Merge remote-tracking branch 'upstream/master' into yuvutu
This commit is contained in:
Simon Morgan
commit
54542a3ed0
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 *2016.10.02*. 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 Issues with outdated version will be rejected.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 **2016.10.02**
|
||||
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.10.07*. 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 Issues with outdated version will be rejected.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 **2016.10.07**
|
||||
|
||||
### 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 2016.10.02
|
||||
[debug] youtube-dl version 2016.10.07
|
||||
[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: {}
|
||||
|
||||
29
ChangeLog
29
ChangeLog
@ -1,3 +1,32 @@
|
||||
version <unreleased>
|
||||
|
||||
Core
|
||||
* [Makefile] Support for GNU make < 4 is fixed; BSD make dropped (#9387)
|
||||
|
||||
Extractors
|
||||
+ [nextmedia] Recognize action news on AppleDaily
|
||||
|
||||
|
||||
version 2016.10.07
|
||||
|
||||
Extractors
|
||||
+ [iprima] Detect geo restriction
|
||||
* [facebook] Fix video extraction (#10846)
|
||||
+ [commonprotocols] Support direct MMS links (#10838)
|
||||
+ [generic] Add support for multiple vimeo embeds (#10862)
|
||||
+ [nzz] Add support for nzz.ch (#4407)
|
||||
+ [npo] Detect geo restriction
|
||||
+ [npo] Add support for 2doc.nl (#10842)
|
||||
+ [lego] Add support for lego.com (#10369)
|
||||
+ [tonline] Add support for t-online.de (#10376)
|
||||
* [techtalks] Relax URL regular expression (#10840)
|
||||
* [youtube:live] Extend URL regular expression (#10839)
|
||||
+ [theweatherchannel] Add support for weather.com (#7188)
|
||||
+ [thisoldhouse] Add support for thisoldhouse.com (#10837)
|
||||
+ [nhl] Add support for wch2016.com (#10833)
|
||||
* [pornoxo] Use JWPlatform to improve metadata extraction
|
||||
|
||||
|
||||
version 2016.10.02
|
||||
|
||||
Core
|
||||
|
||||
4
Makefile
4
Makefile
@ -12,7 +12,7 @@ SHAREDIR ?= $(PREFIX)/share
|
||||
PYTHON ?= /usr/bin/env python
|
||||
|
||||
# set SYSCONFDIR to /etc if PREFIX=/usr or PREFIX=/usr/local
|
||||
SYSCONFDIR != if [ $(PREFIX) = /usr -o $(PREFIX) = /usr/local ]; then echo /etc; else echo $(PREFIX)/etc; fi
|
||||
SYSCONFDIR = $(shell if [ $(PREFIX) = /usr -o $(PREFIX) = /usr/local ]; then echo /etc; else echo $(PREFIX)/etc; fi)
|
||||
|
||||
install: youtube-dl youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish
|
||||
install -d $(DESTDIR)$(BINDIR)
|
||||
@ -90,7 +90,7 @@ fish-completion: youtube-dl.fish
|
||||
|
||||
lazy-extractors: youtube_dl/extractor/lazy_extractors.py
|
||||
|
||||
_EXTRACTOR_FILES != find youtube_dl/extractor -iname '*.py' -and -not -iname 'lazy_extractors.py'
|
||||
_EXTRACTOR_FILES = $(shell find youtube_dl/extractor -iname '*.py' -and -not -iname 'lazy_extractors.py')
|
||||
youtube_dl/extractor/lazy_extractors.py: devscripts/make_lazy_extractors.py devscripts/lazy_load_template.py $(_EXTRACTOR_FILES)
|
||||
$(PYTHON) devscripts/make_lazy_extractors.py $@
|
||||
|
||||
|
||||
@ -923,7 +923,7 @@ To run the test, simply invoke your favorite test runner, or execute a test file
|
||||
If you want to create a build of youtube-dl yourself, you'll need
|
||||
|
||||
* python
|
||||
* make (both GNU make and BSD make are supported)
|
||||
* make (only GNU make is supported)
|
||||
* pandoc
|
||||
* zip
|
||||
* nosetests
|
||||
|
||||
@ -364,6 +364,7 @@
|
||||
- **Le**: 乐视网
|
||||
- **Learnr**
|
||||
- **Lecture2Go**
|
||||
- **LEGO**
|
||||
- **Lemonde**
|
||||
- **LePlaylist**
|
||||
- **LetvCloud**: 乐视云
|
||||
@ -507,6 +508,7 @@
|
||||
- **Nuvid**
|
||||
- **NYTimes**
|
||||
- **NYTimesArticle**
|
||||
- **NZZ**
|
||||
- **ocw.mit.edu**
|
||||
- **OdaTV**
|
||||
- **Odnoklassniki**
|
||||
@ -692,6 +694,7 @@
|
||||
- **SWRMediathek**
|
||||
- **Syfy**
|
||||
- **SztvHu**
|
||||
- **t-online.de**
|
||||
- **Tagesschau**
|
||||
- **tagesschau:player**
|
||||
- **Tass**
|
||||
@ -721,8 +724,10 @@
|
||||
- **TheScene**
|
||||
- **TheSixtyOne**
|
||||
- **TheStar**
|
||||
- **TheWeatherChannel**
|
||||
- **ThisAmericanLife**
|
||||
- **ThisAV**
|
||||
- **ThisOldHouse**
|
||||
- **tinypic**: tinypic.com videos
|
||||
- **tlc.de**
|
||||
- **TMZ**
|
||||
|
||||
@ -21,6 +21,7 @@ from ..compat import (
|
||||
compat_os_name,
|
||||
compat_str,
|
||||
compat_urllib_error,
|
||||
compat_urllib_parse_unquote,
|
||||
compat_urllib_parse_urlencode,
|
||||
compat_urllib_request,
|
||||
compat_urlparse,
|
||||
@ -2020,6 +2021,12 @@ class InfoExtractor(object):
|
||||
headers['Ytdl-request-proxy'] = geo_verification_proxy
|
||||
return headers
|
||||
|
||||
def _generic_id(self, url):
|
||||
return compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
|
||||
|
||||
def _generic_title(self, url):
|
||||
return compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0])
|
||||
|
||||
|
||||
class SearchInfoExtractor(InfoExtractor):
|
||||
"""
|
||||
|
||||
@ -1,13 +1,9 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import os
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import (
|
||||
compat_urllib_parse_unquote,
|
||||
compat_urlparse,
|
||||
)
|
||||
from ..utils import url_basename
|
||||
|
||||
|
||||
class RtmpIE(InfoExtractor):
|
||||
@ -23,8 +19,8 @@ class RtmpIE(InfoExtractor):
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
|
||||
title = compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0])
|
||||
video_id = self._generic_id(url)
|
||||
title = self._generic_title(url)
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
@ -34,3 +30,31 @@ class RtmpIE(InfoExtractor):
|
||||
'format_id': compat_urlparse.urlparse(url).scheme,
|
||||
}],
|
||||
}
|
||||
|
||||
|
||||
class MmsIE(InfoExtractor):
|
||||
IE_DESC = False # Do not list
|
||||
_VALID_URL = r'(?i)mms://.+'
|
||||
|
||||
_TEST = {
|
||||
# Direct MMS link
|
||||
'url': 'mms://kentro.kaist.ac.kr/200907/MilesReid(0709).wmv',
|
||||
'info_dict': {
|
||||
'id': 'MilesReid(0709)',
|
||||
'ext': 'wmv',
|
||||
'title': 'MilesReid(0709)',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True, # rtsp downloads, requiring mplayer or mpv
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._generic_id(url)
|
||||
title = self._generic_title(url)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'url': url,
|
||||
}
|
||||
|
||||
@ -186,7 +186,10 @@ from .comedycentral import (
|
||||
)
|
||||
from .comcarcoff import ComCarCoffIE
|
||||
from .commonmistakes import CommonMistakesIE, UnicodeBOMIE
|
||||
from .commonprotocols import RtmpIE
|
||||
from .commonprotocols import (
|
||||
MmsIE,
|
||||
RtmpIE,
|
||||
)
|
||||
from .condenast import CondeNastIE
|
||||
from .cracked import CrackedIE
|
||||
from .crackle import CrackleIE
|
||||
@ -638,6 +641,7 @@ from .nytimes import (
|
||||
NYTimesArticleIE,
|
||||
)
|
||||
from .nuvid import NuvidIE
|
||||
from .nzz import NZZIE
|
||||
from .odatv import OdaTVIE
|
||||
from .odnoklassniki import OdnoklassnikiIE
|
||||
from .oktoberfesttv import OktoberfestTVIE
|
||||
|
||||
@ -258,7 +258,7 @@ class FacebookIE(InfoExtractor):
|
||||
|
||||
if not video_data:
|
||||
server_js_data = self._parse_json(self._search_regex(
|
||||
r'handleServerJS\(({.+})\);', webpage, 'server js data', default='{}'), video_id)
|
||||
r'handleServerJS\(({.+})(?:\);|,")', webpage, 'server js data', default='{}'), video_id)
|
||||
for item in server_js_data.get('instances', []):
|
||||
if item[1][0] == 'VideoConfig':
|
||||
video_data = video_data_list2dict(item[2][0]['videoData'])
|
||||
|
||||
@ -27,7 +27,6 @@ from ..utils import (
|
||||
unified_strdate,
|
||||
unsmuggle_url,
|
||||
UnsupportedError,
|
||||
url_basename,
|
||||
xpath_text,
|
||||
)
|
||||
from .brightcove import (
|
||||
@ -1549,7 +1548,7 @@ class GenericIE(InfoExtractor):
|
||||
force_videoid = smuggled_data['force_videoid']
|
||||
video_id = force_videoid
|
||||
else:
|
||||
video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
|
||||
video_id = self._generic_id(url)
|
||||
|
||||
self.to_screen('%s: Requesting header' % video_id)
|
||||
|
||||
@ -1578,7 +1577,7 @@ class GenericIE(InfoExtractor):
|
||||
|
||||
info_dict = {
|
||||
'id': video_id,
|
||||
'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
|
||||
'title': self._generic_title(url),
|
||||
'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
|
||||
}
|
||||
|
||||
@ -1754,9 +1753,9 @@ class GenericIE(InfoExtractor):
|
||||
if matches:
|
||||
return _playlist_from_matches(matches, ie='RtlNl')
|
||||
|
||||
vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
|
||||
if vimeo_url is not None:
|
||||
return self.url_result(vimeo_url)
|
||||
vimeo_urls = VimeoIE._extract_urls(url, webpage)
|
||||
if vimeo_urls:
|
||||
return _playlist_from_matches(vimeo_urls, ie=VimeoIE.ie_key())
|
||||
|
||||
vid_me_embed_url = self._search_regex(
|
||||
r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
|
||||
|
||||
@ -81,6 +81,9 @@ class IPrimaIE(InfoExtractor):
|
||||
for _, src in re.findall(r'src["\']\s*:\s*(["\'])(.+?)\1', playerpage):
|
||||
extract_formats(src)
|
||||
|
||||
if not formats and '>GEO_IP_NOT_ALLOWED<' in playerpage:
|
||||
self.raise_geo_restricted()
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
|
||||
@ -1,45 +1,86 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_str
|
||||
from ..utils import (
|
||||
unescapeHTML,
|
||||
int_or_none,
|
||||
parse_duration,
|
||||
get_element_by_class,
|
||||
)
|
||||
|
||||
|
||||
class LEGOIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?lego\.com/(?:[^/]+/)*videos/(?:[^/]+/)*[^/?#]+-(?P<id>[0-9a-f]+)'
|
||||
_TEST = {
|
||||
_VALID_URL = r'https?://(?:www\.)?lego\.com/(?P<locale>[^/]+)/(?:[^/]+/)*videos/(?:[^/]+/)*[^/?#]+-(?P<id>[0-9a-f]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.lego.com/en-us/videos/themes/club/blocumentary-kawaguchi-55492d823b1b4d5e985787fa8c2973b1',
|
||||
'md5': 'f34468f176cfd76488767fc162c405fa',
|
||||
'info_dict': {
|
||||
'id': '55492d823b1b4d5e985787fa8c2973b1',
|
||||
'ext': 'mp4',
|
||||
'title': 'Blocumentary Great Creations: Akiyuki Kawaguchi',
|
||||
}
|
||||
}
|
||||
'description': 'Blocumentary Great Creations: Akiyuki Kawaguchi',
|
||||
},
|
||||
}, {
|
||||
# geo-restricted but the contentUrl contain a valid url
|
||||
'url': 'http://www.lego.com/nl-nl/videos/themes/nexoknights/episode-20-kingdom-of-heroes-13bdc2299ab24d9685701a915b3d71e7##sp=399',
|
||||
'md5': '4c3fec48a12e40c6e5995abc3d36cc2e',
|
||||
'info_dict': {
|
||||
'id': '13bdc2299ab24d9685701a915b3d71e7',
|
||||
'ext': 'mp4',
|
||||
'title': 'Aflevering 20 - Helden van het koninkrijk',
|
||||
'description': 'md5:8ee499aac26d7fa8bcb0cedb7f9c3941',
|
||||
},
|
||||
}, {
|
||||
# special characters in title
|
||||
'url': 'http://www.lego.com/en-us/starwars/videos/lego-star-wars-force-surprise-9685ee9d12e84ff38e84b4e3d0db533d',
|
||||
'info_dict': {
|
||||
'id': '9685ee9d12e84ff38e84b4e3d0db533d',
|
||||
'ext': 'mp4',
|
||||
'title': 'Force Surprise – LEGO® Star Wars™ Microfighters',
|
||||
'description': 'md5:9c673c96ce6f6271b88563fe9dc56de3',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}]
|
||||
_BITRATES = [256, 512, 1024, 1536, 2560]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(
|
||||
'http://www.lego.com/en-US/mediaplayer/video/' + video_id, video_id)
|
||||
title = self._search_regex(r'<title>(.+?)</title>', webpage, 'title')
|
||||
video_data = self._parse_json(unescapeHTML(self._search_regex(
|
||||
r"video='([^']+)'", webpage, 'video data')), video_id)
|
||||
progressive_base = self._search_regex(
|
||||
r'data-video-progressive-url="([^"]+)"',
|
||||
webpage, 'progressive base', default='https://lc-mediaplayerns-live-s.legocdn.com/')
|
||||
streaming_base = self._search_regex(
|
||||
r'data-video-streaming-url="([^"]+)"',
|
||||
webpage, 'streaming base', default='http://legoprod-f.akamaihd.net/')
|
||||
item_id = video_data['ItemId']
|
||||
locale, video_id = re.match(self._VALID_URL, url).groups()
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
title = get_element_by_class('video-header', webpage).strip()
|
||||
progressive_base = 'https://lc-mediaplayerns-live-s.legocdn.com/'
|
||||
streaming_base = 'http://legoprod-f.akamaihd.net/'
|
||||
content_url = self._html_search_meta('contentUrl', webpage)
|
||||
path = self._search_regex(
|
||||
r'(?:https?:)?//[^/]+/(?:[iz]/s/)?public/(.+)_[0-9,]+\.(?:mp4|webm)',
|
||||
content_url, 'video path', default=None)
|
||||
if not path:
|
||||
player_url = self._proto_relative_url(self._search_regex(
|
||||
r'<iframe[^>]+src="((?:https?)?//(?:www\.)?lego\.com/[^/]+/mediaplayer/video/[^"]+)',
|
||||
webpage, 'player url', default=None))
|
||||
if not player_url:
|
||||
base_url = self._proto_relative_url(self._search_regex(
|
||||
r'data-baseurl="([^"]+)"', webpage, 'base url',
|
||||
default='http://www.lego.com/%s/mediaplayer/video/' % locale))
|
||||
player_url = base_url + video_id
|
||||
player_webpage = self._download_webpage(player_url, video_id)
|
||||
video_data = self._parse_json(unescapeHTML(self._search_regex(
|
||||
r"video='([^']+)'", player_webpage, 'video data')), video_id)
|
||||
progressive_base = self._search_regex(
|
||||
r'data-video-progressive-url="([^"]+)"',
|
||||
player_webpage, 'progressive base', default='https://lc-mediaplayerns-live-s.legocdn.com/')
|
||||
streaming_base = self._search_regex(
|
||||
r'data-video-streaming-url="([^"]+)"',
|
||||
player_webpage, 'streaming base', default='http://legoprod-f.akamaihd.net/')
|
||||
item_id = video_data['ItemId']
|
||||
|
||||
net_storage_path = video_data.get('NetStoragePath') or '/'.join([item_id[:2], item_id[2:4]])
|
||||
base_path = '_'.join([item_id, video_data['VideoId'], video_data['Locale'], compat_str(video_data['VideoVersion'])])
|
||||
path = '/'.join([net_storage_path, base_path])
|
||||
net_storage_path = video_data.get('NetStoragePath') or '/'.join([item_id[:2], item_id[2:4]])
|
||||
base_path = '_'.join([item_id, video_data['VideoId'], video_data['Locale'], compat_str(video_data['VideoVersion'])])
|
||||
path = '/'.join([net_storage_path, base_path])
|
||||
streaming_path = ','.join(map(lambda bitrate: compat_str(bitrate), self._BITRATES))
|
||||
|
||||
formats = self._extract_akamai_formats(
|
||||
@ -80,7 +121,8 @@ class LEGOIE(InfoExtractor):
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'thumbnail': video_data.get('CoverImageUrl'),
|
||||
'duration': int_or_none(video_data.get('Length')),
|
||||
'description': self._html_search_meta('description', webpage),
|
||||
'thumbnail': self._html_search_meta('thumbnail', webpage),
|
||||
'duration': parse_duration(self._html_search_meta('duration', webpage)),
|
||||
'formats': formats,
|
||||
}
|
||||
|
||||
@ -93,7 +93,7 @@ class NextMediaActionNewsIE(NextMediaIE):
|
||||
|
||||
class AppleDailyIE(NextMediaIE):
|
||||
IE_DESC = '臺灣蘋果日報'
|
||||
_VALID_URL = r'https?://(www|ent)\.appledaily\.com\.tw/(?:animation|appledaily|enews|realtimenews)/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?'
|
||||
_VALID_URL = r'https?://(www|ent)\.appledaily\.com\.tw/(?:animation|appledaily|enews|realtimenews|actionnews)/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?'
|
||||
_TESTS = [{
|
||||
'url': 'http://ent.appledaily.com.tw/enews/article/entertainment/20150128/36354694',
|
||||
'md5': 'a843ab23d150977cc55ef94f1e2c1e4d',
|
||||
@ -154,6 +154,9 @@ class AppleDailyIE(NextMediaIE):
|
||||
'description': 'md5:7b859991a6a4fedbdf3dd3b66545c748',
|
||||
'upload_date': '20140417',
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.appledaily.com.tw/actionnews/appledaily/7/20161003/960588/',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
_URL_PATTERN = r'\{url: \'(.+)\'\}'
|
||||
|
||||
@ -3,6 +3,7 @@ from __future__ import unicode_literals
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_HTTPError
|
||||
from ..utils import (
|
||||
fix_xml_ampersands,
|
||||
orderedSet,
|
||||
@ -10,6 +11,7 @@ from ..utils import (
|
||||
qualities,
|
||||
strip_jsonp,
|
||||
unified_strdate,
|
||||
ExtractorError,
|
||||
)
|
||||
|
||||
|
||||
@ -181,9 +183,16 @@ class NPOIE(NPOBaseIE):
|
||||
continue
|
||||
streams = format_info.get('streams')
|
||||
if streams:
|
||||
video_info = self._download_json(
|
||||
streams[0] + '&type=json',
|
||||
video_id, 'Downloading %s stream JSON' % format_id)
|
||||
try:
|
||||
video_info = self._download_json(
|
||||
streams[0] + '&type=json',
|
||||
video_id, 'Downloading %s stream JSON' % format_id)
|
||||
except ExtractorError as ee:
|
||||
if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404:
|
||||
error = (self._parse_json(ee.cause.read().decode(), video_id, fatal=False) or {}).get('errorstring')
|
||||
if error:
|
||||
raise ExtractorError(error, expected=True)
|
||||
raise
|
||||
else:
|
||||
video_info = format_info
|
||||
video_url = video_info.get('url')
|
||||
@ -459,8 +468,9 @@ class NPOPlaylistBaseIE(NPOIE):
|
||||
|
||||
class VPROIE(NPOPlaylistBaseIE):
|
||||
IE_NAME = 'vpro'
|
||||
_VALID_URL = r'https?://(?:www\.)?(?:tegenlicht\.)?vpro\.nl/(?:[^/]+/){2,}(?P<id>[^/]+)\.html'
|
||||
_PLAYLIST_TITLE_RE = r'<h1[^>]+class=["\'].*?\bmedia-platform-title\b.*?["\'][^>]*>([^<]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?(?:(?:tegenlicht\.)?vpro|2doc)\.nl/(?:[^/]+/)*(?P<id>[^/]+)\.html'
|
||||
_PLAYLIST_TITLE_RE = (r'<h1[^>]+class=["\'].*?\bmedia-platform-title\b.*?["\'][^>]*>([^<]+)',
|
||||
r'<h5[^>]+class=["\'].*?\bmedia-platform-subtitle\b.*?["\'][^>]*>([^<]+)')
|
||||
_PLAYLIST_ENTRY_RE = r'data-media-id="([^"]+)"'
|
||||
|
||||
_TESTS = [
|
||||
@ -492,6 +502,27 @@ class VPROIE(NPOPlaylistBaseIE):
|
||||
'title': 'education education',
|
||||
},
|
||||
'playlist_count': 2,
|
||||
},
|
||||
{
|
||||
'url': 'http://www.2doc.nl/documentaires/series/2doc/2015/oktober/de-tegenprestatie.html',
|
||||
'info_dict': {
|
||||
'id': 'de-tegenprestatie',
|
||||
'title': 'De Tegenprestatie',
|
||||
},
|
||||
'playlist_count': 2,
|
||||
}, {
|
||||
'url': 'http://www.2doc.nl/speel~VARA_101375237~mh17-het-verdriet-van-nederland~.html',
|
||||
'info_dict': {
|
||||
'id': 'VARA_101375237',
|
||||
'ext': 'm4v',
|
||||
'title': 'MH17: Het verdriet van Nederland',
|
||||
'description': 'md5:09e1a37c1fdb144621e22479691a9f18',
|
||||
'upload_date': '20150716',
|
||||
},
|
||||
'params': {
|
||||
# Skip because of m3u8 download
|
||||
'skip_download': True
|
||||
},
|
||||
}
|
||||
]
|
||||
|
||||
|
||||
36
youtube_dl/extractor/nzz.py
Normal file
36
youtube_dl/extractor/nzz.py
Normal file
@ -0,0 +1,36 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
extract_attributes,
|
||||
)
|
||||
|
||||
|
||||
class NZZIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?nzz\.ch/(?:[^/]+/)*[^/?#]+-ld\.(?P<id>\d+)'
|
||||
_TEST = {
|
||||
'url': 'http://www.nzz.ch/zuerich/gymizyte/gymizyte-schreiben-schueler-heute-noch-diktate-ld.9153',
|
||||
'info_dict': {
|
||||
'id': '9153',
|
||||
},
|
||||
'playlist_mincount': 6,
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
page_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, page_id)
|
||||
|
||||
entries = []
|
||||
for player_element in re.findall(r'(<[^>]+class="kalturaPlayer"[^>]*>)', webpage):
|
||||
player_params = extract_attributes(player_element)
|
||||
if player_params.get('data-type') not in ('kaltura_singleArticle',):
|
||||
self.report_warning('Unsupported player type')
|
||||
continue
|
||||
entry_id = player_params['data-id']
|
||||
entries.append(self.url_result(
|
||||
'kaltura:1750922:' + entry_id, 'Kaltura', entry_id))
|
||||
|
||||
return self.playlist_result(entries, page_id)
|
||||
@ -1,29 +1,29 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import str_or_none
|
||||
from ..utils import (
|
||||
qualities,
|
||||
str_or_none,
|
||||
)
|
||||
|
||||
|
||||
class ReverbNationIE(InfoExtractor):
|
||||
_VALID_URL = r'^https?://(?:www\.)?reverbnation\.com/.*?/song/(?P<id>\d+).*?$'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.reverbnation.com/alkilados/song/16965047-mona-lisa',
|
||||
'md5': '3da12ebca28c67c111a7f8b262d3f7a7',
|
||||
'md5': 'c0aaf339bcee189495fdf5a8c8ba8645',
|
||||
'info_dict': {
|
||||
'id': '16965047',
|
||||
'ext': 'mp3',
|
||||
'title': 'MONA LISA',
|
||||
'uploader': 'ALKILADOS',
|
||||
'uploader_id': '216429',
|
||||
'thumbnail': 're:^https://gp1\.wac\.edgecastcdn\.net/.*?\.jpg$'
|
||||
'thumbnail': 're:^https?://.*\.jpg',
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
song_id = mobj.group('id')
|
||||
song_id = self._match_id(url)
|
||||
|
||||
api_res = self._download_json(
|
||||
'https://api.reverbnation.com/song/%s' % song_id,
|
||||
@ -31,14 +31,23 @@ class ReverbNationIE(InfoExtractor):
|
||||
note='Downloading information of song %s' % song_id
|
||||
)
|
||||
|
||||
THUMBNAILS = ('thumbnail', 'image')
|
||||
quality = qualities(THUMBNAILS)
|
||||
thumbnails = []
|
||||
for thumb_key in THUMBNAILS:
|
||||
if api_res.get(thumb_key):
|
||||
thumbnails.append({
|
||||
'url': api_res[thumb_key],
|
||||
'preference': quality(thumb_key)
|
||||
})
|
||||
|
||||
return {
|
||||
'id': song_id,
|
||||
'title': api_res.get('name'),
|
||||
'url': api_res.get('url'),
|
||||
'title': api_res['name'],
|
||||
'url': api_res['url'],
|
||||
'uploader': api_res.get('artist', {}).get('name'),
|
||||
'uploader_id': str_or_none(api_res.get('artist', {}).get('id')),
|
||||
'thumbnail': self._proto_relative_url(
|
||||
api_res.get('image', api_res.get('thumbnail'))),
|
||||
'thumbnails': thumbnails,
|
||||
'ext': 'mp3',
|
||||
'vcodec': 'none',
|
||||
}
|
||||
|
||||
@ -1,7 +1,5 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
||||
|
||||
@ -9,7 +7,7 @@ class SlutloadIE(InfoExtractor):
|
||||
_VALID_URL = r'^https?://(?:\w+\.)?slutload\.com/video/[^/]+/(?P<id>[^/]+)/?$'
|
||||
_TEST = {
|
||||
'url': 'http://www.slutload.com/video/virginie-baisee-en-cam/TD73btpBqSxc/',
|
||||
'md5': '0cf531ae8006b530bd9df947a6a0df77',
|
||||
'md5': '868309628ba00fd488cf516a113fd717',
|
||||
'info_dict': {
|
||||
'id': 'TD73btpBqSxc',
|
||||
'ext': 'mp4',
|
||||
@ -20,9 +18,7 @@ class SlutloadIE(InfoExtractor):
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
video_title = self._html_search_regex(r'<h1><strong>([^<]+)</strong>',
|
||||
|
||||
@ -355,23 +355,28 @@ class VimeoIE(VimeoBaseInfoExtractor):
|
||||
return smuggle_url(url, {'http_headers': {'Referer': referrer_url}})
|
||||
|
||||
@staticmethod
|
||||
def _extract_vimeo_url(url, webpage):
|
||||
def _extract_urls(url, webpage):
|
||||
urls = []
|
||||
# Look for embedded (iframe) Vimeo player
|
||||
mobj = re.search(
|
||||
r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1', webpage)
|
||||
if mobj:
|
||||
player_url = unescapeHTML(mobj.group('url'))
|
||||
return VimeoIE._smuggle_referrer(player_url, url)
|
||||
# Look for embedded (swf embed) Vimeo player
|
||||
mobj = re.search(
|
||||
r'<embed[^>]+?src="((?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage)
|
||||
if mobj:
|
||||
return mobj.group(1)
|
||||
# Look more for non-standard embedded Vimeo player
|
||||
mobj = re.search(
|
||||
r'<video[^>]+src=(?P<q1>[\'"])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/[0-9]+)(?P=q1)', webpage)
|
||||
if mobj:
|
||||
return mobj.group('url')
|
||||
for mobj in re.finditer(
|
||||
r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1',
|
||||
webpage):
|
||||
urls.append(VimeoIE._smuggle_referrer(unescapeHTML(mobj.group('url')), url))
|
||||
PLAIN_EMBED_RE = (
|
||||
# Look for embedded (swf embed) Vimeo player
|
||||
r'<embed[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)\1',
|
||||
# Look more for non-standard embedded Vimeo player
|
||||
r'<video[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/[0-9]+)\1',
|
||||
)
|
||||
for embed_re in PLAIN_EMBED_RE:
|
||||
for mobj in re.finditer(embed_re, webpage):
|
||||
urls.append(mobj.group('url'))
|
||||
return urls
|
||||
|
||||
@staticmethod
|
||||
def _extract_url(url, webpage):
|
||||
urls = VimeoIE._extract_urls(url, webpage)
|
||||
return urls[0] if urls else None
|
||||
|
||||
def _verify_player_video_password(self, url, video_id):
|
||||
password = self._downloader.params.get('videopassword')
|
||||
|
||||
@ -341,7 +341,7 @@ class VKIE(VKBaseIE):
|
||||
if youtube_url:
|
||||
return self.url_result(youtube_url, 'Youtube')
|
||||
|
||||
vimeo_url = VimeoIE._extract_vimeo_url(url, info_page)
|
||||
vimeo_url = VimeoIE._extract_url(url, info_page)
|
||||
if vimeo_url is not None:
|
||||
return self.url_result(vimeo_url)
|
||||
|
||||
|
||||
@ -1,3 +1,3 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
__version__ = '2016.10.02'
|
||||
__version__ = '2016.10.07'
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user