Compare commits
19 Commits
2017.05.29
...
2017.06.05
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
537191826f | ||
|
|
130880ba48 | ||
|
|
f8ba3fda4d | ||
|
|
e1b90cc3db | ||
|
|
43e6579558 | ||
|
|
6d923aab35 | ||
|
|
62bafabc09 | ||
|
|
9edcdac90c | ||
|
|
cd138d8bd4 | ||
|
|
cd750b731c | ||
|
|
4bede0d8f5 | ||
|
|
f129c3f349 | ||
|
|
39d4c1be4d | ||
|
|
f7a747ce59 | ||
|
|
4489d41816 | ||
|
|
87b5184a0d | ||
|
|
c56ad5c975 | ||
|
|
6b7ce85cdc | ||
|
|
d10d0e3cf8 |
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 *2017.05.29*. 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 Issues with outdated version will be rejected.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 **2017.05.29**
|
||||
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.06.05*. 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 Issues with outdated version will be rejected.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 **2017.06.05**
|
||||
|
||||
### 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 2017.05.29
|
||||
[debug] youtube-dl version 2017.06.05
|
||||
[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: {}
|
||||
|
||||
3
AUTHORS
3
AUTHORS
@@ -217,3 +217,6 @@ Marvin Ewald
|
||||
Frédéric Bournival
|
||||
Timendum
|
||||
gritstub
|
||||
Adam Voss
|
||||
Mike Fährmann
|
||||
Jan Kundrát
|
||||
|
||||
17
ChangeLog
17
ChangeLog
@@ -1,3 +1,20 @@
|
||||
version 2017.06.05
|
||||
|
||||
Core
|
||||
* [YoutubeDL] Don't emit ANSI escape codes on Windows (#13270)
|
||||
|
||||
Extractors
|
||||
+ [bandcamp:weekly] Add support for bandcamp weekly (#12758)
|
||||
* [pornhub:playlist] Fix extraction (#13281)
|
||||
- [godtv] Remove extractor (#13175)
|
||||
* [safari] Fix typo (#13252)
|
||||
* [youtube] Improve chapters extraction (#13247)
|
||||
* [1tv] Lower preference for HTTP formats (#13246)
|
||||
* [francetv] Relax URL regular expression
|
||||
* [drbonanza] Fix extraction (#13231)
|
||||
* [packtpub] Fix authentication (#13240)
|
||||
|
||||
|
||||
version 2017.05.29
|
||||
|
||||
Extractors
|
||||
|
||||
@@ -474,7 +474,10 @@ machine twitch login my_twitch_account_name password my_twitch_password
|
||||
```
|
||||
To activate authentication with the `.netrc` file you should pass `--netrc` to youtube-dl or place it in the [configuration file](#configuration).
|
||||
|
||||
On Windows you may also need to setup the `%HOME%` environment variable manually.
|
||||
On Windows you may also need to setup the `%HOME%` environment variable manually. For example:
|
||||
```
|
||||
set HOME=%USERPROFILE%
|
||||
```
|
||||
|
||||
# OUTPUT TEMPLATE
|
||||
|
||||
@@ -649,7 +652,7 @@ Also filtering work for comparisons `=` (equals), `!=` (not equals), `^=` (begin
|
||||
- `acodec`: Name of the audio codec in use
|
||||
- `vcodec`: Name of the video codec in use
|
||||
- `container`: Name of the container format
|
||||
- `protocol`: The protocol that will be used for the actual download, lower-case (`http`, `https`, `rtsp`, `rtmp`, `rtmpe`, `mms`, `f4m`, `ism`, `m3u8`, or `m3u8_native`)
|
||||
- `protocol`: The protocol that will be used for the actual download, lower-case (`http`, `https`, `rtsp`, `rtmp`, `rtmpe`, `mms`, `f4m`, `ism`, `http_dash_segments`, `m3u8`, or `m3u8_native`)
|
||||
- `format_id`: A short description of the format
|
||||
|
||||
Note that none of the aforementioned meta fields are guaranteed to be present since this solely depends on the metadata obtained by particular extractor, i.e. the metadata offered by the video hoster.
|
||||
|
||||
@@ -87,6 +87,7 @@
|
||||
- **bambuser:channel**
|
||||
- **Bandcamp**
|
||||
- **Bandcamp:album**
|
||||
- **Bandcamp:weekly**
|
||||
- **bangumi.bilibili.com**: BiliBili番剧
|
||||
- **bbc**: BBC
|
||||
- **bbc.co.uk**: BBC iPlayer
|
||||
@@ -310,7 +311,6 @@
|
||||
- **Go**
|
||||
- **Go90**
|
||||
- **GodTube**
|
||||
- **GodTV**
|
||||
- **Golem**
|
||||
- **GoogleDrive**
|
||||
- **Goshgay**
|
||||
|
||||
@@ -254,6 +254,13 @@ class TestYoutubeChapters(unittest.TestCase):
|
||||
'title': '3 - Из серпов луны...[Iz serpov luny]',
|
||||
}]
|
||||
),
|
||||
(
|
||||
# https://www.youtube.com/watch?v=xZW70zEasOk
|
||||
# time point more than duration
|
||||
'''● LCS Spring finals: Saturday and Sunday from <a href="#" onclick="yt.www.watch.player.seekTo(13*60+30);return false;">13:30</a> outside the venue! <br />● PAX East: Fri, Sat & Sun - more info in tomorrows video on the main channel!''',
|
||||
283,
|
||||
[]
|
||||
),
|
||||
]
|
||||
|
||||
def test_youtube_chapters(self):
|
||||
|
||||
@@ -498,24 +498,25 @@ class YoutubeDL(object):
|
||||
def to_console_title(self, message):
|
||||
if not self.params.get('consoletitle', False):
|
||||
return
|
||||
if compat_os_name == 'nt' and ctypes.windll.kernel32.GetConsoleWindow():
|
||||
# c_wchar_p() might not be necessary if `message` is
|
||||
# already of type unicode()
|
||||
ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message))
|
||||
if compat_os_name == 'nt':
|
||||
if ctypes.windll.kernel32.GetConsoleWindow():
|
||||
# c_wchar_p() might not be necessary if `message` is
|
||||
# already of type unicode()
|
||||
ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message))
|
||||
elif 'TERM' in os.environ:
|
||||
self._write_string('\033]0;%s\007' % message, self._screen_file)
|
||||
|
||||
def save_console_title(self):
|
||||
if not self.params.get('consoletitle', False):
|
||||
return
|
||||
if 'TERM' in os.environ:
|
||||
if compat_os_name != 'nt' and 'TERM' in os.environ:
|
||||
# Save the title on stack
|
||||
self._write_string('\033[22;0t', self._screen_file)
|
||||
|
||||
def restore_console_title(self):
|
||||
if not self.params.get('consoletitle', False):
|
||||
return
|
||||
if 'TERM' in os.environ:
|
||||
if compat_os_name != 'nt' and 'TERM' in os.environ:
|
||||
# Restore the title from stack
|
||||
self._write_string('\033[23;0t', self._screen_file)
|
||||
|
||||
|
||||
@@ -14,14 +14,16 @@ from ..utils import (
|
||||
ExtractorError,
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
KNOWN_EXTENSIONS,
|
||||
parse_filesize,
|
||||
unescapeHTML,
|
||||
update_url_query,
|
||||
unified_strdate,
|
||||
)
|
||||
|
||||
|
||||
class BandcampIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://.*?\.bandcamp\.com/track/(?P<title>.*)'
|
||||
_VALID_URL = r'https?://.*?\.bandcamp\.com/track/(?P<title>[^/?#&]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://youtube-dl.bandcamp.com/track/youtube-dl-test-song',
|
||||
'md5': 'c557841d5e50261777a6585648adf439',
|
||||
@@ -155,7 +157,7 @@ class BandcampIE(InfoExtractor):
|
||||
|
||||
class BandcampAlbumIE(InfoExtractor):
|
||||
IE_NAME = 'Bandcamp:album'
|
||||
_VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com(?:/album/(?P<album_id>[^?#]+)|/?(?:$|[?#]))'
|
||||
_VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com(?:/album/(?P<album_id>[^/?#&]+))?'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1',
|
||||
@@ -222,6 +224,12 @@ class BandcampAlbumIE(InfoExtractor):
|
||||
'playlist_count': 2,
|
||||
}]
|
||||
|
||||
@classmethod
|
||||
def suitable(cls, url):
|
||||
return (False
|
||||
if BandcampWeeklyIE.suitable(url) or BandcampIE.suitable(url)
|
||||
else super(BandcampAlbumIE, cls).suitable(url))
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
uploader_id = mobj.group('subdomain')
|
||||
@@ -250,3 +258,92 @@ class BandcampAlbumIE(InfoExtractor):
|
||||
'title': title,
|
||||
'entries': entries,
|
||||
}
|
||||
|
||||
|
||||
class BandcampWeeklyIE(InfoExtractor):
|
||||
IE_NAME = 'Bandcamp:weekly'
|
||||
_VALID_URL = r'https?://(?:www\.)?bandcamp\.com/?\?(?:.*?&)?show=(?P<id>\d+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://bandcamp.com/?show=224',
|
||||
'md5': 'b00df799c733cf7e0c567ed187dea0fd',
|
||||
'info_dict': {
|
||||
'id': '224',
|
||||
'ext': 'opus',
|
||||
'title': 'BC Weekly April 4th 2017 - Magic Moments',
|
||||
'description': 'md5:5d48150916e8e02d030623a48512c874',
|
||||
'duration': 5829.77,
|
||||
'release_date': '20170404',
|
||||
'series': 'Bandcamp Weekly',
|
||||
'episode': 'Magic Moments',
|
||||
'episode_number': 208,
|
||||
'episode_id': '224',
|
||||
}
|
||||
}, {
|
||||
'url': 'https://bandcamp.com/?blah/blah@&show=228',
|
||||
'only_matching': True
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
blob = self._parse_json(
|
||||
self._search_regex(
|
||||
r'data-blob=(["\'])(?P<blob>{.+?})\1', webpage,
|
||||
'blob', group='blob'),
|
||||
video_id, transform_source=unescapeHTML)
|
||||
|
||||
show = blob['bcw_show']
|
||||
|
||||
# This is desired because any invalid show id redirects to `bandcamp.com`
|
||||
# which happens to expose the latest Bandcamp Weekly episode.
|
||||
show_id = int_or_none(show.get('show_id')) or int_or_none(video_id)
|
||||
|
||||
formats = []
|
||||
for format_id, format_url in show['audio_stream'].items():
|
||||
if not isinstance(format_url, compat_str):
|
||||
continue
|
||||
for known_ext in KNOWN_EXTENSIONS:
|
||||
if known_ext in format_id:
|
||||
ext = known_ext
|
||||
break
|
||||
else:
|
||||
ext = None
|
||||
formats.append({
|
||||
'format_id': format_id,
|
||||
'url': format_url,
|
||||
'ext': ext,
|
||||
'vcodec': 'none',
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
title = show.get('audio_title') or 'Bandcamp Weekly'
|
||||
subtitle = show.get('subtitle')
|
||||
if subtitle:
|
||||
title += ' - %s' % subtitle
|
||||
|
||||
episode_number = None
|
||||
seq = blob.get('bcw_seq')
|
||||
|
||||
if seq and isinstance(seq, list):
|
||||
try:
|
||||
episode_number = next(
|
||||
int_or_none(e.get('episode_number'))
|
||||
for e in seq
|
||||
if isinstance(e, dict) and int_or_none(e.get('id')) == show_id)
|
||||
except StopIteration:
|
||||
pass
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'description': show.get('desc') or show.get('short_desc'),
|
||||
'duration': float_or_none(show.get('audio_duration')),
|
||||
'is_live': False,
|
||||
'release_date': unified_strdate(show.get('published_date')),
|
||||
'series': 'Bandcamp Weekly',
|
||||
'episode': show.get('subtitle'),
|
||||
'episode_number': episode_number,
|
||||
'episode_id': compat_str(video_id),
|
||||
'formats': formats
|
||||
}
|
||||
|
||||
@@ -1,135 +1,59 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import json
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
parse_iso8601,
|
||||
js_to_json,
|
||||
parse_duration,
|
||||
unescapeHTML,
|
||||
)
|
||||
|
||||
|
||||
class DRBonanzaIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?dr\.dk/bonanza/(?:[^/]+/)+(?:[^/])+?(?:assetId=(?P<id>\d+))?(?:[#&]|$)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://www.dr.dk/bonanza/serie/portraetter/Talkshowet.htm?assetId=65517',
|
||||
_VALID_URL = r'https?://(?:www\.)?dr\.dk/bonanza/[^/]+/\d+/[^/]+/(?P<id>\d+)/(?P<display_id>[^/?#&]+)'
|
||||
_TEST = {
|
||||
'url': 'http://www.dr.dk/bonanza/serie/154/matador/40312/matador---0824-komme-fremmede-',
|
||||
'info_dict': {
|
||||
'id': '65517',
|
||||
'id': '40312',
|
||||
'display_id': 'matador---0824-komme-fremmede-',
|
||||
'ext': 'mp4',
|
||||
'title': 'Talkshowet - Leonard Cohen',
|
||||
'description': 'md5:8f34194fb30cd8c8a30ad8b27b70c0ca',
|
||||
'title': 'MATADOR - 08:24. "Komme fremmede".',
|
||||
'description': 'md5:77b4c1ac4d4c1b9d610ab4395212ff84',
|
||||
'thumbnail': r're:^https?://.*\.(?:gif|jpg)$',
|
||||
'timestamp': 1295537932,
|
||||
'upload_date': '20110120',
|
||||
'duration': 3664,
|
||||
'duration': 4613,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True, # requires rtmp
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.dr.dk/bonanza/radio/serie/sport/fodbold.htm?assetId=59410',
|
||||
'md5': '6dfe039417e76795fb783c52da3de11d',
|
||||
'info_dict': {
|
||||
'id': '59410',
|
||||
'ext': 'mp3',
|
||||
'title': 'EM fodbold 1992 Danmark - Tyskland finale Transmission',
|
||||
'description': 'md5:501e5a195749480552e214fbbed16c4e',
|
||||
'thumbnail': r're:^https?://.*\.(?:gif|jpg)$',
|
||||
'timestamp': 1223274900,
|
||||
'upload_date': '20081006',
|
||||
'duration': 7369,
|
||||
},
|
||||
}]
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
url_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, url_id)
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id, display_id = mobj.group('id', 'display_id')
|
||||
|
||||
if url_id:
|
||||
info = json.loads(self._html_search_regex(r'({.*?%s.*})' % url_id, webpage, 'json'))
|
||||
else:
|
||||
# Just fetch the first video on that page
|
||||
info = json.loads(self._html_search_regex(r'bonanzaFunctions.newPlaylist\(({.*})\)', webpage, 'json'))
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
asset_id = str(info['AssetId'])
|
||||
title = info['Title'].rstrip(' \'\"-,.:;!?')
|
||||
duration = int_or_none(info.get('Duration'), scale=1000)
|
||||
# First published online. "FirstPublished" contains the date for original airing.
|
||||
timestamp = parse_iso8601(
|
||||
re.sub(r'\.\d+$', '', info['Created']))
|
||||
info = self._parse_html5_media_entries(
|
||||
url, webpage, display_id, m3u8_id='hls',
|
||||
m3u8_entry_protocol='m3u8_native')[0]
|
||||
self._sort_formats(info['formats'])
|
||||
|
||||
def parse_filename_info(url):
|
||||
match = re.search(r'/\d+_(?P<width>\d+)x(?P<height>\d+)x(?P<bitrate>\d+)K\.(?P<ext>\w+)$', url)
|
||||
if match:
|
||||
return {
|
||||
'width': int(match.group('width')),
|
||||
'height': int(match.group('height')),
|
||||
'vbr': int(match.group('bitrate')),
|
||||
'ext': match.group('ext')
|
||||
}
|
||||
match = re.search(r'/\d+_(?P<bitrate>\d+)K\.(?P<ext>\w+)$', url)
|
||||
if match:
|
||||
return {
|
||||
'vbr': int(match.group('bitrate')),
|
||||
'ext': match.group(2)
|
||||
}
|
||||
return {}
|
||||
asset = self._parse_json(
|
||||
self._search_regex(
|
||||
r'(?s)currentAsset\s*=\s*({.+?})\s*</script', webpage, 'asset'),
|
||||
display_id, transform_source=js_to_json)
|
||||
|
||||
video_types = ['VideoHigh', 'VideoMid', 'VideoLow']
|
||||
preferencemap = {
|
||||
'VideoHigh': -1,
|
||||
'VideoMid': -2,
|
||||
'VideoLow': -3,
|
||||
'Audio': -4,
|
||||
}
|
||||
title = unescapeHTML(asset['AssetTitle']).strip()
|
||||
|
||||
formats = []
|
||||
for file in info['Files']:
|
||||
if info['Type'] == 'Video':
|
||||
if file['Type'] in video_types:
|
||||
format = parse_filename_info(file['Location'])
|
||||
format.update({
|
||||
'url': file['Location'],
|
||||
'format_id': file['Type'].replace('Video', ''),
|
||||
'preference': preferencemap.get(file['Type'], -10),
|
||||
})
|
||||
if format['url'].startswith('rtmp'):
|
||||
rtmp_url = format['url']
|
||||
format['rtmp_live'] = True # --resume does not work
|
||||
if '/bonanza/' in rtmp_url:
|
||||
format['play_path'] = rtmp_url.split('/bonanza/')[1]
|
||||
formats.append(format)
|
||||
elif file['Type'] == 'Thumb':
|
||||
thumbnail = file['Location']
|
||||
elif info['Type'] == 'Audio':
|
||||
if file['Type'] == 'Audio':
|
||||
format = parse_filename_info(file['Location'])
|
||||
format.update({
|
||||
'url': file['Location'],
|
||||
'format_id': file['Type'],
|
||||
'vcodec': 'none',
|
||||
})
|
||||
formats.append(format)
|
||||
elif file['Type'] == 'Thumb':
|
||||
thumbnail = file['Location']
|
||||
def extract(field):
|
||||
return self._search_regex(
|
||||
r'<div[^>]+>\s*<p>%s:<p>\s*</div>\s*<div[^>]+>\s*<p>([^<]+)</p>' % field,
|
||||
webpage, field, default=None)
|
||||
|
||||
description = '%s\n%s\n%s\n' % (
|
||||
info['Description'], info['Actors'], info['Colophon'])
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
display_id = re.sub(r'[^\w\d-]', '', re.sub(r' ', '-', title.lower())) + '-' + asset_id
|
||||
display_id = re.sub(r'-+', '-', display_id)
|
||||
|
||||
return {
|
||||
'id': asset_id,
|
||||
info.update({
|
||||
'id': asset.get('AssetId') or video_id,
|
||||
'display_id': display_id,
|
||||
'title': title,
|
||||
'formats': formats,
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
'timestamp': timestamp,
|
||||
'duration': duration,
|
||||
}
|
||||
'description': extract('Programinfo'),
|
||||
'duration': parse_duration(extract('Tid')),
|
||||
'thumbnail': asset.get('AssetImageUrl'),
|
||||
})
|
||||
return info
|
||||
|
||||
@@ -90,7 +90,7 @@ from .azmedien import (
|
||||
)
|
||||
from .baidu import BaiduVideoIE
|
||||
from .bambuser import BambuserIE, BambuserChannelIE
|
||||
from .bandcamp import BandcampIE, BandcampAlbumIE
|
||||
from .bandcamp import BandcampIE, BandcampAlbumIE, BandcampWeeklyIE
|
||||
from .bbc import (
|
||||
BBCCoUkIE,
|
||||
BBCCoUkArticleIE,
|
||||
@@ -392,7 +392,6 @@ from .globo import (
|
||||
from .go import GoIE
|
||||
from .go90 import Go90IE
|
||||
from .godtube import GodTubeIE
|
||||
from .godtv import GodTVIE
|
||||
from .golem import GolemIE
|
||||
from .googledrive import GoogleDriveIE
|
||||
from .googleplus import GooglePlusIE
|
||||
|
||||
@@ -102,6 +102,8 @@ class FirstTVIE(InfoExtractor):
|
||||
'format_id': f.get('name'),
|
||||
'tbr': tbr,
|
||||
'source_preference': quality(f.get('name')),
|
||||
# quality metadata of http formats may be incorrect
|
||||
'preference': -1,
|
||||
})
|
||||
# m3u8 URL format is reverse engineered from [1] (search for
|
||||
# master.m3u8). dashEdges (that is currently balancer-vod.1tv.ru)
|
||||
|
||||
@@ -112,7 +112,7 @@ class FranceTVBaseInfoExtractor(InfoExtractor):
|
||||
|
||||
|
||||
class FranceTVIE(FranceTVBaseInfoExtractor):
|
||||
_VALID_URL = r'https?://(?:(?:www\.)?france\.tv|mobile\.france\.tv)/(?:[^/]+/)+(?P<id>[^/]+)\.html'
|
||||
_VALID_URL = r'https?://(?:(?:www\.)?france\.tv|mobile\.france\.tv)/(?:[^/]+/)*(?P<id>[^/]+)\.html'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'https://www.france.tv/france-2/13h15-le-dimanche/140921-les-mysteres-de-jesus.html',
|
||||
@@ -157,6 +157,9 @@ class FranceTVIE(FranceTVBaseInfoExtractor):
|
||||
}, {
|
||||
'url': 'https://mobile.france.tv/france-5/c-dans-l-air/137347-emission-du-vendredi-12-mai-2017.html',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.france.tv/142749-rouge-sang.html',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
||||
@@ -1,66 +0,0 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from .ooyala import OoyalaIE
|
||||
from ..utils import js_to_json
|
||||
|
||||
|
||||
class GodTVIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?god\.tv(?:/[^/]+)*/(?P<id>[^/?#&]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://god.tv/jesus-image/video/jesus-conference-2016/randy-needham',
|
||||
'info_dict': {
|
||||
'id': 'lpd3g2MzE6D1g8zFAKz8AGpxWcpu6o_3',
|
||||
'ext': 'mp4',
|
||||
'title': 'Randy Needham',
|
||||
'duration': 3615.08,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
}
|
||||
}, {
|
||||
'url': 'http://god.tv/playlist/bible-study',
|
||||
'info_dict': {
|
||||
'id': 'bible-study',
|
||||
},
|
||||
'playlist_mincount': 37,
|
||||
}, {
|
||||
'url': 'http://god.tv/node/15097',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://god.tv/live/africa',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://god.tv/liveevents',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
settings = self._parse_json(
|
||||
self._search_regex(
|
||||
r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);',
|
||||
webpage, 'settings', default='{}'),
|
||||
display_id, transform_source=js_to_json, fatal=False)
|
||||
|
||||
ooyala_id = None
|
||||
|
||||
if settings:
|
||||
playlist = settings.get('playlist')
|
||||
if playlist and isinstance(playlist, list):
|
||||
entries = [
|
||||
OoyalaIE._build_url_result(video['content_id'])
|
||||
for video in playlist if video.get('content_id')]
|
||||
if entries:
|
||||
return self.playlist_result(entries, display_id)
|
||||
ooyala_id = settings.get('ooyala', {}).get('content_id')
|
||||
|
||||
if not ooyala_id:
|
||||
ooyala_id = self._search_regex(
|
||||
r'["\']content_id["\']\s*:\s*(["\'])(?P<id>[\w-]+)\1',
|
||||
webpage, 'ooyala id', group='id')
|
||||
|
||||
return OoyalaIE._build_url_result(ooyala_id)
|
||||
@@ -1,5 +1,6 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import json
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
@@ -14,7 +15,6 @@ from ..utils import (
|
||||
strip_or_none,
|
||||
unified_timestamp,
|
||||
urljoin,
|
||||
urlencode_postdata,
|
||||
)
|
||||
|
||||
|
||||
@@ -45,22 +45,15 @@ class PacktPubIE(PacktPubBaseIE):
|
||||
(username, password) = self._get_login_info()
|
||||
if username is None:
|
||||
return
|
||||
webpage = self._download_webpage(self._PACKT_BASE, None)
|
||||
login_form = self._form_hidden_inputs(
|
||||
'packt-user-login-form', webpage)
|
||||
login_form.update({
|
||||
'email': username,
|
||||
'password': password,
|
||||
})
|
||||
self._download_webpage(
|
||||
self._PACKT_BASE, None, 'Logging in as %s' % username,
|
||||
data=urlencode_postdata(login_form))
|
||||
try:
|
||||
self._TOKEN = self._download_json(
|
||||
'%s/users/tokens/sessions' % self._MAPT_REST, None,
|
||||
'Downloading Authorization Token')['data']['token']
|
||||
self._MAPT_REST + '/users/tokens', None,
|
||||
'Downloading Authorization Token', data=json.dumps({
|
||||
'email': username,
|
||||
'password': password,
|
||||
}).encode())['data']['access']
|
||||
except ExtractorError as e:
|
||||
if isinstance(e.cause, compat_HTTPError) and e.cause.code in (401, 404):
|
||||
if isinstance(e.cause, compat_HTTPError) and e.cause.code in (400, 401, 404):
|
||||
message = self._parse_json(e.cause.read().decode(), None)['message']
|
||||
raise ExtractorError(message, expected=True)
|
||||
raise
|
||||
@@ -83,7 +76,7 @@ class PacktPubIE(PacktPubBaseIE):
|
||||
|
||||
headers = {}
|
||||
if self._TOKEN:
|
||||
headers['Authorization'] = self._TOKEN
|
||||
headers['Authorization'] = 'Bearer ' + self._TOKEN
|
||||
video = self._download_json(
|
||||
'%s/users/me/products/%s/chapters/%s/sections/%s'
|
||||
% (self._MAPT_REST, course_id, chapter_id, video_id), video_id,
|
||||
|
||||
@@ -252,11 +252,14 @@ class PornHubPlaylistBaseIE(InfoExtractor):
|
||||
|
||||
playlist = self._parse_json(
|
||||
self._search_regex(
|
||||
r'playlistObject\s*=\s*({.+?});', webpage, 'playlist'),
|
||||
playlist_id)
|
||||
r'(?:playlistObject|PLAYLIST_VIEW)\s*=\s*({.+?});', webpage,
|
||||
'playlist', default='{}'),
|
||||
playlist_id, fatal=False)
|
||||
title = playlist.get('title') or self._search_regex(
|
||||
r'>Videos\s+in\s+(.+?)\s+[Pp]laylist<', webpage, 'title', fatal=False)
|
||||
|
||||
return self.playlist_result(
|
||||
entries, playlist_id, playlist.get('title'), playlist.get('description'))
|
||||
entries, playlist_id, title, playlist.get('description'))
|
||||
|
||||
|
||||
class PornHubPlaylistIE(PornHubPlaylistBaseIE):
|
||||
@@ -296,6 +299,7 @@ class PornHubUserVideosIE(PornHubPlaylistBaseIE):
|
||||
except ExtractorError as e:
|
||||
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
|
||||
break
|
||||
raise
|
||||
page_entries = self._extract_entries(webpage)
|
||||
if not page_entries:
|
||||
break
|
||||
|
||||
@@ -67,7 +67,7 @@ class SafariBaseIE(InfoExtractor):
|
||||
'Login failed; make sure your credentials are correct and try again.',
|
||||
expected=True)
|
||||
|
||||
SafariBaseIE.LOGGED_IN = True
|
||||
self.LOGGED_IN = True
|
||||
|
||||
self.to_screen('Login successful')
|
||||
|
||||
|
||||
@@ -1353,10 +1353,16 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
start_time = parse_duration(time_point)
|
||||
if start_time is None:
|
||||
continue
|
||||
if start_time > duration:
|
||||
break
|
||||
end_time = (duration if next_num == len(chapter_lines)
|
||||
else parse_duration(chapter_lines[next_num][1]))
|
||||
if end_time is None:
|
||||
continue
|
||||
if end_time > duration:
|
||||
end_time = duration
|
||||
if start_time > end_time:
|
||||
break
|
||||
chapter_title = re.sub(
|
||||
r'<a[^>]+>[^<]+</a>', '', chapter_line).strip(' \t-')
|
||||
chapter_title = re.sub(r'\s+', ' ', chapter_title)
|
||||
|
||||
@@ -1,3 +1,3 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
__version__ = '2017.05.29'
|
||||
__version__ = '2017.06.05'
|
||||
|
||||
Reference in New Issue
Block a user