123,7 +123,7 @@ class CrunchyrollIE(CrunchyrollBaseIE):
|
||||
'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
|
||||
'info_dict': {
|
||||
'id': '645513',
|
||||
'ext': 'flv',
|
||||
'ext': 'mp4',
|
||||
'title': 'Wanna be the Strongest in the World Episode 1 – An Idol-Wrestler is Born!',
|
||||
'description': 'md5:2d17137920c64f2f49981a7797d275ef',
|
||||
'thumbnail': 'http://img1.ak.crunchyroll.com/i/spire1-tmb/20c6b5e10f1a47b10516877d3c039cae1380951166_full.jpg',
|
||||
@ -192,6 +192,36 @@ class CrunchyrollIE(CrunchyrollBaseIE):
|
||||
# geo-restricted (US), 18+ maturity wall, non-premium available
|
||||
'url': 'http://www.crunchyroll.com/cosplay-complex-ova/episode-1-the-birth-of-the-cosplay-club-565617',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# A description with double quotes
|
||||
'url': 'http://www.crunchyroll.com/11eyes/episode-1-piros-jszaka-red-night-535080',
|
||||
'info_dict': {
|
||||
'id': '535080',
|
||||
'ext': 'mp4',
|
||||
'title': '11eyes Episode 1 – Piros éjszaka - Red Night',
|
||||
'description': 'Kakeru and Yuka are thrown into an alternate nightmarish world they call "Red Night".',
|
||||
'uploader': 'Marvelous AQL Inc.',
|
||||
'upload_date': '20091021',
|
||||
},
|
||||
'params': {
|
||||
# Just test metadata extraction
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
# make sure we can extract an uploader name that's not a link
|
||||
'url': 'http://www.crunchyroll.com/hakuoki-reimeiroku/episode-1-dawn-of-the-divine-warriors-606899',
|
||||
'info_dict': {
|
||||
'id': '606899',
|
||||
'ext': 'mp4',
|
||||
'title': 'Hakuoki Reimeiroku Episode 1 – Dawn of the Divine Warriors',
|
||||
'description': 'Ryunosuke was left to die, but Serizawa-san asked him a simple question "Do you want to live?"',
|
||||
'uploader': 'Geneon Entertainment',
|
||||
'upload_date': '20120717',
|
||||
},
|
||||
'params': {
|
||||
# just test metadata extraction
|
||||
'skip_download': True,
|
||||
},
|
||||
}]
|
||||
|
||||
_FORMAT_IDS = {
|
||||
@ -362,9 +392,9 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
|
||||
r'(?s)<h1[^>]*>((?:(?!<h1).)*?<span[^>]+itemprop=["\']title["\'][^>]*>(?:(?!<h1).)+?)</h1>',
|
||||
webpage, 'video_title')
|
||||
video_title = re.sub(r' {2,}', ' ', video_title)
|
||||
video_description = self._html_search_regex(
|
||||
r'<script[^>]*>\s*.+?\[media_id=%s\].+?"description"\s*:\s*"([^"]+)' % video_id,
|
||||
webpage, 'description', default=None)
|
||||
video_description = self._parse_json(self._html_search_regex(
|
||||
r'<script[^>]*>\s*.+?\[media_id=%s\].+?({.+?"description"\s*:.+?})\);' % video_id,
|
||||
webpage, 'description', default='{}'), video_id).get('description')
|
||||
if video_description:
|
||||
video_description = lowercase_escape(video_description.replace(r'\r\n', '\n'))
|
||||
video_upload_date = self._html_search_regex(
|
||||
@ -373,8 +403,9 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
|
||||
if video_upload_date:
|
||||
video_upload_date = unified_strdate(video_upload_date)
|
||||
video_uploader = self._html_search_regex(
|
||||
r'<a[^>]+href="/publisher/[^"]+"[^>]*>([^<]+)</a>', webpage,
|
||||
'video_uploader', fatal=False)
|
||||
# try looking for both an uploader that's a link and one that's not
|
||||
[r'<a[^>]+href="/publisher/[^"]+"[^>]*>([^<]+)</a>', r'<div>\s*Publisher:\s*<span>\s*(.+?)\s*</span>\s*</div>'],
|
||||
webpage, 'video_uploader', fatal=False)
|
||||
|
||||
available_fmts = []
|
||||
for a, fmt in re.findall(r'(<a[^>]+token=["\']showmedia\.([0-9]{3,4})p["\'][^>]+>)', webpage):
|
||||
@ -519,11 +550,11 @@ class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE):
|
||||
r'(?s)<h1[^>]*>\s*<span itemprop="name">(.*?)</span>',
|
||||
webpage, 'title')
|
||||
episode_paths = re.findall(
|
||||
r'(?s)<li id="showview_videos_media_[0-9]+"[^>]+>.*?<a href="([^"]+)"',
|
||||
r'(?s)<li id="showview_videos_media_(\d+)"[^>]+>.*?<a href="([^"]+)"',
|
||||
webpage)
|
||||
entries = [
|
||||
self.url_result('http://www.crunchyroll.com' + ep, 'Crunchyroll')
|
||||
for ep in episode_paths
|
||||
self.url_result('http://www.crunchyroll.com' + ep, 'Crunchyroll', ep_id)
|
||||
for ep_id, ep in episode_paths
|
||||
]
|
||||
entries.reverse()
|
||||
|
||||
|
@ -66,7 +66,6 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
|
||||
'uploader_id': 'xijv66',
|
||||
'age_limit': 0,
|
||||
'view_count': int,
|
||||
'comment_count': int,
|
||||
}
|
||||
},
|
||||
# Vevo video
|
||||
@ -140,7 +139,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
|
||||
view_count = str_to_int(view_count_str)
|
||||
comment_count = int_or_none(self._search_regex(
|
||||
r'<meta[^>]+itemprop="interactionCount"[^>]+content="UserComments:(\d+)"',
|
||||
webpage, 'comment count', fatal=False))
|
||||
webpage, 'comment count', default=None))
|
||||
|
||||
player_v5 = self._search_regex(
|
||||
[r'buildPlayer\(({.+?})\);\n', # See https://github.com/rg3/youtube-dl/issues/7826
|
||||
@ -283,9 +282,14 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
|
||||
}
|
||||
|
||||
def _check_error(self, info):
|
||||
error = info.get('error')
|
||||
if info.get('error') is not None:
|
||||
title = error['title']
|
||||
# See https://developer.dailymotion.com/api#access-error
|
||||
if error.get('code') == 'DM007':
|
||||
self.raise_geo_restricted(msg=title)
|
||||
raise ExtractorError(
|
||||
'%s said: %s' % (self.IE_NAME, info['error']['title']), expected=True)
|
||||
'%s said: %s' % (self.IE_NAME, title), expected=True)
|
||||
|
||||
def _get_subtitles(self, video_id, webpage):
|
||||
try:
|
||||
|
39
youtube_dl/extractor/etonline.py
Normal file
39
youtube_dl/extractor/etonline.py
Normal file
@ -0,0 +1,39 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
||||
|
||||
class ETOnlineIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?etonline\.com/(?:[^/]+/)*(?P<id>[^/?#&]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.etonline.com/tv/211130_dove_cameron_liv_and_maddie_emotional_episode_series_finale/',
|
||||
'info_dict': {
|
||||
'id': '211130_dove_cameron_liv_and_maddie_emotional_episode_series_finale',
|
||||
'title': 'md5:a21ec7d3872ed98335cbd2a046f34ee6',
|
||||
'description': 'md5:8b94484063f463cca709617c79618ccd',
|
||||
},
|
||||
'playlist_count': 2,
|
||||
}, {
|
||||
'url': 'http://www.etonline.com/media/video/here_are_the_stars_who_love_bringing_their_moms_as_dates_to_the_oscars-211359/',
|
||||
'only_matching': True,
|
||||
}]
|
||||
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/1242911076001/default_default/index.html?videoId=ref:%s'
|
||||
|
||||
def _real_extract(self, url):
|
||||
playlist_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, playlist_id)
|
||||
|
||||
entries = [
|
||||
self.url_result(
|
||||
self.BRIGHTCOVE_URL_TEMPLATE % video_id, 'BrightcoveNew', video_id)
|
||||
for video_id in re.findall(
|
||||
r'site\.brightcove\s*\([^,]+,\s*["\'](title_\d+)', webpage)]
|
||||
|
||||
return self.playlist_result(
|
||||
entries, playlist_id,
|
||||
self._og_search_title(webpage, fatal=False),
|
||||
self._og_search_description(webpage))
|
@ -288,6 +288,7 @@ from .espn import (
|
||||
ESPNArticleIE,
|
||||
)
|
||||
from .esri import EsriVideoIE
|
||||
from .etonline import ETOnlineIE
|
||||
from .europa import EuropaIE
|
||||
from .everyonesmixtape import EveryonesMixtapeIE
|
||||
from .expotv import ExpoTVIE
|
||||
@ -338,6 +339,7 @@ from .francetv import (
|
||||
)
|
||||
from .freesound import FreesoundIE
|
||||
from .freespeech import FreespeechIE
|
||||
from .freshlive import FreshLiveIE
|
||||
from .funimation import FunimationIE
|
||||
from .funnyordie import FunnyOrDieIE
|
||||
from .fusion import FusionIE
|
||||
@ -637,6 +639,7 @@ from .ninecninemedia import (
|
||||
from .ninegag import NineGagIE
|
||||
from .ninenow import NineNowIE
|
||||
from .nintendo import NintendoIE
|
||||
from .njpwworld import NJPWWorldIE
|
||||
from .nobelprize import NobelPrizeIE
|
||||
from .noco import NocoIE
|
||||
from .normalboots import NormalbootsIE
|
||||
@ -666,6 +669,7 @@ from .npo import (
|
||||
NPORadioIE,
|
||||
NPORadioFragmentIE,
|
||||
SchoolTVIE,
|
||||
HetKlokhuisIE,
|
||||
VPROIE,
|
||||
WNLIE,
|
||||
)
|
||||
@ -835,7 +839,6 @@ from .safari import (
|
||||
from .sapo import SapoIE
|
||||
from .savefrom import SaveFromIE
|
||||
from .sbs import SBSIE
|
||||
from .scivee import SciVeeIE
|
||||
from .screencast import ScreencastIE
|
||||
from .screencastomatic import ScreencastOMaticIE
|
||||
from .scrippsnetworks import ScrippsNetworksWatchIE
|
||||
@ -852,6 +855,7 @@ from .shared import (
|
||||
from .showroomlive import ShowRoomLiveIE
|
||||
from .sina import SinaIE
|
||||
from .sixplay import SixPlayIE
|
||||
from .skylinewebcams import SkylineWebcamsIE
|
||||
from .skynewsarabia import (
|
||||
SkyNewsArabiaIE,
|
||||
SkyNewsArabiaArticleIE,
|
||||
|
84
youtube_dl/extractor/freshlive.py
Normal file
84
youtube_dl/extractor/freshlive.py
Normal file
@ -0,0 +1,84 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_str
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
int_or_none,
|
||||
try_get,
|
||||
unified_timestamp,
|
||||
)
|
||||
|
||||
|
||||
class FreshLiveIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://freshlive\.tv/[^/]+/(?P<id>\d+)'
|
||||
_TEST = {
|
||||
'url': 'https://freshlive.tv/satotv/74712',
|
||||
'md5': '9f0cf5516979c4454ce982df3d97f352',
|
||||
'info_dict': {
|
||||
'id': '74712',
|
||||
'ext': 'mp4',
|
||||
'title': 'テスト',
|
||||
'description': 'テスト',
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
'duration': 1511,
|
||||
'timestamp': 1483619655,
|
||||
'upload_date': '20170105',
|
||||
'uploader': 'サトTV',
|
||||
'uploader_id': 'satotv',
|
||||
'view_count': int,
|
||||
'comment_count': int,
|
||||
'is_live': False,
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
options = self._parse_json(
|
||||
self._search_regex(
|
||||
r'window\.__CONTEXT__\s*=\s*({.+?});\s*</script>',
|
||||
webpage, 'initial context'),
|
||||
video_id)
|
||||
|
||||
info = options['context']['dispatcher']['stores']['ProgramStore']['programs'][video_id]
|
||||
|
||||
title = info['title']
|
||||
|
||||
if info.get('status') == 'upcoming':
|
||||
raise ExtractorError('Stream %s is upcoming' % video_id, expected=True)
|
||||
|
||||
stream_url = info.get('liveStreamUrl') or info['archiveStreamUrl']
|
||||
|
||||
is_live = info.get('liveStreamUrl') is not None
|
||||
|
||||
formats = self._extract_m3u8_formats(
|
||||
stream_url, video_id, ext='mp4',
|
||||
entry_protocol='m3u8' if is_live else 'm3u8_native',
|
||||
m3u8_id='hls')
|
||||
|
||||
if is_live:
|
||||
title = self._live_title(title)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'formats': formats,
|
||||
'title': title,
|
||||
'description': info.get('description'),
|
||||
'thumbnail': info.get('thumbnailUrl'),
|
||||
'duration': int_or_none(info.get('airTime')),
|
||||
'timestamp': unified_timestamp(info.get('createdAt')),
|
||||
'uploader': try_get(
|
||||
info, lambda x: x['channel']['title'], compat_str),
|
||||
'uploader_id': try_get(
|
||||
info, lambda x: x['channel']['code'], compat_str),
|
||||
'uploader_url': try_get(
|
||||
info, lambda x: x['channel']['permalink'], compat_str),
|
||||
'view_count': int_or_none(info.get('viewCount')),
|
||||
'comment_count': int_or_none(info.get('commentCount')),
|
||||
'tags': info.get('tags', []),
|
||||
'is_live': is_live,
|
||||
}
|
@ -37,7 +37,6 @@ class GoIE(AdobePassIE):
|
||||
}
|
||||
}
|
||||
_VALID_URL = r'https?://(?:(?P<sub_domain>%s)\.)?go\.com/(?:[^/]+/)*(?:vdka(?P<id>\w+)|season-\d+/\d+-(?P<display_id>[^/?#]+))' % '|'.join(_SITE_INFO.keys())
|
||||
_GEO_COUNTRIES = ['US']
|
||||
_TESTS = [{
|
||||
'url': 'http://abc.go.com/shows/castle/video/most-recent/vdka0_g86w5onx',
|
||||
'info_dict': {
|
||||
@ -79,44 +78,60 @@ class GoIE(AdobePassIE):
|
||||
ext = determine_ext(asset_url)
|
||||
if ext == 'm3u8':
|
||||
video_type = video_data.get('type')
|
||||
if video_type == 'lf':
|
||||
data = {
|
||||
'video_id': video_data['id'],
|
||||
'video_type': video_type,
|
||||
'brand': brand,
|
||||
'device': '001',
|
||||
}
|
||||
if video_data.get('accesslevel') == '1':
|
||||
requestor_id = site_info['requestor_id']
|
||||
resource = self._get_mvpd_resource(
|
||||
requestor_id, title, video_id, None)
|
||||
auth = self._extract_mvpd_auth(
|
||||
url, video_id, requestor_id, resource)
|
||||
data.update({
|
||||
'token': auth,
|
||||
'token_type': 'ap',
|
||||
'adobe_requestor_id': requestor_id,
|
||||
})
|
||||
entitlement = self._download_json(
|
||||
'https://api.entitlement.watchabc.go.com/vp2/ws-secure/entitlement/2020/authorize.json',
|
||||
video_id, data=urlencode_postdata(data), headers=self.geo_verification_headers())
|
||||
errors = entitlement.get('errors', {}).get('errors', [])
|
||||
if errors:
|
||||
for error in errors:
|
||||
if error.get('code') == 1002:
|
||||
self.raise_geo_restricted(
|
||||
error['message'], countries=self._GEO_COUNTRIES)
|
||||
error_message = ', '.join([error['message'] for error in errors])
|
||||
raise ExtractorError('%s said: %s' % (self.IE_NAME, error_message), expected=True)
|
||||
asset_url += '?' + entitlement['uplynkData']['sessionKey']
|
||||
data = {
|
||||
'video_id': video_data['id'],
|
||||
'video_type': video_type,
|
||||
'brand': brand,
|
||||
'device': '001',
|
||||
}
|
||||
if video_data.get('accesslevel') == '1':
|
||||
requestor_id = site_info['requestor_id']
|
||||
resource = self._get_mvpd_resource(
|
||||
requestor_id, title, video_id, None)
|
||||
auth = self._extract_mvpd_auth(
|
||||
url, video_id, requestor_id, resource)
|
||||
data.update({
|
||||
'token': auth,
|
||||
'token_type': 'ap',
|
||||
'adobe_requestor_id': requestor_id,
|
||||
})
|
||||
else:
|
||||
self._initialize_geo_bypass(['US'])
|
||||
entitlement = self._download_json(
|
||||
'https://api.entitlement.watchabc.go.com/vp2/ws-secure/entitlement/2020/authorize.json',
|
||||
video_id, data=urlencode_postdata(data), headers=self.geo_verification_headers())
|
||||
errors = entitlement.get('errors', {}).get('errors', [])
|
||||
if errors:
|
||||
for error in errors:
|
||||
if error.get('code') == 1002:
|
||||
self.raise_geo_restricted(
|
||||
error['message'], countries=['US'])
|
||||
error_message = ', '.join([error['message'] for error in errors])
|
||||
raise ExtractorError('%s said: %s' % (self.IE_NAME, error_message), expected=True)
|
||||
asset_url += '?' + entitlement['uplynkData']['sessionKey']
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
asset_url, video_id, 'mp4', m3u8_id=format_id or 'hls', fatal=False))
|
||||
else:
|
||||
formats.append({
|
||||
f = {
|
||||
'format_id': format_id,
|
||||
'url': asset_url,
|
||||
'ext': ext,
|
||||
})
|
||||
}
|
||||
if re.search(r'(?:/mp4/source/|_source\.mp4)', asset_url):
|
||||
f.update({
|
||||
'format_id': ('%s-' % format_id if format_id else '') + 'SOURCE',
|
||||
'preference': 1,
|
||||
})
|
||||
else:
|
||||
mobj = re.search(r'/(\d+)x(\d+)/', asset_url)
|
||||
if mobj:
|
||||
height = int(mobj.group(2))
|
||||
f.update({
|
||||
'format_id': ('%s-' % format_id if format_id else '') + '%dP' % height,
|
||||
'width': int(mobj.group(1)),
|
||||
'height': height,
|
||||
})
|
||||
formats.append(f)
|
||||
self._sort_formats(formats)
|
||||
|
||||
subtitles = {}
|
||||
|
@ -3,6 +3,7 @@ from __future__ import unicode_literals
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_str
|
||||
from ..utils import (
|
||||
get_element_by_attribute,
|
||||
int_or_none,
|
||||
@ -50,6 +51,33 @@ class InstagramIE(InfoExtractor):
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
# multi video post
|
||||
'url': 'https://www.instagram.com/p/BQ0eAlwhDrw/',
|
||||
'playlist': [{
|
||||
'info_dict': {
|
||||
'id': 'BQ0dSaohpPW',
|
||||
'ext': 'mp4',
|
||||
'title': 'Video 1',
|
||||
},
|
||||
}, {
|
||||
'info_dict': {
|
||||
'id': 'BQ0dTpOhuHT',
|
||||
'ext': 'mp4',
|
||||
'title': 'Video 2',
|
||||
},
|
||||
}, {
|
||||
'info_dict': {
|
||||
'id': 'BQ0dT7RBFeF',
|
||||
'ext': 'mp4',
|
||||
'title': 'Video 3',
|
||||
},
|
||||
}],
|
||||
'info_dict': {
|
||||
'id': 'BQ0eAlwhDrw',
|
||||
'title': 'Post by instagram',
|
||||
'description': 'md5:0f9203fc6a2ce4d228da5754bcf54957',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://instagram.com/p/-Cmh1cukG2/',
|
||||
'only_matching': True,
|
||||
@ -113,6 +141,32 @@ class InstagramIE(InfoExtractor):
|
||||
'timestamp': int_or_none(comment.get('created_at')),
|
||||
} for comment in media.get(
|
||||
'comments', {}).get('nodes', []) if comment.get('text')]
|
||||
if not video_url:
|
||||
edges = try_get(
|
||||
media, lambda x: x['edge_sidecar_to_children']['edges'],
|
||||
list) or []
|
||||
if edges:
|
||||
entries = []
|
||||
for edge_num, edge in enumerate(edges, start=1):
|
||||
node = try_get(edge, lambda x: x['node'], dict)
|
||||
if not node:
|
||||
continue
|
||||
node_video_url = try_get(node, lambda x: x['video_url'], compat_str)
|
||||
if not node_video_url:
|
||||
continue
|
||||
entries.append({
|
||||
'id': node.get('shortcode') or node['id'],
|
||||
'title': 'Video %d' % edge_num,
|
||||
'url': node_video_url,
|
||||
'thumbnail': node.get('display_url'),
|
||||
'width': int_or_none(try_get(node, lambda x: x['dimensions']['width'])),
|
||||
'height': int_or_none(try_get(node, lambda x: x['dimensions']['height'])),
|
||||
'view_count': int_or_none(node.get('video_view_count')),
|
||||
})
|
||||
return self.playlist_result(
|
||||
entries, video_id,
|
||||
'Post by %s' % uploader_id if uploader_id else None,
|
||||
description)
|
||||
|
||||
if not video_url:
|
||||
video_url = self._og_search_video_url(webpage, secure=False)
|
||||
|
@ -16,6 +16,8 @@ class IviIE(InfoExtractor):
|
||||
IE_DESC = 'ivi.ru'
|
||||
IE_NAME = 'ivi'
|
||||
_VALID_URL = r'https?://(?:www\.)?ivi\.ru/(?:watch/(?:[^/]+/)?|video/player\?.*?videoId=)(?P<id>\d+)'
|
||||
_GEO_BYPASS = False
|
||||
_GEO_COUNTRIES = ['RU']
|
||||
|
||||
_TESTS = [
|
||||
# Single movie
|
||||
@ -91,7 +93,11 @@ class IviIE(InfoExtractor):
|
||||
|
||||
if 'error' in video_json:
|
||||
error = video_json['error']
|
||||
if error['origin'] == 'NoRedisValidData':
|
||||
origin = error['origin']
|
||||
if origin == 'NotAllowedForLocation':
|
||||
self.raise_geo_restricted(
|
||||
msg=error['message'], countries=self._GEO_COUNTRIES)
|
||||
elif origin == 'NoRedisValidData':
|
||||
raise ExtractorError('Video %s does not exist' % video_id, expected=True)
|
||||
raise ExtractorError(
|
||||
'Unable to download video %s: %s' % (video_id, error['message']),
|
||||
|
@ -30,7 +30,7 @@ from ..utils import (
|
||||
class LeIE(InfoExtractor):
|
||||
IE_DESC = '乐视网'
|
||||
_VALID_URL = r'https?://(?:www\.le\.com/ptv/vplay|(?:sports\.le|(?:www\.)?lesports)\.com/(?:match|video))/(?P<id>\d+)\.html'
|
||||
|
||||
_GEO_COUNTRIES = ['CN']
|
||||
_URL_TEMPLATE = 'http://www.le.com/ptv/vplay/%s.html'
|
||||
|
||||
_TESTS = [{
|
||||
@ -126,10 +126,9 @@ class LeIE(InfoExtractor):
|
||||
if playstatus['status'] == 0:
|
||||
flag = playstatus['flag']
|
||||
if flag == 1:
|
||||
msg = 'Country %s auth error' % playstatus['country']
|
||||
self.raise_geo_restricted()
|
||||
else:
|
||||
msg = 'Generic error. flag = %d' % flag
|
||||
raise ExtractorError(msg, expected=True)
|
||||
raise ExtractorError('Generic error. flag = %d' % flag, expected=True)
|
||||
|
||||
def _real_extract(self, url):
|
||||
media_id = self._match_id(url)
|
||||
|
@ -4,11 +4,13 @@ from __future__ import unicode_literals
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_HTTPError
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
unsmuggle_url,
|
||||
ExtractorError,
|
||||
)
|
||||
|
||||
|
||||
@ -20,9 +22,17 @@ class LimelightBaseIE(InfoExtractor):
|
||||
headers = {}
|
||||
if referer:
|
||||
headers['Referer'] = referer
|
||||
return self._download_json(
|
||||
self._PLAYLIST_SERVICE_URL % (self._PLAYLIST_SERVICE_PATH, item_id, method),
|
||||
item_id, 'Downloading PlaylistService %s JSON' % method, fatal=fatal, headers=headers)
|
||||
try:
|
||||
return self._download_json(
|
||||
self._PLAYLIST_SERVICE_URL % (self._PLAYLIST_SERVICE_PATH, item_id, method),
|
||||
item_id, 'Downloading PlaylistService %s JSON' % method, fatal=fatal, headers=headers)
|
||||
except ExtractorError as e:
|
||||
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
|
||||
error = self._parse_json(e.cause.read().decode(), item_id)['detail']['contentAccessPermission']
|
||||
if error == 'CountryDisabled':
|
||||
self.raise_geo_restricted()
|
||||
raise ExtractorError(error, expected=True)
|
||||
raise
|
||||
|
||||
def _call_api(self, organization_id, item_id, method):
|
||||
return self._download_json(
|
||||
@ -213,6 +223,7 @@ class LimelightMediaIE(LimelightBaseIE):
|
||||
def _real_extract(self, url):
|
||||
url, smuggled_data = unsmuggle_url(url, {})
|
||||
video_id = self._match_id(url)
|
||||
self._initialize_geo_bypass(smuggled_data.get('geo_countries'))
|
||||
|
||||
pc, mobile, metadata = self._extract(
|
||||
video_id, 'getPlaylistByMediaId',
|
||||
|
@ -260,9 +260,24 @@ class LyndaCourseIE(LyndaBaseIE):
|
||||
course_path = mobj.group('coursepath')
|
||||
course_id = mobj.group('courseid')
|
||||
|
||||
item_template = 'https://www.lynda.com/%s/%%s-4.html' % course_path
|
||||
|
||||
course = self._download_json(
|
||||
'https://www.lynda.com/ajax/player?courseId=%s&type=course' % course_id,
|
||||
course_id, 'Downloading course JSON')
|
||||
course_id, 'Downloading course JSON', fatal=False)
|
||||
|
||||
if not course:
|
||||
webpage = self._download_webpage(url, course_id)
|
||||
entries = [
|
||||
self.url_result(
|
||||
item_template % video_id, ie=LyndaIE.ie_key(),
|
||||
video_id=video_id)
|
||||
for video_id in re.findall(
|
||||
r'data-video-id=["\'](\d+)', webpage)]
|
||||
return self.playlist_result(
|
||||
entries, course_id,
|
||||
self._og_search_title(webpage, fatal=False),
|
||||
self._og_search_description(webpage))
|
||||
|
||||
if course.get('Status') == 'NotFound':
|
||||
raise ExtractorError(
|
||||
@ -283,7 +298,7 @@ class LyndaCourseIE(LyndaBaseIE):
|
||||
if video_id:
|
||||
entries.append({
|
||||
'_type': 'url_transparent',
|
||||
'url': 'https://www.lynda.com/%s/%s-4.html' % (course_path, video_id),
|
||||
'url': item_template % video_id,
|
||||
'ie_key': LyndaIE.ie_key(),
|
||||
'chapter': chapter.get('Title'),
|
||||
'chapter_number': int_or_none(chapter.get('ChapterIndex')),
|
||||
|
@ -14,7 +14,7 @@ from ..utils import (
|
||||
|
||||
class MDRIE(InfoExtractor):
|
||||
IE_DESC = 'MDR.DE and KiKA'
|
||||
_VALID_URL = r'https?://(?:www\.)?(?:mdr|kika)\.de/(?:.*)/[a-z]+-?(?P<id>\d+)(?:_.+?)?\.html'
|
||||
_VALID_URL = r'https?://(?:www\.)?(?:mdr|kika)\.de/(?:.*)/[a-z-]+-?(?P<id>\d+)(?:_.+?)?\.html'
|
||||
|
||||
_TESTS = [{
|
||||
# MDR regularly deletes its videos
|
||||
@ -31,6 +31,7 @@ class MDRIE(InfoExtractor):
|
||||
'duration': 250,
|
||||
'uploader': 'MITTELDEUTSCHER RUNDFUNK',
|
||||
},
|
||||
'skip': '404 not found',
|
||||
}, {
|
||||
'url': 'http://www.kika.de/baumhaus/videos/video19636.html',
|
||||
'md5': '4930515e36b06c111213e80d1e4aad0e',
|
||||
@ -41,6 +42,7 @@ class MDRIE(InfoExtractor):
|
||||
'duration': 134,
|
||||
'uploader': 'KIKA',
|
||||
},
|
||||
'skip': '404 not found',
|
||||
}, {
|
||||
'url': 'http://www.kika.de/sendungen/einzelsendungen/weihnachtsprogramm/videos/video8182.html',
|
||||
'md5': '5fe9c4dd7d71e3b238f04b8fdd588357',
|
||||
@ -49,11 +51,21 @@ class MDRIE(InfoExtractor):
|
||||
'ext': 'mp4',
|
||||
'title': 'Beutolomäus und der geheime Weihnachtswunsch',
|
||||
'description': 'md5:b69d32d7b2c55cbe86945ab309d39bbd',
|
||||
'timestamp': 1450950000,
|
||||
'upload_date': '20151224',
|
||||
'timestamp': 1482541200,
|
||||
'upload_date': '20161224',
|
||||
'duration': 4628,
|
||||
'uploader': 'KIKA',
|
||||
},
|
||||
}, {
|
||||
# audio with alternative playerURL pattern
|
||||
'url': 'http://www.mdr.de/kultur/videos-und-audios/audio-radio/operation-mindfuck-robert-wilson100.html',
|
||||
'info_dict': {
|
||||
'id': '100',
|
||||
'ext': 'mp4',
|
||||
'title': 'Feature: Operation Mindfuck - Robert Anton Wilson',
|
||||
'duration': 3239,
|
||||
'uploader': 'MITTELDEUTSCHER RUNDFUNK',
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.kika.de/baumhaus/sendungen/video19636_zc-fea7f8a0_zs-4bf89c60.html',
|
||||
'only_matching': True,
|
||||
@ -71,7 +83,7 @@ class MDRIE(InfoExtractor):
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
data_url = self._search_regex(
|
||||
r'(?:dataURL|playerXml(?:["\'])?)\s*:\s*(["\'])(?P<url>.+/(?:video|audio)-?[0-9]+-avCustom\.xml)\1',
|
||||
r'(?:dataURL|playerXml(?:["\'])?)\s*:\s*(["\'])(?P<url>.+?-avCustom\.xml)\1',
|
||||
webpage, 'data url', group='url').replace(r'\/', '/')
|
||||
|
||||
doc = self._download_xml(
|
||||
|
@ -2,16 +2,17 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_str
|
||||
from ..utils import int_or_none
|
||||
|
||||
|
||||
class MGTVIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?mgtv\.com/v/(?:[^/]+/)*(?P<id>\d+)\.html'
|
||||
_VALID_URL = r'https?://(?:www\.)?mgtv\.com/(v|b)/(?:[^/]+/)*(?P<id>\d+)\.html'
|
||||
IE_DESC = '芒果TV'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://www.mgtv.com/v/1/290525/f/3116640.html',
|
||||
'md5': '1bdadcf760a0b90946ca68ee9a2db41a',
|
||||
'md5': 'b1ffc0fc163152acf6beaa81832c9ee7',
|
||||
'info_dict': {
|
||||
'id': '3116640',
|
||||
'ext': 'mp4',
|
||||
@ -21,48 +22,45 @@ class MGTVIE(InfoExtractor):
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
},
|
||||
}, {
|
||||
# no tbr extracted from stream_url
|
||||
'url': 'http://www.mgtv.com/v/1/1/f/3324755.html',
|
||||
'url': 'http://www.mgtv.com/b/301817/3826653.html',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
api_data = self._download_json(
|
||||
'http://v.api.mgtv.com/player/video', video_id,
|
||||
'http://pcweb.api.mgtv.com/player/video', video_id,
|
||||
query={'video_id': video_id},
|
||||
headers=self.geo_verification_headers())['data']
|
||||
info = api_data['info']
|
||||
title = info['title'].strip()
|
||||
stream_domain = api_data['stream_domain'][0]
|
||||
|
||||
formats = []
|
||||
for idx, stream in enumerate(api_data['stream']):
|
||||
stream_url = stream.get('url')
|
||||
if not stream_url:
|
||||
stream_path = stream.get('url')
|
||||
if not stream_path:
|
||||
continue
|
||||
format_data = self._download_json(
|
||||
stream_domain + stream_path, video_id,
|
||||
note='Download video info for format #%d' % idx)
|
||||
format_url = format_data.get('info')
|
||||
if not format_url:
|
||||
continue
|
||||
tbr = int_or_none(self._search_regex(
|
||||
r'(\d+)\.mp4', stream_url, 'tbr', default=None))
|
||||
|
||||
def extract_format(stream_url, format_id, idx, query={}):
|
||||
format_info = self._download_json(
|
||||
stream_url, video_id,
|
||||
note='Download video info for format %s' % (format_id or '#%d' % idx),
|
||||
query=query)
|
||||
return {
|
||||
'format_id': format_id,
|
||||
'url': format_info['info'],
|
||||
'ext': 'mp4',
|
||||
'tbr': tbr,
|
||||
}
|
||||
|
||||
formats.append(extract_format(
|
||||
stream_url, 'hls-%d' % tbr if tbr else None, idx * 2))
|
||||
formats.append(extract_format(stream_url.replace(
|
||||
'/playlist.m3u8', ''), 'http-%d' % tbr if tbr else None, idx * 2 + 1, {'pno': 1031}))
|
||||
r'_(\d+)_mp4/', format_url, 'tbr', default=None))
|
||||
formats.append({
|
||||
'format_id': compat_str(tbr or idx),
|
||||
'url': format_url,
|
||||
'ext': 'mp4',
|
||||
'tbr': tbr,
|
||||
'protocol': 'm3u8_native',
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': info['title'].strip(),
|
||||
'title': title,
|
||||
'formats': formats,
|
||||
'description': info.get('desc'),
|
||||
'duration': int_or_none(info.get('duration')),
|
||||
|
83
youtube_dl/extractor/njpwworld.py
Normal file
83
youtube_dl/extractor/njpwworld.py
Normal file
@ -0,0 +1,83 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_urlparse
|
||||
from ..utils import (
|
||||
get_element_by_class,
|
||||
urlencode_postdata,
|
||||
)
|
||||
|
||||
|
||||
class NJPWWorldIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://njpwworld\.com/p/(?P<id>[a-z0-9_]+)'
|
||||
IE_DESC = '新日本プロレスワールド'
|
||||
_NETRC_MACHINE = 'njpwworld'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://njpwworld.com/p/s_series_00155_1_9/',
|
||||
'info_dict': {
|
||||
'id': 's_series_00155_1_9',
|
||||
'ext': 'mp4',
|
||||
'title': '第9試合 ランディ・サベージ vs リック・スタイナー',
|
||||
'tags': list,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True, # AES-encrypted m3u8
|
||||
},
|
||||
'skip': 'Requires login',
|
||||
}
|
||||
|
||||
def _real_initialize(self):
|
||||
self._login()
|
||||
|
||||
def _login(self):
|
||||
username, password = self._get_login_info()
|
||||
# No authentication to be performed
|
||||
if not username:
|
||||
return True
|
||||
|
||||
webpage, urlh = self._download_webpage_handle(
|
||||
'https://njpwworld.com/auth/login', None,
|
||||
note='Logging in', errnote='Unable to login',
|
||||
data=urlencode_postdata({'login_id': username, 'pw': password}))
|
||||
# /auth/login will return 302 for successful logins
|
||||
if urlh.geturl() == 'https://njpwworld.com/auth/login':
|
||||
self.report_warning('unable to login')
|
||||
return False
|
||||
|
||||
return True
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
formats = []
|
||||
for player_url, kind in re.findall(r'<a[^>]+href="(/player[^"]+)".+?<img[^>]+src="[^"]+qf_btn_([^".]+)', webpage):
|
||||
player_url = compat_urlparse.urljoin(url, player_url)
|
||||
|
||||
player_page = self._download_webpage(
|
||||
player_url, video_id, note='Downloading player page')
|
||||
|
||||
entries = self._parse_html5_media_entries(
|
||||
player_url, player_page, video_id, m3u8_id='hls-%s' % kind,
|
||||
m3u8_entry_protocol='m3u8_native',
|
||||
preference=2 if 'hq' in kind else 1)
|
||||
formats.extend(entries[0]['formats'])
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
post_content = get_element_by_class('post-content', webpage)
|
||||
tags = re.findall(
|
||||
r'<li[^>]+class="tag-[^"]+"><a[^>]*>([^<]+)</a></li>', post_content
|
||||
) if post_content else None
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': self._og_search_title(webpage),
|
||||
'formats': formats,
|
||||
'tags': tags,
|
||||
}
|
@ -23,7 +23,7 @@ from ..utils import (
|
||||
|
||||
class NocoIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:(?:www\.)?noco\.tv/emission/|player\.noco\.tv/\?idvideo=)(?P<id>\d+)'
|
||||
_LOGIN_URL = 'http://noco.tv/do.php'
|
||||
_LOGIN_URL = 'https://noco.tv/do.php'
|
||||
_API_URL_TEMPLATE = 'https://api.noco.tv/1.1/%s?ts=%s&tk=%s'
|
||||
_SUB_LANG_TEMPLATE = '&sub_lang=%s'
|
||||
_NETRC_MACHINE = 'noco'
|
||||
@ -69,16 +69,17 @@ class NocoIE(InfoExtractor):
|
||||
if username is None:
|
||||
return
|
||||
|
||||
login_form = {
|
||||
'a': 'login',
|
||||
'cookie': '1',
|
||||
'username': username,
|
||||
'password': password,
|
||||
}
|
||||
request = sanitized_Request(self._LOGIN_URL, urlencode_postdata(login_form))
|
||||
request.add_header('Content-Type', 'application/x-www-form-urlencoded; charset=UTF-8')
|
||||
|
||||
login = self._download_json(request, None, 'Logging in as %s' % username)
|
||||
login = self._download_json(
|
||||
self._LOGIN_URL, None, 'Logging in as %s' % username,
|
||||
data=urlencode_postdata({
|
||||
'a': 'login',
|
||||
'cookie': '1',
|
||||
'username': username,
|
||||
'password': password,
|
||||
}),
|
||||
headers={
|
||||
'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
|
||||
})
|
||||
|
||||
if 'erreur' in login:
|
||||
raise ExtractorError('Unable to login: %s' % clean_html(login['erreur']), expected=True)
|
||||
|
@ -51,7 +51,8 @@ class NPOIE(NPOBaseIE):
|
||||
(?:
|
||||
npo\.nl/(?!live|radio)(?:[^/]+/){2}|
|
||||
ntr\.nl/(?:[^/]+/){2,}|
|
||||
omroepwnl\.nl/video/fragment/[^/]+__
|
||||
omroepwnl\.nl/video/fragment/[^/]+__|
|
||||
zapp\.nl/[^/]+/[^/]+/
|
||||
)
|
||||
)
|
||||
(?P<id>[^/?#]+)
|
||||
@ -140,6 +141,18 @@ class NPOIE(NPOBaseIE):
|
||||
'upload_date': '20150508',
|
||||
'duration': 462,
|
||||
},
|
||||
},
|
||||
{
|
||||
'url': 'http://www.zapp.nl/de-bzt-show/gemist/KN_1687547',
|
||||
'only_matching': True,
|
||||
},
|
||||
{
|
||||
'url': 'http://www.zapp.nl/de-bzt-show/filmpjes/POMS_KN_7315118',
|
||||
'only_matching': True,
|
||||
},
|
||||
{
|
||||
'url': 'http://www.zapp.nl/beste-vrienden-quiz/extra-video-s/WO_NTR_1067990',
|
||||
'only_matching': True,
|
||||
}
|
||||
]
|
||||
|
||||
@ -416,7 +429,21 @@ class NPORadioFragmentIE(InfoExtractor):
|
||||
}
|
||||
|
||||
|
||||
class SchoolTVIE(InfoExtractor):
|
||||
class NPODataMidEmbedIE(InfoExtractor):
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
video_id = self._search_regex(
|
||||
r'data-mid=(["\'])(?P<id>(?:(?!\1).)+)\1', webpage, 'video_id', group='id')
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'ie_key': 'NPO',
|
||||
'url': 'npo:%s' % video_id,
|
||||
'display_id': display_id
|
||||
}
|
||||
|
||||
|
||||
class SchoolTVIE(NPODataMidEmbedIE):
|
||||
IE_NAME = 'schooltv'
|
||||
_VALID_URL = r'https?://(?:www\.)?schooltv\.nl/video/(?P<id>[^/?#&]+)'
|
||||
|
||||
@ -435,17 +462,25 @@ class SchoolTVIE(InfoExtractor):
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
video_id = self._search_regex(
|
||||
r'data-mid=(["\'])(?P<id>(?:(?!\1).)+)\1', webpage, 'video_id', group='id')
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'ie_key': 'NPO',
|
||||
'url': 'npo:%s' % video_id,
|
||||
'display_id': display_id
|
||||
|
||||
class HetKlokhuisIE(NPODataMidEmbedIE):
|
||||
IE_NAME = 'hetklokhuis'
|
||||
_VALID_URL = r'https?://(?:www\.)?hetklokhuis.nl/[^/]+/\d+/(?P<id>[^/?#&]+)'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://hetklokhuis.nl/tv-uitzending/3471/Zwaartekrachtsgolven',
|
||||
'info_dict': {
|
||||
'id': 'VPWON_1260528',
|
||||
'display_id': 'Zwaartekrachtsgolven',
|
||||
'ext': 'm4v',
|
||||
'title': 'Het Klokhuis: Zwaartekrachtsgolven',
|
||||
'description': 'md5:c94f31fb930d76c2efa4a4a71651dd48',
|
||||
'upload_date': '20170223',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
class NPOPlaylistBaseIE(NPOIE):
|
||||
|
@ -72,16 +72,21 @@ class OpenloadIE(InfoExtractor):
|
||||
raise ExtractorError('File not found', expected=True)
|
||||
|
||||
ol_id = self._search_regex(
|
||||
'<span[^>]+id="[^"]+"[^>]*>([0-9]+)</span>',
|
||||
'<span[^>]+id="[^"]+"[^>]*>([0-9A-Za-z]+)</span>',
|
||||
webpage, 'openload ID')
|
||||
|
||||
first_two_chars = int(float(ol_id[0:][:2]))
|
||||
first_char = int(ol_id[0])
|
||||
urlcode = []
|
||||
num = 2
|
||||
num = 1
|
||||
|
||||
while num < len(ol_id):
|
||||
key = int(float(ol_id[num + 3:][:2]))
|
||||
urlcode.append((key, compat_chr(int(float(ol_id[num:][:3])) - first_two_chars)))
|
||||
i = ord(ol_id[num])
|
||||
key = 0
|
||||
if i <= 90:
|
||||
key = i - 65
|
||||
elif i >= 97:
|
||||
key = 25 + i - 97
|
||||
urlcode.append((key, compat_chr(int(ol_id[num + 2:num + 5]) // int(ol_id[num + 1]) - first_char)))
|
||||
num += 5
|
||||
|
||||
video_url = 'https://openload.co/stream/' + ''.join(
|
||||
|
@ -1,57 +0,0 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import int_or_none
|
||||
|
||||
|
||||
class SciVeeIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?scivee\.tv/node/(?P<id>\d+)'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://www.scivee.tv/node/62352',
|
||||
'md5': 'b16699b74c9e6a120f6772a44960304f',
|
||||
'info_dict': {
|
||||
'id': '62352',
|
||||
'ext': 'mp4',
|
||||
'title': 'Adam Arkin at the 2014 DOE JGI Genomics of Energy & Environment Meeting',
|
||||
'description': 'md5:81f1710638e11a481358fab1b11059d7',
|
||||
},
|
||||
'skip': 'Not accessible from Travis CI server',
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
|
||||
# annotations XML is malformed
|
||||
annotations = self._download_webpage(
|
||||
'http://www.scivee.tv/assets/annotations/%s' % video_id, video_id, 'Downloading annotations')
|
||||
|
||||
title = self._html_search_regex(r'<title>([^<]+)</title>', annotations, 'title')
|
||||
description = self._html_search_regex(r'<abstract>([^<]+)</abstract>', annotations, 'abstract', fatal=False)
|
||||
filesize = int_or_none(self._html_search_regex(
|
||||
r'<filesize>([^<]+)</filesize>', annotations, 'filesize', fatal=False))
|
||||
|
||||
formats = [
|
||||
{
|
||||
'url': 'http://www.scivee.tv/assets/audio/%s' % video_id,
|
||||
'ext': 'mp3',
|
||||
'format_id': 'audio',
|
||||
},
|
||||
{
|
||||
'url': 'http://www.scivee.tv/assets/video/%s' % video_id,
|
||||
'ext': 'mp4',
|
||||
'format_id': 'video',
|
||||
'filesize': filesize,
|
||||
},
|
||||
]
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'thumbnail': 'http://www.scivee.tv/assets/videothumb/%s' % video_id,
|
||||
'formats': formats,
|
||||
}
|
42
youtube_dl/extractor/skylinewebcams.py
Normal file
42
youtube_dl/extractor/skylinewebcams.py
Normal file
@ -0,0 +1,42 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
||||
|
||||
class SkylineWebcamsIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?skylinewebcams\.com/[^/]+/webcam/(?:[^/]+/)+(?P<id>[^/]+)\.html'
|
||||
_TEST = {
|
||||
'url': 'https://www.skylinewebcams.com/it/webcam/italia/lazio/roma/scalinata-piazza-di-spagna-barcaccia.html',
|
||||
'info_dict': {
|
||||
'id': 'scalinata-piazza-di-spagna-barcaccia',
|
||||
'ext': 'mp4',
|
||||
'title': 're:^Live Webcam Scalinata di Piazza di Spagna - La Barcaccia [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
|
||||
'description': 'Roma, veduta sulla Scalinata di Piazza di Spagna e sulla Barcaccia',
|
||||
'is_live': True,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
stream_url = self._search_regex(
|
||||
r'url\s*:\s*(["\'])(?P<url>(?:https?:)?//.+?\.m3u8.*?)\1', webpage,
|
||||
'stream url', group='url')
|
||||
|
||||
title = self._og_search_title(webpage)
|
||||
description = self._og_search_description(webpage)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'url': stream_url,
|
||||
'ext': 'mp4',
|
||||
'title': self._live_title(title),
|
||||
'description': description,
|
||||
'is_live': True,
|
||||
}
|
@ -108,12 +108,11 @@ class SohuIE(InfoExtractor):
|
||||
if vid_data['play'] != 1:
|
||||
if vid_data.get('status') == 12:
|
||||
raise ExtractorError(
|
||||
'Sohu said: There\'s something wrong in the video.',
|
||||
'%s said: There\'s something wrong in the video.' % self.IE_NAME,
|
||||
expected=True)
|
||||
else:
|
||||
raise ExtractorError(
|
||||
'Sohu said: The video is only licensed to users in Mainland China.',
|
||||
expected=True)
|
||||
self.raise_geo_restricted(
|
||||
'%s said: The video is only licensed to users in Mainland China.' % self.IE_NAME)
|
||||
|
||||
formats_json = {}
|
||||
for format_id in ('nor', 'high', 'super', 'ori', 'h2644k', 'h2654k'):
|
||||
|
@ -2,7 +2,10 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import int_or_none
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
smuggle_url,
|
||||
)
|
||||
|
||||
|
||||
class TeleQuebecIE(InfoExtractor):
|
||||
@ -28,7 +31,7 @@ class TeleQuebecIE(InfoExtractor):
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'id': media_id,
|
||||
'url': 'limelight:media:' + media_data['streamInfo']['sourceId'],
|
||||
'url': smuggle_url('limelight:media:' + media_data['streamInfo']['sourceId'], {'geo_countries': ['CA']}),
|
||||
'title': media_data['title'],
|
||||
'description': media_data.get('descriptions', [{'text': None}])[0].get('text'),
|
||||
'duration': int_or_none(media_data.get('durationInMilliseconds'), 1000),
|
||||
|
@ -8,10 +8,12 @@ from ..utils import (
|
||||
HEADRequest,
|
||||
ExtractorError,
|
||||
int_or_none,
|
||||
clean_html,
|
||||
)
|
||||
|
||||
|
||||
class TFOIE(InfoExtractor):
|
||||
_GEO_COUNTRIES = ['CA']
|
||||
_VALID_URL = r'https?://(?:www\.)?tfo\.org/(?:en|fr)/(?:[^/]+/){2}(?P<id>\d+)'
|
||||
_TEST = {
|
||||
'url': 'http://www.tfo.org/en/universe/tfo-247/100463871/video-game-hackathon',
|
||||
@ -36,7 +38,9 @@ class TFOIE(InfoExtractor):
|
||||
'X-tfo-session': self._get_cookies('http://www.tfo.org/')['tfo-session'].value,
|
||||
})
|
||||
if infos.get('success') == 0:
|
||||
raise ExtractorError('%s said: %s' % (self.IE_NAME, infos['msg']), expected=True)
|
||||
if infos.get('code') == 'ErrGeoBlocked':
|
||||
self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
|
||||
raise ExtractorError('%s said: %s' % (self.IE_NAME, clean_html(infos['msg'])), expected=True)
|
||||
video_data = infos['data']
|
||||
|
||||
return {
|
||||
|
@ -3,7 +3,10 @@ from __future__ import unicode_literals
|
||||
from .common import InfoExtractor
|
||||
|
||||
from ..compat import compat_urlparse
|
||||
from ..utils import qualities
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
qualities,
|
||||
)
|
||||
|
||||
|
||||
class TheSceneIE(InfoExtractor):
|
||||
@ -16,6 +19,11 @@ class TheSceneIE(InfoExtractor):
|
||||
'ext': 'mp4',
|
||||
'title': 'Narciso Rodriguez: Spring 2013 Ready-to-Wear',
|
||||
'display_id': 'narciso-rodriguez-spring-2013-ready-to-wear',
|
||||
'duration': 127,
|
||||
'series': 'Style.com Fashion Shows',
|
||||
'season': 'Ready To Wear Spring 2013',
|
||||
'tags': list,
|
||||
'categories': list,
|
||||
},
|
||||
}
|
||||
|
||||
@ -32,21 +40,29 @@ class TheSceneIE(InfoExtractor):
|
||||
player = self._download_webpage(player_url, display_id)
|
||||
info = self._parse_json(
|
||||
self._search_regex(
|
||||
r'(?m)var\s+video\s+=\s+({.+?});$', player, 'info json'),
|
||||
r'(?m)video\s*:\s*({.+?}),$', player, 'info json'),
|
||||
display_id)
|
||||
|
||||
video_id = info['id']
|
||||
title = info['title']
|
||||
|
||||
qualities_order = qualities(('low', 'high'))
|
||||
formats = [{
|
||||
'format_id': '{0}-{1}'.format(f['type'].split('/')[0], f['quality']),
|
||||
'url': f['src'],
|
||||
'quality': qualities_order(f['quality']),
|
||||
} for f in info['sources'][0]]
|
||||
} for f in info['sources']]
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': info['id'],
|
||||
'id': video_id,
|
||||
'display_id': display_id,
|
||||
'title': info['title'],
|
||||
'title': title,
|
||||
'formats': formats,
|
||||
'thumbnail': info.get('poster_frame'),
|
||||
'duration': int_or_none(info.get('duration')),
|
||||
'series': info.get('series_title'),
|
||||
'season': info.get('season_title'),
|
||||
'tags': info.get('tags'),
|
||||
'categories': info.get('categories'),
|
||||
}
|
||||
|
@ -16,6 +16,7 @@ class TubiTvIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?tubitv\.com/video/(?P<id>[0-9]+)'
|
||||
_LOGIN_URL = 'http://tubitv.com/login'
|
||||
_NETRC_MACHINE = 'tubitv'
|
||||
_GEO_COUNTRIES = ['US']
|
||||
_TEST = {
|
||||
'url': 'http://tubitv.com/video/283829/the_comedian_at_the_friday',
|
||||
'md5': '43ac06be9326f41912dc64ccf7a80320',
|
||||
|
@ -17,6 +17,9 @@ class TvigleIE(InfoExtractor):
|
||||
IE_DESC = 'Интернет-телевидение Tvigle.ru'
|
||||
_VALID_URL = r'https?://(?:www\.)?(?:tvigle\.ru/(?:[^/]+/)+(?P<display_id>[^/]+)/$|cloud\.tvigle\.ru/video/(?P<id>\d+))'
|
||||
|
||||
_GEO_BYPASS = False
|
||||
_GEO_COUNTRIES = ['RU']
|
||||
|
||||
_TESTS = [
|
||||
{
|
||||
'url': 'http://www.tvigle.ru/video/sokrat/',
|
||||
@ -72,8 +75,13 @@ class TvigleIE(InfoExtractor):
|
||||
|
||||
error_message = item.get('errorMessage')
|
||||
if not videos and error_message:
|
||||
raise ExtractorError(
|
||||
'%s returned error: %s' % (self.IE_NAME, error_message), expected=True)
|
||||
if item.get('isGeoBlocked') is True:
|
||||
self.raise_geo_restricted(
|
||||
msg=error_message, countries=self._GEO_COUNTRIES)
|
||||
else:
|
||||
raise ExtractorError(
|
||||
'%s returned error: %s' % (self.IE_NAME, error_message),
|
||||
expected=True)
|
||||
|
||||
title = item['title']
|
||||
description = item.get('description')
|
||||
|
@ -12,7 +12,7 @@ from ..utils import (
|
||||
|
||||
class TwentyFourVideoIE(InfoExtractor):
|
||||
IE_NAME = '24video'
|
||||
_VALID_URL = r'https?://(?:www\.)?24video\.(?:net|me|xxx|sex)/(?:video/(?:view|xml)/|player/new24_play\.swf\?id=)(?P<id>\d+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?24video\.(?:net|me|xxx|sex|tube)/(?:video/(?:view|xml)/|player/new24_play\.swf\?id=)(?P<id>\d+)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://www.24video.net/video/view/1044982',
|
||||
@ -37,6 +37,9 @@ class TwentyFourVideoIE(InfoExtractor):
|
||||
}, {
|
||||
'url': 'http://www.24video.me/video/view/1044982',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.24video.tube/video/view/2363750',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
@ -17,12 +17,12 @@ from ..utils import (
|
||||
|
||||
|
||||
class VevoBaseIE(InfoExtractor):
|
||||
def _extract_json(self, webpage, video_id, item):
|
||||
def _extract_json(self, webpage, video_id):
|
||||
return self._parse_json(
|
||||
self._search_regex(
|
||||
r'window\.__INITIAL_STORE__\s*=\s*({.+?});\s*</script>',
|
||||
webpage, 'initial store'),
|
||||
video_id)['default'][item]
|
||||
video_id)
|
||||
|
||||
|
||||
class VevoIE(VevoBaseIE):
|
||||
@ -139,6 +139,11 @@ class VevoIE(VevoBaseIE):
|
||||
# no genres available
|
||||
'url': 'http://www.vevo.com/watch/INS171400764',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# Another case available only via the webpage; using streams/streamsV3 formats
|
||||
# Geo-restricted to Netherlands/Germany
|
||||
'url': 'http://www.vevo.com/watch/boostee/pop-corn-clip-officiel/FR1A91600909',
|
||||
'only_matching': True,
|
||||
}]
|
||||
_VERSIONS = {
|
||||
0: 'youtube', # only in AuthenticateVideo videoVersions
|
||||
@ -193,7 +198,14 @@ class VevoIE(VevoBaseIE):
|
||||
# https://github.com/rg3/youtube-dl/issues/9366)
|
||||
if not video_versions:
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
video_versions = self._extract_json(webpage, video_id, 'streams')[video_id][0]
|
||||
json_data = self._extract_json(webpage, video_id)
|
||||
if 'streams' in json_data.get('default', {}):
|
||||
video_versions = json_data['default']['streams'][video_id][0]
|
||||
else:
|
||||
video_versions = [
|
||||
value
|
||||
for key, value in json_data['apollo']['data'].items()
|
||||
if key.startswith('%s.streams' % video_id)]
|
||||
|
||||
uploader = None
|
||||
artist = None
|
||||
@ -207,7 +219,7 @@ class VevoIE(VevoBaseIE):
|
||||
|
||||
formats = []
|
||||
for video_version in video_versions:
|
||||
version = self._VERSIONS.get(video_version['version'])
|
||||
version = self._VERSIONS.get(video_version.get('version'), 'generic')
|
||||
version_url = video_version.get('url')
|
||||
if not version_url:
|
||||
continue
|
||||
@ -339,7 +351,7 @@ class VevoPlaylistIE(VevoBaseIE):
|
||||
if video_id:
|
||||
return self.url_result('vevo:%s' % video_id, VevoIE.ie_key())
|
||||
|
||||
playlists = self._extract_json(webpage, playlist_id, '%ss' % playlist_kind)
|
||||
playlists = self._extract_json(webpage, playlist_id)['default']['%ss' % playlist_kind]
|
||||
|
||||
playlist = (list(playlists.values())[0]
|
||||
if playlist_kind == 'playlist' else playlists[playlist_id])
|
||||
|
@ -13,7 +13,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class VidziIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?vidzi\.tv/(?:embed-)?(?P<id>[0-9a-zA-Z]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?vidzi\.(?:tv|cc)/(?:embed-)?(?P<id>[0-9a-zA-Z]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://vidzi.tv/cghql9yq6emu.html',
|
||||
'md5': '4f16c71ca0c8c8635ab6932b5f3f1660',
|
||||
@ -29,6 +29,9 @@ class VidziIE(InfoExtractor):
|
||||
}, {
|
||||
'url': 'http://vidzi.tv/embed-4z2yb0rzphe9-600x338.html',
|
||||
'skip_download': True,
|
||||
}, {
|
||||
'url': 'http://vidzi.cc/cghql9yq6emu.html',
|
||||
'skip_download': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
@ -86,7 +86,9 @@ class ViewsterIE(InfoExtractor):
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
# Get 'api_token' cookie
|
||||
self._request_webpage(HEADRequest('http://www.viewster.com/'), video_id)
|
||||
self._request_webpage(
|
||||
HEADRequest('http://www.viewster.com/'),
|
||||
video_id, headers=self.geo_verification_headers())
|
||||
cookies = self._get_cookies('http://www.viewster.com/')
|
||||
self._AUTH_TOKEN = compat_urllib_parse_unquote(cookies['api_token'].value)
|
||||
|
||||
|
@ -5,6 +5,7 @@ import re
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
dict_get,
|
||||
ExtractorError,
|
||||
int_or_none,
|
||||
parse_duration,
|
||||
unified_strdate,
|
||||
@ -57,6 +58,10 @@ class XHamsterIE(InfoExtractor):
|
||||
}, {
|
||||
'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# This video is visible for marcoalfa123456's friends only
|
||||
'url': 'https://it.xhamster.com/movies/7263980/la_mia_vicina.html',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
@ -78,6 +83,12 @@ class XHamsterIE(InfoExtractor):
|
||||
mrss_url = '%s://xhamster.com/movies/%s/%s.html' % (proto, video_id, seo)
|
||||
webpage = self._download_webpage(mrss_url, video_id)
|
||||
|
||||
error = self._html_search_regex(
|
||||
r'<div[^>]+id=["\']videoClosed["\'][^>]*>(.+?)</div>',
|
||||
webpage, 'error', default=None)
|
||||
if error:
|
||||
raise ExtractorError(error, expected=True)
|
||||
|
||||
title = self._html_search_regex(
|
||||
[r'<h1[^>]*>([^<]+)</h1>',
|
||||
r'<meta[^>]+itemprop=".*?caption.*?"[^>]+content="(.+?)"',
|
||||
|
@ -47,7 +47,6 @@ from ..utils import (
|
||||
unsmuggle_url,
|
||||
uppercase_escape,
|
||||
urlencode_postdata,
|
||||
ISO3166Utils,
|
||||
)
|
||||
|
||||
|
||||
@ -371,6 +370,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
}
|
||||
_SUBTITLE_FORMATS = ('ttml', 'vtt')
|
||||
|
||||
_GEO_BYPASS = False
|
||||
|
||||
IE_NAME = 'youtube'
|
||||
_TESTS = [
|
||||
{
|
||||
@ -917,7 +918,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
# itag 212
|
||||
'url': '1t24XAntNCY',
|
||||
'only_matching': True,
|
||||
}
|
||||
},
|
||||
{
|
||||
# geo restricted to JP
|
||||
'url': 'sJL6WA-aGkQ',
|
||||
'only_matching': True,
|
||||
},
|
||||
]
|
||||
|
||||
def __init__(self, *args, **kwargs):
|
||||
@ -1376,11 +1382,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
if 'token' not in video_info:
|
||||
if 'reason' in video_info:
|
||||
if 'The uploader has not made this video available in your country.' in video_info['reason']:
|
||||
regions_allowed = self._html_search_meta('regionsAllowed', video_webpage, default=None)
|
||||
if regions_allowed:
|
||||
raise ExtractorError('YouTube said: This video is available in %s only' % (
|
||||
', '.join(map(ISO3166Utils.short2full, regions_allowed.split(',')))),
|
||||
expected=True)
|
||||
regions_allowed = self._html_search_meta(
|
||||
'regionsAllowed', video_webpage, default=None)
|
||||
countries = regions_allowed.split(',') if regions_allowed else None
|
||||
self.raise_geo_restricted(
|
||||
msg=video_info['reason'][0], countries=countries)
|
||||
raise ExtractorError(
|
||||
'YouTube said: %s' % video_info['reason'][0],
|
||||
expected=True, video_id=video_id)
|
||||
@ -2226,7 +2232,7 @@ class YoutubeUserIE(YoutubeChannelIE):
|
||||
'url': 'https://www.youtube.com/gametrailers',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# This channel is not available.
|
||||
# This channel is not available, geo restricted to JP
|
||||
'url': 'https://www.youtube.com/user/kananishinoSMEJ/videos',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
@ -679,8 +679,8 @@ def parseOpts(overrideArguments=None):
|
||||
help=('Output filename template, see the "OUTPUT TEMPLATE" for all the info'))
|
||||
filesystem.add_option(
|
||||
'--autonumber-size',
|
||||
dest='autonumber_size', metavar='NUMBER', default=5, type=int,
|
||||
help='Specify the number of digits in %(autonumber)s when it is present in output filename template or --auto-number option is given (default is %default)')
|
||||
dest='autonumber_size', metavar='NUMBER', type=int,
|
||||
help=optparse.SUPPRESS_HELP)
|
||||
filesystem.add_option(
|
||||
'--autonumber-start',
|
||||
dest='autonumber_start', metavar='NUMBER', default=1, type=int,
|
||||
@ -692,15 +692,15 @@ def parseOpts(overrideArguments=None):
|
||||
filesystem.add_option(
|
||||
'-A', '--auto-number',
|
||||
action='store_true', dest='autonumber', default=False,
|
||||
help='[deprecated; use -o "%(autonumber)s-%(title)s.%(ext)s" ] Number downloaded files starting from 00000')
|
||||
help=optparse.SUPPRESS_HELP)
|
||||
filesystem.add_option(
|
||||
'-t', '--title',
|
||||
action='store_true', dest='usetitle', default=False,
|
||||
help='[deprecated] Use title in file name (default)')
|
||||
help=optparse.SUPPRESS_HELP)
|
||||
filesystem.add_option(
|
||||
'-l', '--literal', default=False,
|
||||
action='store_true', dest='usetitle',
|
||||
help='[deprecated] Alias of --title')
|
||||
help=optparse.SUPPRESS_HELP)
|
||||
filesystem.add_option(
|
||||
'-w', '--no-overwrites',
|
||||
action='store_true', dest='nooverwrites', default=False,
|
||||
|
@ -536,8 +536,7 @@ class FFmpegSubtitlesConvertorPP(FFmpegPostProcessor):
|
||||
ext = sub['ext']
|
||||
if ext == new_ext:
|
||||
self._downloader.to_screen(
|
||||
'[ffmpeg] Subtitle file for %s is already in the requested'
|
||||
'format' % new_ext)
|
||||
'[ffmpeg] Subtitle file for %s is already in the requested format' % new_ext)
|
||||
continue
|
||||
old_file = subtitles_filename(filename, lang, ext)
|
||||
sub_filenames.append(old_file)
|
||||
|
@ -1,3 +1,3 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
__version__ = '2017.02.21'
|
||||
__version__ = '2017.02.27'
|
||||
|
Reference in New Issue
Block a user