Merge branch 'master' of github.com:rg3/youtube-dl into mixcloud-play-info
This commit is contained in:
Lukáš Lalinský
commit
bd308874c3
14
Makefile
14
Makefile
@ -61,34 +61,34 @@ youtube-dl: youtube_dl/*.py youtube_dl/*/*.py
|
||||
chmod a+x youtube-dl
|
||||
|
||||
README.md: youtube_dl/*.py youtube_dl/*/*.py
|
||||
COLUMNS=80 python youtube_dl/__main__.py --help | python devscripts/make_readme.py
|
||||
COLUMNS=80 $(PYTHON) youtube_dl/__main__.py --help | $(PYTHON) devscripts/make_readme.py
|
||||
|
||||
CONTRIBUTING.md: README.md
|
||||
python devscripts/make_contributing.py README.md CONTRIBUTING.md
|
||||
$(PYTHON) devscripts/make_contributing.py README.md CONTRIBUTING.md
|
||||
|
||||
supportedsites:
|
||||
python devscripts/make_supportedsites.py docs/supportedsites.md
|
||||
$(PYTHON) devscripts/make_supportedsites.py docs/supportedsites.md
|
||||
|
||||
README.txt: README.md
|
||||
pandoc -f markdown -t plain README.md -o README.txt
|
||||
|
||||
youtube-dl.1: README.md
|
||||
python devscripts/prepare_manpage.py >youtube-dl.1.temp.md
|
||||
$(PYTHON) devscripts/prepare_manpage.py >youtube-dl.1.temp.md
|
||||
pandoc -s -f markdown -t man youtube-dl.1.temp.md -o youtube-dl.1
|
||||
rm -f youtube-dl.1.temp.md
|
||||
|
||||
youtube-dl.bash-completion: youtube_dl/*.py youtube_dl/*/*.py devscripts/bash-completion.in
|
||||
python devscripts/bash-completion.py
|
||||
$(PYTHON) devscripts/bash-completion.py
|
||||
|
||||
bash-completion: youtube-dl.bash-completion
|
||||
|
||||
youtube-dl.zsh: youtube_dl/*.py youtube_dl/*/*.py devscripts/zsh-completion.in
|
||||
python devscripts/zsh-completion.py
|
||||
$(PYTHON) devscripts/zsh-completion.py
|
||||
|
||||
zsh-completion: youtube-dl.zsh
|
||||
|
||||
youtube-dl.fish: youtube_dl/*.py youtube_dl/*/*.py devscripts/fish-completion.in
|
||||
python devscripts/fish-completion.py
|
||||
$(PYTHON) devscripts/fish-completion.py
|
||||
|
||||
fish-completion: youtube-dl.fish
|
||||
|
||||
|
||||
@ -319,7 +319,8 @@ which means you can modify it, redistribute it or use it however you like.
|
||||
--all-formats Download all available video formats
|
||||
--prefer-free-formats Prefer free video formats unless a specific
|
||||
one is requested
|
||||
-F, --list-formats List all available formats
|
||||
-F, --list-formats List all available formats of requested
|
||||
videos
|
||||
--youtube-skip-dash-manifest Do not download the DASH manifests and
|
||||
related data on YouTube videos
|
||||
--merge-output-format FORMAT If a merge is required (e.g.
|
||||
|
||||
@ -15,8 +15,12 @@
|
||||
- **abc.net.au**
|
||||
- **Abc7News**
|
||||
- **AcademicEarth:Course**
|
||||
- **acast**
|
||||
- **acast:channel**
|
||||
- **AddAnime**
|
||||
- **AdobeTV**
|
||||
- **AdobeTVChannel**
|
||||
- **AdobeTVShow**
|
||||
- **AdobeTVVideo**
|
||||
- **AdultSwim**
|
||||
- **Aftenposten**
|
||||
@ -43,6 +47,7 @@
|
||||
- **arte.tv:future**
|
||||
- **AtresPlayer**
|
||||
- **ATTTechChannel**
|
||||
- **AudiMedia**
|
||||
- **audiomack**
|
||||
- **audiomack:album**
|
||||
- **Azubu**
|
||||
@ -92,6 +97,7 @@
|
||||
- **Clipfish**
|
||||
- **cliphunter**
|
||||
- **Clipsyndicate**
|
||||
- **cloudtime**: CloudTime
|
||||
- **Cloudy**
|
||||
- **Clubic**
|
||||
- **Clyp**
|
||||
@ -183,6 +189,7 @@
|
||||
- **freespeech.org**
|
||||
- **FreeVideo**
|
||||
- **FunnyOrDie**
|
||||
- **GameInformer**
|
||||
- **Gamekings**
|
||||
- **GameOne**
|
||||
- **gameone:playlist**
|
||||
@ -307,7 +314,6 @@
|
||||
- **MovieClips**
|
||||
- **MovieFap**
|
||||
- **Moviezine**
|
||||
- **movshare**: MovShare
|
||||
- **MPORA**
|
||||
- **MSNBC**
|
||||
- **MTV**
|
||||
@ -480,6 +486,8 @@
|
||||
- **Shared**: shared.sx and vivo.sx
|
||||
- **ShareSix**
|
||||
- **Sina**
|
||||
- **skynewsarabia:video**
|
||||
- **skynewsarabia:video**
|
||||
- **Slideshare**
|
||||
- **Slutload**
|
||||
- **smotri**: Smotri.com
|
||||
@ -665,6 +673,7 @@
|
||||
- **WebOfStories**
|
||||
- **WebOfStoriesPlaylist**
|
||||
- **Weibo**
|
||||
- **wholecloud**: WholeCloud
|
||||
- **Wimp**
|
||||
- **Wistia**
|
||||
- **WNL**
|
||||
|
||||
@ -13,6 +13,7 @@ from ..utils import (
|
||||
encodeArgument,
|
||||
encodeFilename,
|
||||
sanitize_open,
|
||||
handle_youtubedl_headers,
|
||||
)
|
||||
|
||||
|
||||
@ -33,9 +34,10 @@ class HlsFD(FileDownloader):
|
||||
if info_dict['http_headers'] and re.match(r'^https?://', url):
|
||||
# Trailing \r\n after each HTTP header is important to prevent warning from ffmpeg/avconv:
|
||||
# [http @ 00000000003d2fa0] No trailing CRLF found in HTTP header.
|
||||
headers = handle_youtubedl_headers(info_dict['http_headers'])
|
||||
args += [
|
||||
'-headers',
|
||||
''.join('%s: %s\r\n' % (key, val) for key, val in info_dict['http_headers'].items())]
|
||||
''.join('%s: %s\r\n' % (key, val) for key, val in headers.items())]
|
||||
|
||||
args += ['-i', url, '-f', 'mp4', '-c', 'copy', '-bsf:a', 'aac_adtstoasc']
|
||||
|
||||
|
||||
@ -3,9 +3,15 @@ from __future__ import unicode_literals
|
||||
from .abc import ABCIE
|
||||
from .abc7news import Abc7NewsIE
|
||||
from .academicearth import AcademicEarthCourseIE
|
||||
from .acast import (
|
||||
ACastIE,
|
||||
ACastChannelIE,
|
||||
)
|
||||
from .addanime import AddAnimeIE
|
||||
from .adobetv import (
|
||||
AdobeTVIE,
|
||||
AdobeTVShowIE,
|
||||
AdobeTVChannelIE,
|
||||
AdobeTVVideoIE,
|
||||
)
|
||||
from .adultswim import AdultSwimIE
|
||||
@ -38,6 +44,7 @@ from .arte import (
|
||||
)
|
||||
from .atresplayer import AtresPlayerIE
|
||||
from .atttechchannel import ATTTechChannelIE
|
||||
from .audimedia import AudiMediaIE
|
||||
from .audiomack import AudiomackIE, AudiomackAlbumIE
|
||||
from .azubu import AzubuIE
|
||||
from .baidu import BaiduVideoIE
|
||||
@ -200,6 +207,7 @@ from .freesound import FreesoundIE
|
||||
from .freespeech import FreespeechIE
|
||||
from .freevideo import FreeVideoIE
|
||||
from .funnyordie import FunnyOrDieIE
|
||||
from .gameinformer import GameInformerIE
|
||||
from .gamekings import GamekingsIE
|
||||
from .gameone import (
|
||||
GameOneIE,
|
||||
@ -349,7 +357,6 @@ from .motherless import MotherlessIE
|
||||
from .motorsport import MotorsportIE
|
||||
from .movieclips import MovieClipsIE
|
||||
from .moviezine import MoviezineIE
|
||||
from .movshare import MovShareIE
|
||||
from .mtv import (
|
||||
MTVIE,
|
||||
MTVServicesEmbeddedIE,
|
||||
@ -415,7 +422,13 @@ from .noco import NocoIE
|
||||
from .normalboots import NormalbootsIE
|
||||
from .nosvideo import NosVideoIE
|
||||
from .nova import NovaIE
|
||||
from .novamov import NovaMovIE
|
||||
from .novamov import (
|
||||
NovaMovIE,
|
||||
WholeCloudIE,
|
||||
NowVideoIE,
|
||||
VideoWeedIE,
|
||||
CloudTimeIE,
|
||||
)
|
||||
from .nowness import (
|
||||
NownessIE,
|
||||
NownessPlaylistIE,
|
||||
@ -425,7 +438,6 @@ from .nowtv import (
|
||||
NowTVIE,
|
||||
NowTVListIE,
|
||||
)
|
||||
from .nowvideo import NowVideoIE
|
||||
from .npo import (
|
||||
NPOIE,
|
||||
NPOLiveIE,
|
||||
@ -554,6 +566,10 @@ from .shahid import ShahidIE
|
||||
from .shared import SharedIE
|
||||
from .sharesix import ShareSixIE
|
||||
from .sina import SinaIE
|
||||
from .skynewsarabia import (
|
||||
SkyNewsArabiaIE,
|
||||
SkyNewsArabiaArticleIE,
|
||||
)
|
||||
from .slideshare import SlideshareIE
|
||||
from .slutload import SlutloadIE
|
||||
from .smotri import (
|
||||
@ -732,7 +748,6 @@ from .videofyme import VideofyMeIE
|
||||
from .videomega import VideoMegaIE
|
||||
from .videopremium import VideoPremiumIE
|
||||
from .videott import VideoTtIE
|
||||
from .videoweed import VideoWeedIE
|
||||
from .vidme import VidmeIE
|
||||
from .vidzi import VidziIE
|
||||
from .vier import VierIE, VierVideosIE
|
||||
|
||||
70
youtube_dl/extractor/acast.py
Normal file
70
youtube_dl/extractor/acast.py
Normal file
@ -0,0 +1,70 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_str
|
||||
from ..utils import int_or_none
|
||||
|
||||
|
||||
class ACastBaseIE(InfoExtractor):
|
||||
_API_BASE_URL = 'https://www.acast.com/api/'
|
||||
|
||||
|
||||
class ACastIE(ACastBaseIE):
|
||||
IE_NAME = 'acast'
|
||||
_VALID_URL = r'https?://(?:www\.)?acast\.com/(?P<channel>[^/]+)/(?P<id>[^/#?]+)'
|
||||
_TEST = {
|
||||
'url': 'https://www.acast.com/condenasttraveler/-where-are-you-taipei-101-taiwan',
|
||||
'md5': 'ada3de5a1e3a2a381327d749854788bb',
|
||||
'info_dict': {
|
||||
'id': '57de3baa-4bb0-487e-9418-2692c1277a34',
|
||||
'ext': 'mp3',
|
||||
'title': '"Where Are You?": Taipei 101, Taiwan',
|
||||
'timestamp': 1196172000000,
|
||||
'description': 'md5:0c5d8201dfea2b93218ea986c91eee6e',
|
||||
'duration': 211,
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
channel, display_id = re.match(self._VALID_URL, url).groups()
|
||||
cast_data = self._download_json(self._API_BASE_URL + 'channels/%s/acasts/%s/playback' % (channel, display_id), display_id)
|
||||
|
||||
return {
|
||||
'id': compat_str(cast_data['id']),
|
||||
'display_id': display_id,
|
||||
'url': cast_data['blings'][0]['audio'],
|
||||
'title': cast_data['name'],
|
||||
'description': cast_data.get('description'),
|
||||
'thumbnail': cast_data.get('image'),
|
||||
'timestamp': int_or_none(cast_data.get('publishingDate')),
|
||||
'duration': int_or_none(cast_data.get('duration')),
|
||||
}
|
||||
|
||||
|
||||
class ACastChannelIE(ACastBaseIE):
|
||||
IE_NAME = 'acast:channel'
|
||||
_VALID_URL = r'https?://(?:www\.)?acast\.com/(?P<id>[^/#?]+)'
|
||||
_TEST = {
|
||||
'url': 'https://www.acast.com/condenasttraveler',
|
||||
'info_dict': {
|
||||
'id': '50544219-29bb-499e-a083-6087f4cb7797',
|
||||
'title': 'Condé Nast Traveler Podcast',
|
||||
'description': 'md5:98646dee22a5b386626ae31866638fbd',
|
||||
},
|
||||
'playlist_mincount': 20,
|
||||
}
|
||||
|
||||
@classmethod
|
||||
def suitable(cls, url):
|
||||
return False if ACastIE.suitable(url) else super(ACastChannelIE, cls).suitable(url)
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
channel_data = self._download_json(self._API_BASE_URL + 'channels/%s' % display_id, display_id)
|
||||
casts = self._download_json(self._API_BASE_URL + 'channels/%s/acasts' % display_id, display_id)
|
||||
entries = [self.url_result('https://www.acast.com/%s/%s' % (display_id, cast['url']), 'ACast') for cast in casts]
|
||||
|
||||
return self.playlist_result(entries, compat_str(channel_data['id']), channel_data['name'], channel_data.get('description'))
|
||||
@ -1,23 +1,32 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_str
|
||||
from ..utils import (
|
||||
parse_duration,
|
||||
unified_strdate,
|
||||
str_to_int,
|
||||
int_or_none,
|
||||
float_or_none,
|
||||
ISO639Utils,
|
||||
determine_ext,
|
||||
)
|
||||
|
||||
|
||||
class AdobeTVIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://tv\.adobe\.com/watch/[^/]+/(?P<id>[^/]+)'
|
||||
class AdobeTVBaseIE(InfoExtractor):
|
||||
_API_BASE_URL = 'http://tv.adobe.com/api/v4/'
|
||||
|
||||
|
||||
class AdobeTVIE(AdobeTVBaseIE):
|
||||
_VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?watch/(?P<show_urlname>[^/]+)/(?P<id>[^/]+)'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://tv.adobe.com/watch/the-complete-picture-with-julieanne-kost/quick-tip-how-to-draw-a-circle-around-an-object-in-photoshop/',
|
||||
'md5': '9bc5727bcdd55251f35ad311ca74fa1e',
|
||||
'info_dict': {
|
||||
'id': 'quick-tip-how-to-draw-a-circle-around-an-object-in-photoshop',
|
||||
'id': '10981',
|
||||
'ext': 'mp4',
|
||||
'title': 'Quick Tip - How to Draw a Circle Around an Object in Photoshop',
|
||||
'description': 'md5:99ec318dc909d7ba2a1f2b038f7d2311',
|
||||
@ -29,50 +38,106 @@ class AdobeTVIE(InfoExtractor):
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
language, show_urlname, urlname = re.match(self._VALID_URL, url).groups()
|
||||
if not language:
|
||||
language = 'en'
|
||||
|
||||
player = self._parse_json(
|
||||
self._search_regex(r'html5player:\s*({.+?})\s*\n', webpage, 'player'),
|
||||
video_id)
|
||||
|
||||
title = player.get('title') or self._search_regex(
|
||||
r'data-title="([^"]+)"', webpage, 'title')
|
||||
description = self._og_search_description(webpage)
|
||||
thumbnail = self._og_search_thumbnail(webpage)
|
||||
|
||||
upload_date = unified_strdate(
|
||||
self._html_search_meta('datepublished', webpage, 'upload date'))
|
||||
|
||||
duration = parse_duration(
|
||||
self._html_search_meta('duration', webpage, 'duration') or
|
||||
self._search_regex(
|
||||
r'Runtime:\s*(\d{2}:\d{2}:\d{2})',
|
||||
webpage, 'duration', fatal=False))
|
||||
|
||||
view_count = str_to_int(self._search_regex(
|
||||
r'<div class="views">\s*Views?:\s*([\d,.]+)\s*</div>',
|
||||
webpage, 'view count'))
|
||||
video_data = self._download_json(
|
||||
self._API_BASE_URL + 'episode/get/?language=%s&show_urlname=%s&urlname=%s&disclosure=standard' % (language, show_urlname, urlname),
|
||||
urlname)['data'][0]
|
||||
|
||||
formats = [{
|
||||
'url': source['src'],
|
||||
'format_id': source.get('quality') or source['src'].split('-')[-1].split('.')[0] or None,
|
||||
'tbr': source.get('bitrate'),
|
||||
} for source in player['sources']]
|
||||
'url': source['url'],
|
||||
'format_id': source.get('quality_level') or source['url'].split('-')[-1].split('.')[0] or None,
|
||||
'width': int_or_none(source.get('width')),
|
||||
'height': int_or_none(source.get('height')),
|
||||
'tbr': int_or_none(source.get('video_data_rate')),
|
||||
} for source in video_data['videos']]
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
'upload_date': upload_date,
|
||||
'duration': duration,
|
||||
'view_count': view_count,
|
||||
'id': compat_str(video_data['id']),
|
||||
'title': video_data['title'],
|
||||
'description': video_data.get('description'),
|
||||
'thumbnail': video_data.get('thumbnail'),
|
||||
'upload_date': unified_strdate(video_data.get('start_date')),
|
||||
'duration': parse_duration(video_data.get('duration')),
|
||||
'view_count': str_to_int(video_data.get('playcount')),
|
||||
'formats': formats,
|
||||
}
|
||||
|
||||
|
||||
class AdobeTVPlaylistBaseIE(AdobeTVBaseIE):
|
||||
def _parse_page_data(self, page_data):
|
||||
return [self.url_result(self._get_element_url(element_data)) for element_data in page_data]
|
||||
|
||||
def _extract_playlist_entries(self, url, display_id):
|
||||
page = self._download_json(url, display_id)
|
||||
entries = self._parse_page_data(page['data'])
|
||||
for page_num in range(2, page['paging']['pages'] + 1):
|
||||
entries.extend(self._parse_page_data(
|
||||
self._download_json(url + '&page=%d' % page_num, display_id)['data']))
|
||||
return entries
|
||||
|
||||
|
||||
class AdobeTVShowIE(AdobeTVPlaylistBaseIE):
|
||||
_VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?show/(?P<id>[^/]+)'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://tv.adobe.com/show/the-complete-picture-with-julieanne-kost',
|
||||
'info_dict': {
|
||||
'id': '36',
|
||||
'title': 'The Complete Picture with Julieanne Kost',
|
||||
'description': 'md5:fa50867102dcd1aa0ddf2ab039311b27',
|
||||
},
|
||||
'playlist_mincount': 136,
|
||||
}
|
||||
|
||||
def _get_element_url(self, element_data):
|
||||
return element_data['urls'][0]
|
||||
|
||||
def _real_extract(self, url):
|
||||
language, show_urlname = re.match(self._VALID_URL, url).groups()
|
||||
if not language:
|
||||
language = 'en'
|
||||
query = 'language=%s&show_urlname=%s' % (language, show_urlname)
|
||||
|
||||
show_data = self._download_json(self._API_BASE_URL + 'show/get/?%s' % query, show_urlname)['data'][0]
|
||||
|
||||
return self.playlist_result(
|
||||
self._extract_playlist_entries(self._API_BASE_URL + 'episode/?%s' % query, show_urlname),
|
||||
compat_str(show_data['id']),
|
||||
show_data['show_name'],
|
||||
show_data['show_description'])
|
||||
|
||||
|
||||
class AdobeTVChannelIE(AdobeTVPlaylistBaseIE):
|
||||
_VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?channel/(?P<id>[^/]+)(?:/(?P<category_urlname>[^/]+))?'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://tv.adobe.com/channel/development',
|
||||
'info_dict': {
|
||||
'id': 'development',
|
||||
},
|
||||
'playlist_mincount': 96,
|
||||
}
|
||||
|
||||
def _get_element_url(self, element_data):
|
||||
return element_data['url']
|
||||
|
||||
def _real_extract(self, url):
|
||||
language, channel_urlname, category_urlname = re.match(self._VALID_URL, url).groups()
|
||||
if not language:
|
||||
language = 'en'
|
||||
query = 'language=%s&channel_urlname=%s' % (language, channel_urlname)
|
||||
if category_urlname:
|
||||
query += '&category_urlname=%s' % category_urlname
|
||||
|
||||
return self.playlist_result(
|
||||
self._extract_playlist_entries(self._API_BASE_URL + 'show/?%s' % query, channel_urlname),
|
||||
channel_urlname)
|
||||
|
||||
|
||||
class AdobeTVVideoIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://video\.tv\.adobe\.com/v/(?P<id>\d+)'
|
||||
|
||||
@ -91,28 +156,25 @@ class AdobeTVVideoIE(InfoExtractor):
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
player_params = self._parse_json(self._search_regex(
|
||||
r'var\s+bridge\s*=\s*([^;]+);', webpage, 'player parameters'),
|
||||
video_id)
|
||||
video_data = self._download_json(url + '?format=json', video_id)
|
||||
|
||||
formats = [{
|
||||
'format_id': '%s-%s' % (determine_ext(source['src']), source.get('height')),
|
||||
'url': source['src'],
|
||||
'width': source.get('width'),
|
||||
'height': source.get('height'),
|
||||
'tbr': source.get('bitrate'),
|
||||
} for source in player_params['sources']]
|
||||
'width': int_or_none(source.get('width')),
|
||||
'height': int_or_none(source.get('height')),
|
||||
'tbr': int_or_none(source.get('bitrate')),
|
||||
} for source in video_data['sources']]
|
||||
self._sort_formats(formats)
|
||||
|
||||
# For both metadata and downloaded files the duration varies among
|
||||
# formats. I just pick the max one
|
||||
duration = max(filter(None, [
|
||||
float_or_none(source.get('duration'), scale=1000)
|
||||
for source in player_params['sources']]))
|
||||
for source in video_data['sources']]))
|
||||
|
||||
subtitles = {}
|
||||
for translation in player_params.get('translations', []):
|
||||
for translation in video_data.get('translations', []):
|
||||
lang_id = translation.get('language_w3c') or ISO639Utils.long2short(translation['language_medium'])
|
||||
if lang_id not in subtitles:
|
||||
subtitles[lang_id] = []
|
||||
@ -124,8 +186,9 @@ class AdobeTVVideoIE(InfoExtractor):
|
||||
return {
|
||||
'id': video_id,
|
||||
'formats': formats,
|
||||
'title': player_params['title'],
|
||||
'description': self._og_search_description(webpage),
|
||||
'title': video_data['title'],
|
||||
'description': video_data.get('description'),
|
||||
'thumbnail': video_data['video'].get('poster'),
|
||||
'duration': duration,
|
||||
'subtitles': subtitles,
|
||||
}
|
||||
|
||||
80
youtube_dl/extractor/audimedia.py
Normal file
80
youtube_dl/extractor/audimedia.py
Normal file
@ -0,0 +1,80 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
parse_iso8601,
|
||||
sanitized_Request,
|
||||
)
|
||||
|
||||
|
||||
class AudiMediaIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?audimedia\.tv/(?:en|de)/vid/(?P<id>[^/?#]+)'
|
||||
_TEST = {
|
||||
'url': 'https://audimedia.tv/en/vid/60-seconds-of-audi-sport-104-2015-wec-bahrain-rookie-test',
|
||||
'md5': '79a8b71c46d49042609795ab59779b66',
|
||||
'info_dict': {
|
||||
'id': '1564',
|
||||
'ext': 'mp4',
|
||||
'title': '60 Seconds of Audi Sport 104/2015 - WEC Bahrain, Rookie Test',
|
||||
'description': 'md5:60e5d30a78ced725f7b8d34370762941',
|
||||
'upload_date': '20151124',
|
||||
'timestamp': 1448354940,
|
||||
'duration': 74022,
|
||||
'view_count': int,
|
||||
}
|
||||
}
|
||||
# extracted from https://audimedia.tv/assets/embed/embedded-player.js (dataSourceAuthToken)
|
||||
_AUTH_TOKEN = 'e25b42847dba18c6c8816d5d8ce94c326e06823ebf0859ed164b3ba169be97f2'
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
raw_payload = self._search_regex(r'<script[^>]+class="amtv-embed"[^>]+id="([^"]+)"', webpage, 'raw payload')
|
||||
_, stage_mode, video_id, lang = raw_payload.split('-')
|
||||
|
||||
# TODO: handle s and e stage_mode (live streams and ended live streams)
|
||||
if stage_mode not in ('s', 'e'):
|
||||
request = sanitized_Request(
|
||||
'https://audimedia.tv/api/video/v1/videos/%s?embed[]=video_versions&embed[]=thumbnail_image&where[content_language_iso]=%s' % (video_id, lang),
|
||||
headers={'X-Auth-Token': self._AUTH_TOKEN})
|
||||
json_data = self._download_json(request, video_id)['results']
|
||||
formats = []
|
||||
|
||||
stream_url_hls = json_data.get('stream_url_hls')
|
||||
if stream_url_hls:
|
||||
m3u8_formats = self._extract_m3u8_formats(stream_url_hls, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)
|
||||
if m3u8_formats:
|
||||
formats.extend(m3u8_formats)
|
||||
|
||||
stream_url_hds = json_data.get('stream_url_hds')
|
||||
if stream_url_hds:
|
||||
f4m_formats = self._extract_f4m_formats(json_data.get('stream_url_hds') + '?hdcore=3.4.0', video_id, -1, f4m_id='hds', fatal=False)
|
||||
if f4m_formats:
|
||||
formats.extend(f4m_formats)
|
||||
|
||||
for video_version in json_data.get('video_versions'):
|
||||
video_version_url = video_version.get('download_url') or video_version.get('stream_url')
|
||||
if not video_version_url:
|
||||
continue
|
||||
formats.append({
|
||||
'url': video_version_url,
|
||||
'width': int_or_none(video_version.get('width')),
|
||||
'height': int_or_none(video_version.get('height')),
|
||||
'abr': int_or_none(video_version.get('audio_bitrate')),
|
||||
'vbr': int_or_none(video_version.get('video_bitrate')),
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': json_data['title'],
|
||||
'description': json_data.get('subtitle'),
|
||||
'thumbnail': json_data.get('thumbnail_image', {}).get('file'),
|
||||
'timestamp': parse_iso8601(json_data.get('publication_date')),
|
||||
'duration': int_or_none(json_data.get('duration')),
|
||||
'view_count': int_or_none(json_data.get('view_count')),
|
||||
'formats': formats,
|
||||
}
|
||||
@ -22,7 +22,8 @@ from ..compat import (
|
||||
class BBCCoUkIE(InfoExtractor):
|
||||
IE_NAME = 'bbc.co.uk'
|
||||
IE_DESC = 'BBC iPlayer'
|
||||
_VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:programmes/(?!articles/)|iplayer(?:/[^/]+)?/(?:episode/|playlist/))|music/clips[/#])(?P<id>[\da-z]{8})'
|
||||
_ID_REGEX = r'[pb][\da-z]{7}'
|
||||
_VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:programmes/(?!articles/)|iplayer(?:/[^/]+)?/(?:episode/|playlist/))|music/clips[/#])(?P<id>%s)' % _ID_REGEX
|
||||
|
||||
_MEDIASELECTOR_URLS = [
|
||||
# Provides HQ HLS streams with even better quality that pc mediaset but fails
|
||||
@ -46,9 +47,8 @@ class BBCCoUkIE(InfoExtractor):
|
||||
'info_dict': {
|
||||
'id': 'b039d07m',
|
||||
'ext': 'flv',
|
||||
'title': 'Kaleidoscope, Leonard Cohen',
|
||||
'title': 'Leonard Cohen, Kaleidoscope - BBC Radio 4',
|
||||
'description': 'The Canadian poet and songwriter reflects on his musical career.',
|
||||
'duration': 1740,
|
||||
},
|
||||
'params': {
|
||||
# rtmp download
|
||||
@ -111,7 +111,8 @@ class BBCCoUkIE(InfoExtractor):
|
||||
'params': {
|
||||
# rtmp download
|
||||
'skip_download': True,
|
||||
}
|
||||
},
|
||||
'skip': 'Episode is no longer available on BBC iPlayer Radio',
|
||||
}, {
|
||||
'url': 'http://www.bbc.co.uk/music/clips/p02frcc3',
|
||||
'note': 'Audio',
|
||||
@ -453,6 +454,7 @@ class BBCCoUkIE(InfoExtractor):
|
||||
webpage = self._download_webpage(url, group_id, 'Downloading video page')
|
||||
|
||||
programme_id = None
|
||||
duration = None
|
||||
|
||||
tviplayer = self._search_regex(
|
||||
r'mediator\.bind\(({.+?})\s*,\s*document\.getElementById',
|
||||
@ -465,14 +467,16 @@ class BBCCoUkIE(InfoExtractor):
|
||||
|
||||
if not programme_id:
|
||||
programme_id = self._search_regex(
|
||||
r'"vpid"\s*:\s*"([\da-z]{8})"', webpage, 'vpid', fatal=False, default=None)
|
||||
r'"vpid"\s*:\s*"(%s)"' % self._ID_REGEX, webpage, 'vpid', fatal=False, default=None)
|
||||
|
||||
if programme_id:
|
||||
formats, subtitles = self._download_media_selector(programme_id)
|
||||
title = self._og_search_title(webpage)
|
||||
description = self._search_regex(
|
||||
r'<p class="[^"]*medium-description[^"]*">([^<]+)</p>',
|
||||
webpage, 'description', fatal=False)
|
||||
webpage, 'description', default=None)
|
||||
if not description:
|
||||
description = self._html_search_meta('description', webpage)
|
||||
else:
|
||||
programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id)
|
||||
|
||||
@ -586,6 +590,7 @@ class BBCIE(BBCCoUkIE):
|
||||
'ext': 'mp4',
|
||||
'title': '''Judge Mindy Glazer: "I'm sorry to see you here... I always wondered what happened to you"''',
|
||||
'duration': 56,
|
||||
'description': '''Judge Mindy Glazer: "I'm sorry to see you here... I always wondered what happened to you"''',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
@ -728,6 +733,7 @@ class BBCIE(BBCCoUkIE):
|
||||
# article with multiple videos embedded with playlist.sxml (e.g.
|
||||
# http://www.bbc.com/sport/0/football/34475836)
|
||||
playlists = re.findall(r'<param[^>]+name="playlist"[^>]+value="([^"]+)"', webpage)
|
||||
playlists.extend(re.findall(r'data-media-id="([^"]+/playlist\.sxml)"', webpage))
|
||||
if playlists:
|
||||
entries = [
|
||||
self._extract_from_playlist_sxml(playlist_url, playlist_id, timestamp)
|
||||
@ -780,8 +786,9 @@ class BBCIE(BBCCoUkIE):
|
||||
|
||||
# single video story (e.g. http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret)
|
||||
programme_id = self._search_regex(
|
||||
[r'data-video-player-vpid="([\da-z]{8})"',
|
||||
r'<param[^>]+name="externalIdentifier"[^>]+value="([\da-z]{8})"'],
|
||||
[r'data-video-player-vpid="(%s)"' % self._ID_REGEX,
|
||||
r'<param[^>]+name="externalIdentifier"[^>]+value="(%s)"' % self._ID_REGEX,
|
||||
r'videoId\s*:\s*["\'](%s)["\']' % self._ID_REGEX],
|
||||
webpage, 'vpid', default=None)
|
||||
|
||||
if programme_id:
|
||||
@ -816,7 +823,7 @@ class BBCIE(BBCCoUkIE):
|
||||
|
||||
# Multiple video article (e.g.
|
||||
# http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460)
|
||||
EMBED_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:[^/]+/)+[\da-z]{8}(?:\b[^"]+)?'
|
||||
EMBED_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:[^/]+/)+%s(?:\b[^"]+)?' % self._ID_REGEX
|
||||
entries = []
|
||||
for match in extract_all(r'new\s+SMP\(({.+?})\)'):
|
||||
embed_url = match.get('playerSettings', {}).get('externalEmbedUrl')
|
||||
|
||||
@ -1,6 +1,11 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import (
|
||||
compat_chr,
|
||||
compat_ord,
|
||||
compat_urllib_parse_unquote,
|
||||
)
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
parse_iso8601,
|
||||
@ -29,7 +34,24 @@ class BeegIE(InfoExtractor):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
video = self._download_json(
|
||||
'http://beeg.com/api/v1/video/%s' % video_id, video_id)
|
||||
'http://beeg.com/api/v4/video/%s' % video_id, video_id)
|
||||
|
||||
def decrypt_key(key):
|
||||
# Reverse engineered from http://static.beeg.com/cpl/1067.js
|
||||
a = '8RPUUCS35ZWp3ADnKcSmpH71ZusrROo'
|
||||
e = compat_urllib_parse_unquote(key)
|
||||
return ''.join([
|
||||
compat_chr(compat_ord(e[n]) - compat_ord(a[n % len(a)]) % 25)
|
||||
for n in range(len(e))])
|
||||
|
||||
def decrypt_url(encrypted_url):
|
||||
encrypted_url = self._proto_relative_url(
|
||||
encrypted_url.replace('{DATA_MARKERS}', ''), 'http:')
|
||||
key = self._search_regex(
|
||||
r'/key=(.*?)%2Cend=', encrypted_url, 'key', default=None)
|
||||
if not key:
|
||||
return encrypted_url
|
||||
return encrypted_url.replace(key, decrypt_key(key))
|
||||
|
||||
formats = []
|
||||
for format_id, video_url in video.items():
|
||||
@ -40,7 +62,7 @@ class BeegIE(InfoExtractor):
|
||||
if not height:
|
||||
continue
|
||||
formats.append({
|
||||
'url': self._proto_relative_url(video_url.replace('{DATA_MARKERS}', ''), 'http:'),
|
||||
'url': decrypt_url(video_url),
|
||||
'format_id': format_id,
|
||||
'height': int(height),
|
||||
})
|
||||
|
||||
@ -2,143 +2,109 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
import itertools
|
||||
import json
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import (
|
||||
compat_etree_fromstring,
|
||||
)
|
||||
from ..compat import compat_str
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
unified_strdate,
|
||||
unescapeHTML,
|
||||
ExtractorError,
|
||||
xpath_text,
|
||||
)
|
||||
|
||||
|
||||
class BiliBiliIE(InfoExtractor):
|
||||
_VALID_URL = r'http://www\.bilibili\.(?:tv|com)/video/av(?P<id>[0-9]+)/'
|
||||
_VALID_URL = r'http://www\.bilibili\.(?:tv|com)/video/av(?P<id>\d+)(?:/index_(?P<page_num>\d+).html)?'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://www.bilibili.tv/video/av1074402/',
|
||||
'md5': '2c301e4dab317596e837c3e7633e7d86',
|
||||
'info_dict': {
|
||||
'id': '1074402_part1',
|
||||
'id': '1554319',
|
||||
'ext': 'flv',
|
||||
'title': '【金坷垃】金泡沫',
|
||||
'duration': 308,
|
||||
'duration': 308313,
|
||||
'upload_date': '20140420',
|
||||
'thumbnail': 're:^https?://.+\.jpg',
|
||||
'description': 'md5:ce18c2a2d2193f0df2917d270f2e5923',
|
||||
'timestamp': 1397983878,
|
||||
'uploader': '菊子桑',
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.bilibili.com/video/av1041170/',
|
||||
'info_dict': {
|
||||
'id': '1041170',
|
||||
'title': '【BD1080P】刀语【诸神&异域】',
|
||||
'description': '这是个神奇的故事~每个人不留弹幕不给走哦~切利哦！~',
|
||||
'uploader': '枫叶逝去',
|
||||
'timestamp': 1396501299,
|
||||
},
|
||||
'playlist_count': 9,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
page_num = mobj.group('page_num') or '1'
|
||||
|
||||
if '(此视频不存在或被删除)' in webpage:
|
||||
raise ExtractorError(
|
||||
'The video does not exist or was deleted', expected=True)
|
||||
view_data = self._download_json(
|
||||
'http://api.bilibili.com/view?type=json&appkey=8e9fc618fbd41e28&id=%s&page=%s' % (video_id, page_num),
|
||||
video_id)
|
||||
if 'error' in view_data:
|
||||
raise ExtractorError('%s said: %s' % (self.IE_NAME, view_data['error']), expected=True)
|
||||
|
||||
if '>你没有权限浏览！ 由于版权相关问题 我们不对您所在的地区提供服务<' in webpage:
|
||||
raise ExtractorError(
|
||||
'The video is not available in your region due to copyright reasons',
|
||||
expected=True)
|
||||
cid = view_data['cid']
|
||||
title = unescapeHTML(view_data['title'])
|
||||
|
||||
video_code = self._search_regex(
|
||||
r'(?s)<div itemprop="video".*?>(.*?)</div>', webpage, 'video code')
|
||||
doc = self._download_xml(
|
||||
'http://interface.bilibili.com/v_cdn_play?appkey=8e9fc618fbd41e28&cid=%s' % cid,
|
||||
cid,
|
||||
'Downloading page %s/%s' % (page_num, view_data['pages'])
|
||||
)
|
||||
|
||||
title = self._html_search_meta(
|
||||
'media:title', video_code, 'title', fatal=True)
|
||||
duration_str = self._html_search_meta(
|
||||
'duration', video_code, 'duration')
|
||||
if duration_str is None:
|
||||
duration = None
|
||||
else:
|
||||
duration_mobj = re.match(
|
||||
r'^T(?:(?P<hours>[0-9]+)H)?(?P<minutes>[0-9]+)M(?P<seconds>[0-9]+)S$',
|
||||
duration_str)
|
||||
duration = (
|
||||
int_or_none(duration_mobj.group('hours'), default=0) * 3600 +
|
||||
int(duration_mobj.group('minutes')) * 60 +
|
||||
int(duration_mobj.group('seconds')))
|
||||
upload_date = unified_strdate(self._html_search_meta(
|
||||
'uploadDate', video_code, fatal=False))
|
||||
thumbnail = self._html_search_meta(
|
||||
'thumbnailUrl', video_code, 'thumbnail', fatal=False)
|
||||
|
||||
cid = self._search_regex(r'cid=(\d+)', webpage, 'cid')
|
||||
if xpath_text(doc, './result') == 'error':
|
||||
raise ExtractorError('%s said: %s' % (self.IE_NAME, xpath_text(doc, './message')), expected=True)
|
||||
|
||||
entries = []
|
||||
|
||||
lq_page = self._download_webpage(
|
||||
'http://interface.bilibili.com/v_cdn_play?appkey=1&cid=%s' % cid,
|
||||
video_id,
|
||||
note='Downloading LQ video info'
|
||||
)
|
||||
try:
|
||||
err_info = json.loads(lq_page)
|
||||
raise ExtractorError(
|
||||
'BiliBili said: ' + err_info['error_text'], expected=True)
|
||||
except ValueError:
|
||||
pass
|
||||
|
||||
lq_doc = compat_etree_fromstring(lq_page)
|
||||
lq_durls = lq_doc.findall('./durl')
|
||||
|
||||
hq_doc = self._download_xml(
|
||||
'http://interface.bilibili.com/playurl?appkey=1&cid=%s' % cid,
|
||||
video_id,
|
||||
note='Downloading HQ video info',
|
||||
fatal=False,
|
||||
)
|
||||
if hq_doc is not False:
|
||||
hq_durls = hq_doc.findall('./durl')
|
||||
assert len(lq_durls) == len(hq_durls)
|
||||
else:
|
||||
hq_durls = itertools.repeat(None)
|
||||
|
||||
i = 1
|
||||
for lq_durl, hq_durl in zip(lq_durls, hq_durls):
|
||||
for durl in doc.findall('./durl'):
|
||||
size = xpath_text(durl, ['./filesize', './size'])
|
||||
formats = [{
|
||||
'format_id': 'lq',
|
||||
'quality': 1,
|
||||
'url': lq_durl.find('./url').text,
|
||||
'filesize': int_or_none(
|
||||
lq_durl.find('./size'), get_attr='text'),
|
||||
'url': durl.find('./url').text,
|
||||
'filesize': int_or_none(size),
|
||||
'ext': 'flv',
|
||||
}]
|
||||
if hq_durl is not None:
|
||||
formats.append({
|
||||
'format_id': 'hq',
|
||||
'quality': 2,
|
||||
'ext': 'flv',
|
||||
'url': hq_durl.find('./url').text,
|
||||
'filesize': int_or_none(
|
||||
hq_durl.find('./size'), get_attr='text'),
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
backup_urls = durl.find('./backup_url')
|
||||
if backup_urls is not None:
|
||||
for backup_url in backup_urls.findall('./url'):
|
||||
formats.append({'url': backup_url.text})
|
||||
formats.reverse()
|
||||
|
||||
entries.append({
|
||||
'id': '%s_part%d' % (video_id, i),
|
||||
'id': '%s_part%s' % (cid, xpath_text(durl, './order')),
|
||||
'title': title,
|
||||
'duration': int_or_none(xpath_text(durl, './length'), 1000),
|
||||
'formats': formats,
|
||||
'duration': duration,
|
||||
'upload_date': upload_date,
|
||||
'thumbnail': thumbnail,
|
||||
})
|
||||
|
||||
i += 1
|
||||
|
||||
return {
|
||||
'_type': 'multi_video',
|
||||
'entries': entries,
|
||||
'id': video_id,
|
||||
'title': title
|
||||
info = {
|
||||
'id': compat_str(cid),
|
||||
'title': title,
|
||||
'description': view_data.get('description'),
|
||||
'thumbnail': view_data.get('pic'),
|
||||
'uploader': view_data.get('author'),
|
||||
'timestamp': int_or_none(view_data.get('created')),
|
||||
'view_count': int_or_none(view_data.get('play')),
|
||||
'duration': int_or_none(xpath_text(doc, './timelength')),
|
||||
}
|
||||
|
||||
if len(entries) == 1:
|
||||
entries[0].update(info)
|
||||
return entries[0]
|
||||
else:
|
||||
info.update({
|
||||
'_type': 'multi_video',
|
||||
'id': video_id,
|
||||
'entries': entries,
|
||||
})
|
||||
return info
|
||||
|
||||
@ -6,7 +6,7 @@ from .common import InfoExtractor
|
||||
|
||||
|
||||
class BloombergIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://www\.bloomberg\.com/news/[^/]+/[^/]+/(?P<id>[^/?#]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?bloomberg\.com/(?:[^/]+/)*(?P<id>[^/?#]+)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://www.bloomberg.com/news/videos/b/aaeae121-5949-481e-a1ce-4562db6f5df2',
|
||||
@ -20,22 +20,36 @@ class BloombergIE(InfoExtractor):
|
||||
}, {
|
||||
'url': 'http://www.bloomberg.com/news/articles/2015-11-12/five-strange-things-that-have-been-happening-in-financial-markets',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.bloomberg.com/politics/videos/2015-11-25/karl-rove-on-jeb-bush-s-struggles-stopping-trump',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
name = self._match_id(url)
|
||||
webpage = self._download_webpage(url, name)
|
||||
video_id = self._search_regex(r'"bmmrId":"(.+?)"', webpage, 'id')
|
||||
video_id = self._search_regex(
|
||||
r'["\']bmmrId["\']\s*:\s*(["\'])(?P<url>.+?)\1',
|
||||
webpage, 'id', group='url')
|
||||
title = re.sub(': Video$', '', self._og_search_title(webpage))
|
||||
|
||||
embed_info = self._download_json(
|
||||
'http://www.bloomberg.com/api/embed?id=%s' % video_id, video_id)
|
||||
formats = []
|
||||
for stream in embed_info['streams']:
|
||||
if stream["muxing_format"] == "TS":
|
||||
formats.extend(self._extract_m3u8_formats(stream['url'], video_id))
|
||||
stream_url = stream.get('url')
|
||||
if not stream_url:
|
||||
continue
|
||||
if stream['muxing_format'] == 'TS':
|
||||
m3u8_formats = self._extract_m3u8_formats(
|
||||
stream_url, video_id, 'mp4', m3u8_id='hls', fatal=False)
|
||||
if m3u8_formats:
|
||||
formats.extend(m3u8_formats)
|
||||
else:
|
||||
formats.extend(self._extract_f4m_formats(stream['url'], video_id))
|
||||
f4m_formats = self._extract_f4m_formats(
|
||||
stream_url, video_id, f4m_id='hds', fatal=False)
|
||||
if f4m_formats:
|
||||
formats.extend(f4m_formats)
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
|
||||
@ -14,9 +14,10 @@ class BYUtvIE(InfoExtractor):
|
||||
'info_dict': {
|
||||
'id': 'studio-c-season-5-episode-5',
|
||||
'ext': 'mp4',
|
||||
'description': 'md5:5438d33774b6bdc662f9485a340401cc',
|
||||
'description': 'md5:e07269172baff037f8e8bf9956bc9747',
|
||||
'title': 'Season 5 Episode 5',
|
||||
'thumbnail': 're:^https?://.*\.jpg$'
|
||||
'thumbnail': 're:^https?://.*\.jpg$',
|
||||
'duration': 1486.486,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
|
||||
@ -1,14 +1,9 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
int_or_none,
|
||||
js_to_json,
|
||||
parse_iso8601,
|
||||
remove_end,
|
||||
unified_strdate,
|
||||
)
|
||||
|
||||
|
||||
@ -21,48 +16,47 @@ class ClipfishIE(InfoExtractor):
|
||||
'id': '3966754',
|
||||
'ext': 'mp4',
|
||||
'title': 'FIFA 14 - E3 2013 Trailer',
|
||||
'timestamp': 1370938118,
|
||||
'description': 'Video zu FIFA 14: E3 2013 Trailer',
|
||||
'upload_date': '20130611',
|
||||
'duration': 82,
|
||||
'view_count': int,
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
video_info = self._parse_json(
|
||||
js_to_json(self._html_search_regex(
|
||||
'(?s)videoObject\s*=\s*({.+?});', webpage, 'video object')),
|
||||
video_id)
|
||||
video_info = self._download_json(
|
||||
'http://www.clipfish.de/devapi/id/%s?format=json&apikey=hbbtv' % video_id,
|
||||
video_id)['items'][0]
|
||||
|
||||
formats = []
|
||||
for video_url in re.findall(r'var\s+videourl\s*=\s*"([^"]+)"', webpage):
|
||||
ext = determine_ext(video_url)
|
||||
if ext == 'm3u8':
|
||||
formats.append({
|
||||
'url': video_url.replace('de.hls.fra.clipfish.de', 'hls.fra.clipfish.de'),
|
||||
'ext': 'mp4',
|
||||
'format_id': 'hls',
|
||||
})
|
||||
else:
|
||||
formats.append({
|
||||
'url': video_url,
|
||||
'format_id': ext,
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
title = remove_end(self._og_search_title(webpage), ' - Video')
|
||||
thumbnail = self._og_search_thumbnail(webpage)
|
||||
duration = int_or_none(video_info.get('length'))
|
||||
timestamp = parse_iso8601(self._html_search_meta('uploadDate', webpage, 'upload date'))
|
||||
m3u8_url = video_info.get('media_videourl_hls')
|
||||
if m3u8_url:
|
||||
formats.append({
|
||||
'url': m3u8_url.replace('de.hls.fra.clipfish.de', 'hls.fra.clipfish.de'),
|
||||
'ext': 'mp4',
|
||||
'format_id': 'hls',
|
||||
})
|
||||
|
||||
mp4_url = video_info.get('media_videourl')
|
||||
if mp4_url:
|
||||
formats.append({
|
||||
'url': mp4_url,
|
||||
'format_id': 'mp4',
|
||||
'width': int_or_none(video_info.get('width')),
|
||||
'height': int_or_none(video_info.get('height')),
|
||||
'tbr': int_or_none(video_info.get('bitrate')),
|
||||
})
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'title': video_info['title'],
|
||||
'description': video_info.get('descr'),
|
||||
'formats': formats,
|
||||
'thumbnail': thumbnail,
|
||||
'duration': duration,
|
||||
'timestamp': timestamp,
|
||||
'thumbnail': video_info.get('media_content_thumbnail_large') or video_info.get('media_thumbnail'),
|
||||
'duration': int_or_none(video_info.get('media_length')),
|
||||
'upload_date': unified_strdate(video_info.get('pubDate')),
|
||||
'view_count': int_or_none(video_info.get('media_views'))
|
||||
}
|
||||
|
||||
@ -167,7 +167,7 @@ class InfoExtractor(object):
|
||||
"ext" will be calculated from URL if missing
|
||||
automatic_captions: Like 'subtitles', used by the YoutubeIE for
|
||||
automatically generated captions
|
||||
duration: Length of the video in seconds, as an integer.
|
||||
duration: Length of the video in seconds, as an integer or float.
|
||||
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
|
||||
|
||||
@ -9,6 +9,7 @@ from ..utils import (
|
||||
find_xpath_attr,
|
||||
smuggle_url,
|
||||
determine_ext,
|
||||
ExtractorError,
|
||||
)
|
||||
from .senateisvp import SenateISVPIE
|
||||
|
||||
@ -18,33 +19,32 @@ class CSpanIE(InfoExtractor):
|
||||
IE_DESC = 'C-SPAN'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.c-span.org/video/?313572-1/HolderonV',
|
||||
'md5': '8e44ce11f0f725527daccc453f553eb0',
|
||||
'md5': '94b29a4f131ff03d23471dd6f60b6a1d',
|
||||
'info_dict': {
|
||||
'id': '315139',
|
||||
'ext': 'mp4',
|
||||
'title': 'Attorney General Eric Holder on Voting Rights Act Decision',
|
||||
'description': 'Attorney General Eric Holder spoke to reporters following the Supreme Court decision in Shelby County v. Holder in which the court ruled that the preclearance provisions of the Voting Rights Act could not be enforced until Congress established new guidelines for review.',
|
||||
'description': 'Attorney General Eric Holder speaks to reporters following the Supreme Court decision in [Shelby County v. Holder], in which the court ruled that the preclearance provisions of the Voting Rights Act could not be enforced.',
|
||||
},
|
||||
'skip': 'Regularly fails on travis, for unknown reasons',
|
||||
}, {
|
||||
'url': 'http://www.c-span.org/video/?c4486943/cspan-international-health-care-models',
|
||||
# For whatever reason, the served video alternates between
|
||||
# two different ones
|
||||
'md5': '8e5fbfabe6ad0f89f3012a7943c1287b',
|
||||
'info_dict': {
|
||||
'id': '340723',
|
||||
'id': 'c4486943',
|
||||
'ext': 'mp4',
|
||||
'title': 'International Health Care Models',
|
||||
'title': 'CSPAN - International Health Care Models',
|
||||
'description': 'md5:7a985a2d595dba00af3d9c9f0783c967',
|
||||
}
|
||||
}, {
|
||||
'url': 'http://www.c-span.org/video/?318608-1/gm-ignition-switch-recall',
|
||||
'md5': '446562a736c6bf97118e389433ed88d4',
|
||||
'md5': '2ae5051559169baadba13fc35345ae74',
|
||||
'info_dict': {
|
||||
'id': '342759',
|
||||
'ext': 'mp4',
|
||||
'title': 'General Motors Ignition Switch Recall',
|
||||
'duration': 14848,
|
||||
'description': 'md5:70c7c3b8fa63fa60d42772440596034c'
|
||||
'description': 'md5:118081aedd24bf1d3b68b3803344e7f3'
|
||||
},
|
||||
}, {
|
||||
# Video from senate.gov
|
||||
@ -57,67 +57,77 @@ class CSpanIE(InfoExtractor):
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
page_id = mobj.group('id')
|
||||
webpage = self._download_webpage(url, page_id)
|
||||
video_id = self._search_regex(r'progid=\'?([0-9]+)\'?>', webpage, 'video id')
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
matches = re.search(r'data-(prog|clip)id=\'([0-9]+)\'', webpage)
|
||||
if matches:
|
||||
video_type, video_id = matches.groups()
|
||||
if video_type == 'prog':
|
||||
video_type = 'program'
|
||||
else:
|
||||
senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
|
||||
if senate_isvp_url:
|
||||
title = self._og_search_title(webpage)
|
||||
surl = smuggle_url(senate_isvp_url, {'force_title': title})
|
||||
return self.url_result(surl, 'SenateISVP', video_id, title)
|
||||
|
||||
description = self._html_search_regex(
|
||||
[
|
||||
# The full description
|
||||
r'<div class=\'expandable\'>(.*?)<a href=\'#\'',
|
||||
# If the description is small enough the other div is not
|
||||
# present, otherwise this is a stripped version
|
||||
r'<p class=\'initial\'>(.*?)</p>'
|
||||
],
|
||||
webpage, 'description', flags=re.DOTALL, default=None)
|
||||
def get_text_attr(d, attr):
|
||||
return d.get(attr, {}).get('#text')
|
||||
|
||||
info_url = 'http://c-spanvideo.org/videoLibrary/assets/player/ajax-player.php?os=android&html5=program&id=' + video_id
|
||||
data = self._download_json(info_url, video_id)
|
||||
data = self._download_json(
|
||||
'http://www.c-span.org/assets/player/ajax-player.php?os=android&html5=%s&id=%s' % (video_type, video_id),
|
||||
video_id)['video']
|
||||
if data['@status'] != 'Success':
|
||||
raise ExtractorError('%s said: %s' % (self.IE_NAME, get_text_attr(data, 'error')), expected=True)
|
||||
|
||||
doc = self._download_xml(
|
||||
'http://www.c-span.org/common/services/flashXml.php?programid=' + video_id,
|
||||
'http://www.c-span.org/common/services/flashXml.php?%sid=%s' % (video_type, video_id),
|
||||
video_id)
|
||||
|
||||
description = self._html_search_meta('description', webpage)
|
||||
|
||||
title = find_xpath_attr(doc, './/string', 'name', 'title').text
|
||||
thumbnail = find_xpath_attr(doc, './/string', 'name', 'poster').text
|
||||
|
||||
senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
|
||||
if senate_isvp_url:
|
||||
surl = smuggle_url(senate_isvp_url, {'force_title': title})
|
||||
return self.url_result(surl, 'SenateISVP', video_id, title)
|
||||
files = data['files']
|
||||
capfile = get_text_attr(data, 'capfile')
|
||||
|
||||
files = data['video']['files']
|
||||
try:
|
||||
capfile = data['video']['capfile']['#text']
|
||||
except KeyError:
|
||||
capfile = None
|
||||
|
||||
entries = [{
|
||||
'id': '%s_%d' % (video_id, partnum + 1),
|
||||
'title': (
|
||||
title if len(files) == 1 else
|
||||
'%s part %d' % (title, partnum + 1)),
|
||||
'url': unescapeHTML(f['path']['#text']),
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
'duration': int_or_none(f.get('length', {}).get('#text')),
|
||||
'subtitles': {
|
||||
'en': [{
|
||||
'url': capfile,
|
||||
'ext': determine_ext(capfile, 'dfxp')
|
||||
}],
|
||||
} if capfile else None,
|
||||
} for partnum, f in enumerate(files)]
|
||||
entries = []
|
||||
for partnum, f in enumerate(files):
|
||||
formats = []
|
||||
for quality in f['qualities']:
|
||||
formats.append({
|
||||
'format_id': '%s-%sp' % (get_text_attr(quality, 'bitrate'), get_text_attr(quality, 'height')),
|
||||
'url': unescapeHTML(get_text_attr(quality, 'file')),
|
||||
'height': int_or_none(get_text_attr(quality, 'height')),
|
||||
'tbr': int_or_none(get_text_attr(quality, 'bitrate')),
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
entries.append({
|
||||
'id': '%s_%d' % (video_id, partnum + 1),
|
||||
'title': (
|
||||
title if len(files) == 1 else
|
||||
'%s part %d' % (title, partnum + 1)),
|
||||
'formats': formats,
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
'duration': int_or_none(get_text_attr(f, 'length')),
|
||||
'subtitles': {
|
||||
'en': [{
|
||||
'url': capfile,
|
||||
'ext': determine_ext(capfile, 'dfxp')
|
||||
}],
|
||||
} if capfile else None,
|
||||
})
|
||||
|
||||
if len(entries) == 1:
|
||||
entry = dict(entries[0])
|
||||
entry['id'] = video_id
|
||||
entry['id'] = 'c' + video_id if video_type == 'clip' else video_id
|
||||
return entry
|
||||
else:
|
||||
return {
|
||||
'_type': 'playlist',
|
||||
'entries': entries,
|
||||
'title': title,
|
||||
'id': video_id,
|
||||
'id': 'c' + video_id if video_type == 'clip' else video_id,
|
||||
}
|
||||
|
||||
@ -13,8 +13,8 @@ from ..utils import (
|
||||
|
||||
|
||||
class DBTVIE(InfoExtractor):
|
||||
_VALID_URL = r'http://dbtv\.no/(?P<id>[0-9]+)#(?P<display_id>.+)'
|
||||
_TEST = {
|
||||
_VALID_URL = r'https?://(?:www\.)?dbtv\.no/(?:(?:lazyplayer|player)/)?(?P<id>[0-9]+)(?:#(?P<display_id>.+))?'
|
||||
_TESTS = [{
|
||||
'url': 'http://dbtv.no/3649835190001#Skulle_teste_ut_fornøyelsespark,_men_kollegaen_var_bare_opptatt_av_bikinikroppen',
|
||||
'md5': 'b89953ed25dacb6edb3ef6c6f430f8bc',
|
||||
'info_dict': {
|
||||
@ -30,12 +30,18 @@ class DBTVIE(InfoExtractor):
|
||||
'view_count': int,
|
||||
'categories': list,
|
||||
}
|
||||
}
|
||||
}, {
|
||||
'url': 'http://dbtv.no/3649835190001',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.dbtv.no/lazyplayer/4631135248001',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
display_id = mobj.group('display_id')
|
||||
display_id = mobj.group('display_id') or video_id
|
||||
|
||||
data = self._download_json(
|
||||
'http://api.dbtv.no/discovery/%s' % video_id, display_id)
|
||||
|
||||
@ -164,7 +164,7 @@ class FacebookIE(InfoExtractor):
|
||||
if not video_title:
|
||||
video_title = self._html_search_regex(
|
||||
r'(?s)<span class="fbPhotosPhotoCaption".*?id="fbPhotoPageCaption"><span class="hasCaption">(.*?)</span>',
|
||||
webpage, 'alternative title', fatal=False)
|
||||
webpage, 'alternative title', default=None)
|
||||
video_title = limit_length(video_title, 80)
|
||||
if not video_title:
|
||||
video_title = 'Facebook video #%s' % video_id
|
||||
|
||||
@ -37,8 +37,8 @@ class FC2IE(InfoExtractor):
|
||||
'params': {
|
||||
'username': 'ytdl@yt-dl.org',
|
||||
'password': '(snip)',
|
||||
'skip': 'requires actual password'
|
||||
}
|
||||
},
|
||||
'skip': 'requires actual password',
|
||||
}, {
|
||||
'url': 'http://video.fc2.com/en/a/content/20130926eZpARwsF',
|
||||
'only_matching': True,
|
||||
|
||||
43
youtube_dl/extractor/gameinformer.py
Normal file
43
youtube_dl/extractor/gameinformer.py
Normal file
@ -0,0 +1,43 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_str
|
||||
from ..utils import int_or_none
|
||||
|
||||
|
||||
class GameInformerIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?gameinformer\.com/(?:[^/]+/)*(?P<id>.+)\.aspx'
|
||||
_TEST = {
|
||||
'url': 'http://www.gameinformer.com/b/features/archive/2015/09/26/replay-animal-crossing.aspx',
|
||||
'info_dict': {
|
||||
'id': '4515472681001',
|
||||
'ext': 'm3u8',
|
||||
'title': 'Replay - Animal Crossing',
|
||||
'description': 'md5:2e211891b215c85d061adc7a4dd2d930',
|
||||
'timestamp': 1443457610706,
|
||||
},
|
||||
'params': {
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
bc_api_url = self._search_regex(r"getVideo\('([^']+)'", webpage, 'brightcove api url')
|
||||
json_data = self._download_json(
|
||||
bc_api_url + '&video_fields=id,name,shortDescription,publishedDate,videoStillURL,length,IOSRenditions',
|
||||
display_id)
|
||||
|
||||
return {
|
||||
'id': compat_str(json_data['id']),
|
||||
'display_id': display_id,
|
||||
'url': json_data['IOSRenditions'][0]['url'],
|
||||
'title': json_data['name'],
|
||||
'description': json_data.get('shortDescription'),
|
||||
'timestamp': int_or_none(json_data.get('publishedDate')),
|
||||
'duration': int_or_none(json_data.get('length')),
|
||||
}
|
||||
@ -1,19 +1,62 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .mtv import MTVServicesInfoExtractor
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
parse_age_limit,
|
||||
url_basename,
|
||||
)
|
||||
|
||||
|
||||
class GametrailersIE(MTVServicesInfoExtractor):
|
||||
_VALID_URL = r'http://www\.gametrailers\.com/(?P<type>videos|reviews|full-episodes)/(?P<id>.*?)/(?P<title>.*)'
|
||||
class GametrailersIE(InfoExtractor):
|
||||
_VALID_URL = r'http://www\.gametrailers\.com/videos/view/[^/]+/(?P<id>.+)'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://www.gametrailers.com/videos/zbvr8i/mirror-s-edge-2-e3-2013--debut-trailer',
|
||||
'md5': '4c8e67681a0ea7ec241e8c09b3ea8cf7',
|
||||
'url': 'http://www.gametrailers.com/videos/view/gametrailers-com/116437-Just-Cause-3-Review',
|
||||
'md5': 'f28c4efa0bdfaf9b760f6507955b6a6a',
|
||||
'info_dict': {
|
||||
'id': '70e9a5d7-cf25-4a10-9104-6f3e7342ae0d',
|
||||
'id': '2983958',
|
||||
'ext': 'mp4',
|
||||
'title': 'E3 2013: Debut Trailer',
|
||||
'description': 'Faith is back! Check out the World Premiere trailer for Mirror\'s Edge 2 straight from the EA Press Conference at E3 2013!',
|
||||
'display_id': '116437-Just-Cause-3-Review',
|
||||
'title': 'Just Cause 3 - Review',
|
||||
'description': 'It\'s a lot of fun to shoot at things and then watch them explode in Just Cause 3, but should there be more to the experience than that?',
|
||||
},
|
||||
}
|
||||
|
||||
_FEED_URL = 'http://www.gametrailers.com/feeds/mrss'
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
title = self._html_search_regex(
|
||||
r'<title>(.+?)\|', webpage, 'title').strip()
|
||||
embed_url = self._proto_relative_url(
|
||||
self._search_regex(
|
||||
r'src=\'(//embed.gametrailers.com/embed/[^\']+)\'', webpage,
|
||||
'embed url'),
|
||||
scheme='http:')
|
||||
video_id = url_basename(embed_url)
|
||||
embed_page = self._download_webpage(embed_url, video_id)
|
||||
embed_vars_json = self._search_regex(
|
||||
r'(?s)var embedVars = (\{.*?\})\s*</script>', embed_page,
|
||||
'embed vars')
|
||||
info = self._parse_json(embed_vars_json, video_id)
|
||||
|
||||
formats = []
|
||||
for media in info['media']:
|
||||
if media['mediaPurpose'] == 'play':
|
||||
formats.append({
|
||||
'url': media['uri'],
|
||||
'height': media['height'],
|
||||
'width:': media['width'],
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'display_id': display_id,
|
||||
'title': title,
|
||||
'formats': formats,
|
||||
'thumbnail': info.get('thumbUri'),
|
||||
'description': self._og_search_description(webpage),
|
||||
'duration': int_or_none(info.get('videoLengthInSeconds')),
|
||||
'age_limit': parse_age_limit(info.get('audienceRating')),
|
||||
}
|
||||
|
||||
@ -339,6 +339,7 @@ class GenericIE(InfoExtractor):
|
||||
'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
|
||||
'ext': 'mp4',
|
||||
'title': '2cc213299525360.mov', # that's what we get
|
||||
'duration': 238.231,
|
||||
},
|
||||
'add_ie': ['Ooyala'],
|
||||
},
|
||||
@ -350,6 +351,7 @@ class GenericIE(InfoExtractor):
|
||||
'ext': 'mp4',
|
||||
'title': '"Steve Jobs: Man in the Machine" trailer',
|
||||
'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
|
||||
'duration': 135.427,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
@ -960,8 +962,9 @@ class GenericIE(InfoExtractor):
|
||||
'info_dict': {
|
||||
'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
|
||||
'ext': 'mp4',
|
||||
'description': 'VIDEO: Index/Match versus VLOOKUP.',
|
||||
'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
|
||||
'title': 'This is what separates the Excel masters from the wannabes',
|
||||
'duration': 191.933,
|
||||
},
|
||||
'params': {
|
||||
# m3u8 downloads
|
||||
@ -1501,7 +1504,7 @@ class GenericIE(InfoExtractor):
|
||||
re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
|
||||
re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
|
||||
if mobj is not None:
|
||||
return OoyalaIE._build_url_result(mobj.group('ec'))
|
||||
return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
|
||||
|
||||
# Look for multiple Ooyala embeds on SBN network websites
|
||||
mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
|
||||
@ -1509,7 +1512,7 @@ class GenericIE(InfoExtractor):
|
||||
embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
|
||||
if embeds:
|
||||
return _playlist_from_matches(
|
||||
embeds, getter=lambda v: OoyalaIE._url_for_embed_code(v['provider_video_id']), ie='Ooyala')
|
||||
embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
|
||||
|
||||
# Look for Aparat videos
|
||||
mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
|
||||
|
||||
@ -18,6 +18,8 @@ class GrouponIE(InfoExtractor):
|
||||
'id': 'tubGNycTo_9Uxg82uESj4i61EYX8nyuf',
|
||||
'ext': 'mp4',
|
||||
'title': 'Bikram Yoga Huntington Beach | Orange County',
|
||||
'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
|
||||
'duration': 44.961,
|
||||
},
|
||||
}],
|
||||
'params': {
|
||||
|
||||
@ -16,6 +16,7 @@ class HowcastIE(InfoExtractor):
|
||||
'description': 'md5:dbe792e5f6f1489027027bf2eba188a3',
|
||||
'timestamp': 1276081287,
|
||||
'upload_date': '20100609',
|
||||
'duration': 56.823,
|
||||
},
|
||||
'params': {
|
||||
# m3u8 download
|
||||
|
||||
@ -28,15 +28,12 @@ class HypemIE(InfoExtractor):
|
||||
track_id = self._match_id(url)
|
||||
|
||||
data = {'ax': 1, 'ts': time.time()}
|
||||
data_encoded = compat_urllib_parse.urlencode(data)
|
||||
complete_url = url + "?" + data_encoded
|
||||
request = sanitized_Request(complete_url)
|
||||
request = sanitized_Request(url + '?' + compat_urllib_parse.urlencode(data))
|
||||
response, urlh = self._download_webpage_handle(
|
||||
request, track_id, 'Downloading webpage with the url')
|
||||
cookie = urlh.headers.get('Set-Cookie', '')
|
||||
|
||||
html_tracks = self._html_search_regex(
|
||||
r'(?ms)<script type="application/json" id="displayList-data">\s*(.*?)\s*</script>',
|
||||
r'(?ms)<script type="application/json" id="displayList-data">(.+?)</script>',
|
||||
response, 'tracks')
|
||||
try:
|
||||
track_list = json.loads(html_tracks)
|
||||
@ -46,15 +43,14 @@ class HypemIE(InfoExtractor):
|
||||
|
||||
key = track['key']
|
||||
track_id = track['id']
|
||||
artist = track['artist']
|
||||
title = track['song']
|
||||
|
||||
serve_url = "http://hypem.com/serve/source/%s/%s" % (track_id, key)
|
||||
request = sanitized_Request(
|
||||
serve_url, '', {'Content-Type': 'application/json'})
|
||||
request.add_header('cookie', cookie)
|
||||
'http://hypem.com/serve/source/%s/%s' % (track_id, key),
|
||||
'', {'Content-Type': 'application/json'})
|
||||
song_data = self._download_json(request, track_id, 'Downloading metadata')
|
||||
final_url = song_data["url"]
|
||||
final_url = song_data['url']
|
||||
artist = track.get('artist')
|
||||
|
||||
return {
|
||||
'id': track_id,
|
||||
|
||||
@ -205,9 +205,8 @@ class IqiyiIE(InfoExtractor):
|
||||
|
||||
def get_enc_key(self, swf_url, video_id):
|
||||
# TODO: automatic key extraction
|
||||
# last update at 2015-10-22 for Zombie::bite
|
||||
# '7223c67061dbea1259d0ceb44f44b6d62288f4f80c972170de5201d2321060270e05'[2:66][0::2]
|
||||
enc_key = '2c76de15dcb44bd28ff0927d50d31620'
|
||||
# last update at 2015-12-06 for Zombie::bite
|
||||
enc_key = '3719f6a1da83ee0aee3488d8802d7696'[::-1]
|
||||
return enc_key
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
||||
@ -1,23 +1,25 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import os
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_urllib_parse_urlparse
|
||||
from ..utils import sanitized_Request
|
||||
from ..utils import (
|
||||
sanitized_Request,
|
||||
url_basename,
|
||||
)
|
||||
|
||||
|
||||
class KeezMoviesIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?keezmovies\.com/video/.+?(?P<id>[0-9]+)(?:[/?&]|$)'
|
||||
_TEST = {
|
||||
'url': 'http://www.keezmovies.com/video/petite-asian-lady-mai-playing-in-bathtub-1214711',
|
||||
'md5': '6e297b7e789329923fcf83abb67c9289',
|
||||
'md5': '1c1e75d22ffa53320f45eeb07bc4cdc0',
|
||||
'info_dict': {
|
||||
'id': '1214711',
|
||||
'ext': 'mp4',
|
||||
'title': 'Petite Asian Lady Mai Playing In Bathtub',
|
||||
'age_limit': 18,
|
||||
'thumbnail': 're:^https?://.*\.jpg$',
|
||||
}
|
||||
}
|
||||
|
||||
@ -36,21 +38,29 @@ class KeezMoviesIE(InfoExtractor):
|
||||
|
||||
video_title = self._html_search_regex(
|
||||
r'<h1 [^>]*>([^<]+)', webpage, 'title')
|
||||
video_url = self._html_search_regex(
|
||||
r'(?s)html5VideoPlayer = .*?src="([^"]+)"', webpage, 'video URL')
|
||||
path = compat_urllib_parse_urlparse(video_url).path
|
||||
extension = os.path.splitext(path)[1][1:]
|
||||
format = path.split('/')[4].split('_')[:2]
|
||||
format = "-".join(format)
|
||||
flashvars = self._parse_json(self._search_regex(
|
||||
r'var\s+flashvars\s*=\s*([^;]+);', webpage, 'flashvars'), video_id)
|
||||
|
||||
formats = []
|
||||
for height in (180, 240, 480):
|
||||
if flashvars.get('quality_%dp' % height):
|
||||
video_url = flashvars['quality_%dp' % height]
|
||||
a_format = {
|
||||
'url': video_url,
|
||||
'height': height,
|
||||
'format_id': '%dp' % height,
|
||||
}
|
||||
filename_parts = url_basename(video_url).split('_')
|
||||
if len(filename_parts) >= 2 and re.match(r'\d+[Kk]', filename_parts[1]):
|
||||
a_format['tbr'] = int(filename_parts[1][:-1])
|
||||
formats.append(a_format)
|
||||
|
||||
age_limit = self._rta_search(webpage)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': video_title,
|
||||
'url': video_url,
|
||||
'ext': extension,
|
||||
'format': format,
|
||||
'format_id': format,
|
||||
'formats': formats,
|
||||
'age_limit': age_limit,
|
||||
'thumbnail': flashvars.get('image_url')
|
||||
}
|
||||
|
||||
@ -154,10 +154,10 @@ class MetacafeIE(InfoExtractor):
|
||||
# Extract URL, uploader and title from webpage
|
||||
self.report_extraction(video_id)
|
||||
video_url = None
|
||||
mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
|
||||
mobj = re.search(r'(?m)&(?:media|video)URL=([^&]+)', webpage)
|
||||
if mobj is not None:
|
||||
mediaURL = compat_urllib_parse_unquote(mobj.group(1))
|
||||
video_ext = mediaURL[-3:]
|
||||
video_ext = determine_ext(mediaURL)
|
||||
|
||||
# Extract gdaKey if available
|
||||
mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
|
||||
@ -229,7 +229,7 @@ class MetacafeIE(InfoExtractor):
|
||||
|
||||
age_limit = (
|
||||
18
|
||||
if re.search(r'"contentRating":"restricted"', webpage)
|
||||
if re.search(r'(?:"contentRating":|"rating",)"restricted"', webpage)
|
||||
else 0)
|
||||
|
||||
if isinstance(video_url, list):
|
||||
|
||||
@ -79,7 +79,8 @@ class MixcloudIE(InfoExtractor):
|
||||
preview_url = self._search_regex(
|
||||
r'\s(?:data-preview-url|m-preview)="([^"]+)"', webpage, 'preview url', default=None)
|
||||
if preview_url is not None:
|
||||
song_url = preview_url.replace('/previews/', '/c/originals/')
|
||||
song_url = re.sub(r'audiocdn(\d+)', r'stream\1', preview_url)
|
||||
song_url = song_url.replace('/previews/', '/c/originals/')
|
||||
if not self._check_url(song_url, track_id, 'mp3'):
|
||||
song_url = song_url.replace('.mp3', '.m4a').replace('originals/', 'm4a/64/')
|
||||
if not self._check_url(song_url, track_id, 'm4a'):
|
||||
|
||||
@ -1,27 +0,0 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .novamov import NovaMovIE
|
||||
|
||||
|
||||
class MovShareIE(NovaMovIE):
|
||||
IE_NAME = 'movshare'
|
||||
IE_DESC = 'MovShare'
|
||||
|
||||
_VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'movshare\.(?:net|sx|ag)'}
|
||||
|
||||
_HOST = 'www.movshare.net'
|
||||
|
||||
_FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
|
||||
_TITLE_REGEX = r'<strong>Title:</strong> ([^<]+)</p>'
|
||||
_DESCRIPTION_REGEX = r'<strong>Description:</strong> ([^<]+)</p>'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://www.movshare.net/video/559e28be54d96',
|
||||
'md5': 'abd31a2132947262c50429e1d16c1bfd',
|
||||
'info_dict': {
|
||||
'id': '559e28be54d96',
|
||||
'ext': 'flv',
|
||||
'title': 'dissapeared image',
|
||||
'description': 'optical illusion dissapeared image magic illusion',
|
||||
}
|
||||
}
|
||||
@ -1,63 +1,102 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
remove_end,
|
||||
parse_duration,
|
||||
int_or_none,
|
||||
xpath_text,
|
||||
xpath_attr,
|
||||
)
|
||||
|
||||
|
||||
class NBAIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:watch\.|www\.)?nba\.com/(?:nba/)?video(?P<id>/[^?]*?)/?(?:/index\.html)?(?:\?.*)?$'
|
||||
_VALID_URL = r'https?://(?:watch\.|www\.)?nba\.com/(?P<path>(?:[^/]+/)?video/(?P<id>[^?]*?))/?(?:/index\.html)?(?:\?.*)?$'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.nba.com/video/games/nets/2012/12/04/0021200253-okc-bkn-recap.nba/index.html',
|
||||
'md5': 'c0edcfc37607344e2ff8f13c378c88a4',
|
||||
'md5': '9e7729d3010a9c71506fd1248f74e4f4',
|
||||
'info_dict': {
|
||||
'id': '0021200253-okc-bkn-recap.nba',
|
||||
'ext': 'mp4',
|
||||
'id': '0021200253-okc-bkn-recap',
|
||||
'ext': 'flv',
|
||||
'title': 'Thunder vs. Nets',
|
||||
'description': 'Kevin Durant scores 32 points and dishes out six assists as the Thunder beat the Nets in Brooklyn.',
|
||||
'duration': 181,
|
||||
'timestamp': 1354638466,
|
||||
'upload_date': '20121204',
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.nba.com/video/games/hornets/2014/12/05/0021400276-nyk-cha-play5.nba/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://watch.nba.com/nba/video/channels/playoffs/2015/05/20/0041400301-cle-atl-recap.nba',
|
||||
'url': 'http://watch.nba.com/video/channels/playoffs/2015/05/20/0041400301-cle-atl-recap.nba',
|
||||
'md5': 'b2b39b81cf28615ae0c3360a3f9668c4',
|
||||
'info_dict': {
|
||||
'id': '0041400301-cle-atl-recap.nba',
|
||||
'id': '0041400301-cle-atl-recap',
|
||||
'ext': 'mp4',
|
||||
'title': 'NBA GAME TIME | Video: Hawks vs. Cavaliers Game 1',
|
||||
'title': 'Hawks vs. Cavaliers Game 1',
|
||||
'description': 'md5:8094c3498d35a9bd6b1a8c396a071b4d',
|
||||
'duration': 228,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
'timestamp': 1432134543,
|
||||
'upload_date': '20150520',
|
||||
}
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
path, video_id = re.match(self._VALID_URL, url).groups()
|
||||
if path.startswith('nba/'):
|
||||
path = path[3:]
|
||||
video_info = self._download_xml('http://www.nba.com/%s.xml' % path, video_id)
|
||||
video_id = xpath_text(video_info, 'slug')
|
||||
title = xpath_text(video_info, 'headline')
|
||||
description = xpath_text(video_info, 'description')
|
||||
duration = parse_duration(xpath_text(video_info, 'length'))
|
||||
timestamp = int_or_none(xpath_attr(video_info, 'dateCreated', 'uts'))
|
||||
|
||||
video_url = 'http://ht-mobile.cdn.turner.com/nba/big' + video_id + '_nba_1280x720.mp4'
|
||||
thumbnails = []
|
||||
for image in video_info.find('images'):
|
||||
thumbnails.append({
|
||||
'id': image.attrib.get('cut'),
|
||||
'url': image.text,
|
||||
'width': int_or_none(image.attrib.get('width')),
|
||||
'height': int_or_none(image.attrib.get('height')),
|
||||
})
|
||||
|
||||
shortened_video_id = video_id.rpartition('/')[2]
|
||||
title = remove_end(
|
||||
self._og_search_title(webpage, default=shortened_video_id), ' : NBA.com')
|
||||
|
||||
description = self._og_search_description(webpage)
|
||||
duration_str = self._html_search_meta(
|
||||
'duration', webpage, 'duration', default=None)
|
||||
if not duration_str:
|
||||
duration_str = self._html_search_regex(
|
||||
r'Duration:</b>\s*(\d+:\d+)', webpage, 'duration', fatal=False)
|
||||
duration = parse_duration(duration_str)
|
||||
formats = []
|
||||
for video_file in video_info.findall('.//file'):
|
||||
video_url = video_file.text
|
||||
if video_url.startswith('/'):
|
||||
continue
|
||||
if video_url.endswith('.m3u8'):
|
||||
m3u8_formats = self._extract_m3u8_formats(video_url, video_id, m3u8_id='hls', fatal=False)
|
||||
if m3u8_formats:
|
||||
formats.extend(m3u8_formats)
|
||||
elif video_url.endswith('.f4m'):
|
||||
f4m_formats = self._extract_f4m_formats(video_url + '?hdcore=3.4.1.1', video_id, f4m_id='hds', fatal=False)
|
||||
if f4m_formats:
|
||||
formats.extend(f4m_formats)
|
||||
else:
|
||||
key = video_file.attrib.get('bitrate')
|
||||
format_info = {
|
||||
'format_id': key,
|
||||
'url': video_url,
|
||||
}
|
||||
mobj = re.search(r'(\d+)x(\d+)(?:_(\d+))?', key)
|
||||
if mobj:
|
||||
format_info.update({
|
||||
'width': int(mobj.group(1)),
|
||||
'height': int(mobj.group(2)),
|
||||
'tbr': int_or_none(mobj.group(3)),
|
||||
})
|
||||
formats.append(format_info)
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': shortened_video_id,
|
||||
'url': video_url,
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'duration': duration,
|
||||
'timestamp': timestamp,
|
||||
'thumbnails': thumbnails,
|
||||
'formats': formats,
|
||||
}
|
||||
|
||||
@ -92,3 +92,89 @@ class NovaMovIE(InfoExtractor):
|
||||
'title': title,
|
||||
'description': description
|
||||
}
|
||||
|
||||
|
||||
class WholeCloudIE(NovaMovIE):
|
||||
IE_NAME = 'wholecloud'
|
||||
IE_DESC = 'WholeCloud'
|
||||
|
||||
_VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': '(?:wholecloud\.net|movshare\.(?:net|sx|ag))'}
|
||||
|
||||
_HOST = 'www.wholecloud.net'
|
||||
|
||||
_FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
|
||||
_TITLE_REGEX = r'<strong>Title:</strong> ([^<]+)</p>'
|
||||
_DESCRIPTION_REGEX = r'<strong>Description:</strong> ([^<]+)</p>'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://www.wholecloud.net/video/559e28be54d96',
|
||||
'md5': 'abd31a2132947262c50429e1d16c1bfd',
|
||||
'info_dict': {
|
||||
'id': '559e28be54d96',
|
||||
'ext': 'flv',
|
||||
'title': 'dissapeared image',
|
||||
'description': 'optical illusion dissapeared image magic illusion',
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
class NowVideoIE(NovaMovIE):
|
||||
IE_NAME = 'nowvideo'
|
||||
IE_DESC = 'NowVideo'
|
||||
|
||||
_VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'nowvideo\.(?:to|ch|ec|sx|eu|at|ag|co|li)'}
|
||||
|
||||
_HOST = 'www.nowvideo.to'
|
||||
|
||||
_FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
|
||||
_FILEKEY_REGEX = r'var fkzd="([^"]+)";'
|
||||
_TITLE_REGEX = r'<h4>([^<]+)</h4>'
|
||||
_DESCRIPTION_REGEX = r'</h4>\s*<p>([^<]+)</p>'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://www.nowvideo.to/video/0mw0yow7b6dxa',
|
||||
'md5': 'f8fbbc8add72bd95b7850c6a02fc8817',
|
||||
'info_dict': {
|
||||
'id': '0mw0yow7b6dxa',
|
||||
'ext': 'flv',
|
||||
'title': 'youtubedl test video _BaW_jenozKc.mp4',
|
||||
'description': 'Description',
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
class VideoWeedIE(NovaMovIE):
|
||||
IE_NAME = 'videoweed'
|
||||
IE_DESC = 'VideoWeed'
|
||||
|
||||
_VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'videoweed\.(?:es|com)'}
|
||||
|
||||
_HOST = 'www.videoweed.es'
|
||||
|
||||
_FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
|
||||
_TITLE_REGEX = r'<h1 class="text_shadow">([^<]+)</h1>'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://www.videoweed.es/file/b42178afbea14',
|
||||
'md5': 'abd31a2132947262c50429e1d16c1bfd',
|
||||
'info_dict': {
|
||||
'id': 'b42178afbea14',
|
||||
'ext': 'flv',
|
||||
'title': 'optical illusion dissapeared image magic illusion',
|
||||
'description': ''
|
||||
},
|
||||
}
|
||||
|
||||
|
||||
class CloudTimeIE(NovaMovIE):
|
||||
IE_NAME = 'cloudtime'
|
||||
IE_DESC = 'CloudTime'
|
||||
|
||||
_VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'cloudtime\.to'}
|
||||
|
||||
_HOST = 'www.cloudtime.to'
|
||||
|
||||
_FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
|
||||
_TITLE_REGEX = r'<div[^>]+class=["\']video_det["\'][^>]*>\s*<strong>([^<]+)</strong>'
|
||||
|
||||
_TEST = None
|
||||
|
||||
@ -71,7 +71,7 @@ class NowTVBaseIE(InfoExtractor):
|
||||
|
||||
|
||||
class NowTVIE(NowTVBaseIE):
|
||||
_VALID_URL = r'https?://(?:www\.)?nowtv\.(?:de|at|ch)/(?:rtl|rtl2|rtlnitro|superrtl|ntv|vox)/(?P<show_id>[^/]+)/(?:list/[^/]+/)?(?P<id>[^/]+)/(?:player|preview)'
|
||||
_VALID_URL = r'https?://(?:www\.)?nowtv\.(?:de|at|ch)/(?:rtl|rtl2|rtlnitro|superrtl|ntv|vox)/(?P<show_id>[^/]+)/(?:(?:list/[^/]+|jahr/\d{4}/\d{1,2})/)?(?P<id>[^/]+)/(?:player|preview)'
|
||||
|
||||
_TESTS = [{
|
||||
# rtl
|
||||
@ -190,6 +190,9 @@ class NowTVIE(NowTVBaseIE):
|
||||
}, {
|
||||
'url': 'http://www.nowtv.de/rtl2/echtzeit/list/aktuell/schnelles-geld-am-ende-der-welt/player',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.nowtv.de/rtl2/zuhause-im-glueck/jahr/2015/11/eine-erschuetternde-diagnose/player',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
||||
@ -1,28 +0,0 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .novamov import NovaMovIE
|
||||
|
||||
|
||||
class NowVideoIE(NovaMovIE):
|
||||
IE_NAME = 'nowvideo'
|
||||
IE_DESC = 'NowVideo'
|
||||
|
||||
_VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'nowvideo\.(?:to|ch|ec|sx|eu|at|ag|co|li)'}
|
||||
|
||||
_HOST = 'www.nowvideo.to'
|
||||
|
||||
_FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
|
||||
_FILEKEY_REGEX = r'var fkzd="([^"]+)";'
|
||||
_TITLE_REGEX = r'<h4>([^<]+)</h4>'
|
||||
_DESCRIPTION_REGEX = r'</h4>\s*<p>([^<]+)</p>'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://www.nowvideo.ch/video/0mw0yow7b6dxa',
|
||||
'md5': 'f8fbbc8add72bd95b7850c6a02fc8817',
|
||||
'info_dict': {
|
||||
'id': '0mw0yow7b6dxa',
|
||||
'ext': 'flv',
|
||||
'title': 'youtubedl test video _BaW_jenozKc.mp4',
|
||||
'description': 'Description',
|
||||
}
|
||||
}
|
||||
@ -6,6 +6,7 @@ import re
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_urlparse
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
ExtractorError,
|
||||
float_or_none,
|
||||
parse_duration,
|
||||
@ -48,12 +49,22 @@ class NRKIE(InfoExtractor):
|
||||
'http://v8.psapi.nrk.no/mediaelement/%s' % video_id,
|
||||
video_id, 'Downloading media JSON')
|
||||
|
||||
if data['usageRights']['isGeoBlocked']:
|
||||
raise ExtractorError(
|
||||
'NRK har ikke rettigheter til å vise dette programmet utenfor Norge',
|
||||
expected=True)
|
||||
media_url = data.get('mediaUrl')
|
||||
|
||||
video_url = data['mediaUrl'] + '?hdcore=3.5.0&plugin=aasp-3.5.0.151.81'
|
||||
if not media_url:
|
||||
if data['usageRights']['isGeoBlocked']:
|
||||
raise ExtractorError(
|
||||
'NRK har ikke rettigheter til å vise dette programmet utenfor Norge',
|
||||
expected=True)
|
||||
|
||||
if determine_ext(media_url) == 'f4m':
|
||||
formats = self._extract_f4m_formats(
|
||||
media_url + '?hdcore=3.5.0&plugin=aasp-3.5.0.151.81', video_id, f4m_id='hds')
|
||||
else:
|
||||
formats = [{
|
||||
'url': media_url,
|
||||
'ext': 'flv',
|
||||
}]
|
||||
|
||||
duration = parse_duration(data.get('duration'))
|
||||
|
||||
@ -67,12 +78,11 @@ class NRKIE(InfoExtractor):
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'url': video_url,
|
||||
'ext': 'flv',
|
||||
'title': data['title'],
|
||||
'description': data['description'],
|
||||
'duration': duration,
|
||||
'thumbnail': thumbnail,
|
||||
'formats': formats,
|
||||
}
|
||||
|
||||
|
||||
|
||||
@ -1,108 +1,69 @@
|
||||
from __future__ import unicode_literals
|
||||
import re
|
||||
import json
|
||||
import base64
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
unescapeHTML,
|
||||
ExtractorError,
|
||||
determine_ext,
|
||||
int_or_none,
|
||||
float_or_none,
|
||||
ExtractorError,
|
||||
unsmuggle_url,
|
||||
)
|
||||
from ..compat import compat_urllib_parse
|
||||
|
||||
|
||||
class OoyalaBaseIE(InfoExtractor):
|
||||
|
||||
def _extract_result(self, info, more_info):
|
||||
embedCode = info['embedCode']
|
||||
video_url = info.get('ipad_url') or info['url']
|
||||
|
||||
if determine_ext(video_url) == 'm3u8':
|
||||
formats = self._extract_m3u8_formats(video_url, embedCode, ext='mp4')
|
||||
else:
|
||||
formats = [{
|
||||
'url': video_url,
|
||||
'ext': 'mp4',
|
||||
}]
|
||||
|
||||
return {
|
||||
'id': embedCode,
|
||||
'title': unescapeHTML(info['title']),
|
||||
'formats': formats,
|
||||
'description': unescapeHTML(more_info['description']),
|
||||
'thumbnail': more_info['promo'],
|
||||
def _extract(self, content_tree_url, video_id, domain='example.org'):
|
||||
content_tree = self._download_json(content_tree_url, video_id)['content_tree']
|
||||
metadata = content_tree[list(content_tree)[0]]
|
||||
embed_code = metadata['embed_code']
|
||||
pcode = metadata.get('asset_pcode') or embed_code
|
||||
video_info = {
|
||||
'id': embed_code,
|
||||
'title': metadata['title'],
|
||||
'description': metadata.get('description'),
|
||||
'thumbnail': metadata.get('thumbnail_image') or metadata.get('promo_image'),
|
||||
'duration': float_or_none(metadata.get('duration'), 1000),
|
||||
}
|
||||
|
||||
def _extract(self, player_url, video_id):
|
||||
player = self._download_webpage(player_url, video_id)
|
||||
mobile_url = self._search_regex(r'mobile_player_url="(.+?)&device="',
|
||||
player, 'mobile player url')
|
||||
# Looks like some videos are only available for particular devices
|
||||
# (e.g. http://player.ooyala.com/player.js?embedCode=x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0
|
||||
# is only available for ipad)
|
||||
# Working around with fetching URLs for all the devices found starting with 'unknown'
|
||||
# until we succeed or eventually fail for each device.
|
||||
devices = re.findall(r'device\s*=\s*"([^"]+)";', player)
|
||||
devices.remove('unknown')
|
||||
devices.insert(0, 'unknown')
|
||||
for device in devices:
|
||||
mobile_player = self._download_webpage(
|
||||
'%s&device=%s' % (mobile_url, device), video_id,
|
||||
'Downloading mobile player JS for %s device' % device)
|
||||
videos_info = self._search_regex(
|
||||
r'var streams=window.oo_testEnv\?\[\]:eval\("\((\[{.*?}\])\)"\);',
|
||||
mobile_player, 'info', fatal=False, default=None)
|
||||
if videos_info:
|
||||
break
|
||||
|
||||
if not videos_info:
|
||||
formats = []
|
||||
formats = []
|
||||
for supported_format in ('mp4', 'm3u8', 'hds', 'rtmp'):
|
||||
auth_data = self._download_json(
|
||||
'http://player.ooyala.com/sas/player_api/v1/authorization/embed_code/%s/%s?domain=www.example.org&supportedFormats=mp4,webm' % (video_id, video_id),
|
||||
video_id)
|
||||
'http://player.ooyala.com/sas/player_api/v1/authorization/embed_code/%s/%s?' % (pcode, embed_code) + compat_urllib_parse.urlencode({'domain': domain, 'supportedFormats': supported_format}),
|
||||
video_id, 'Downloading %s JSON' % supported_format)
|
||||
|
||||
cur_auth_data = auth_data['authorization_data'][video_id]
|
||||
cur_auth_data = auth_data['authorization_data'][embed_code]
|
||||
|
||||
for stream in cur_auth_data['streams']:
|
||||
formats.append({
|
||||
'url': base64.b64decode(stream['url']['data'].encode('ascii')).decode('utf-8'),
|
||||
'ext': stream.get('delivery_type'),
|
||||
'format': stream.get('video_codec'),
|
||||
'format_id': stream.get('profile'),
|
||||
'width': int_or_none(stream.get('width')),
|
||||
'height': int_or_none(stream.get('height')),
|
||||
'abr': int_or_none(stream.get('audio_bitrate')),
|
||||
'vbr': int_or_none(stream.get('video_bitrate')),
|
||||
})
|
||||
if formats:
|
||||
return {
|
||||
'id': video_id,
|
||||
'formats': formats,
|
||||
'title': 'Ooyala video',
|
||||
}
|
||||
if cur_auth_data['authorized']:
|
||||
for stream in cur_auth_data['streams']:
|
||||
url = base64.b64decode(stream['url']['data'].encode('ascii')).decode('utf-8')
|
||||
delivery_type = stream['delivery_type']
|
||||
if delivery_type == 'remote_asset':
|
||||
video_info['url'] = url
|
||||
return video_info
|
||||
if delivery_type == 'hls':
|
||||
formats.extend(self._extract_m3u8_formats(url, embed_code, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
|
||||
elif delivery_type == 'hds':
|
||||
formats.extend(self._extract_f4m_formats(url, embed_code, -1, 'hds', fatal=False))
|
||||
else:
|
||||
formats.append({
|
||||
'url': url,
|
||||
'ext': stream.get('delivery_type'),
|
||||
'vcodec': stream.get('video_codec'),
|
||||
'format_id': '%s-%s-%sp' % (stream.get('profile'), delivery_type, stream.get('height')),
|
||||
'width': int_or_none(stream.get('width')),
|
||||
'height': int_or_none(stream.get('height')),
|
||||
'abr': int_or_none(stream.get('audio_bitrate')),
|
||||
'vbr': int_or_none(stream.get('video_bitrate')),
|
||||
'fps': float_or_none(stream.get('framerate')),
|
||||
})
|
||||
else:
|
||||
raise ExtractorError('%s said: %s' % (self.IE_NAME, cur_auth_data['message']), expected=True)
|
||||
self._sort_formats(formats)
|
||||
|
||||
if not cur_auth_data['authorized']:
|
||||
raise ExtractorError(cur_auth_data['message'], expected=True)
|
||||
|
||||
if not videos_info:
|
||||
raise ExtractorError('Unable to extract info')
|
||||
videos_info = videos_info.replace('\\"', '"')
|
||||
videos_more_info = self._search_regex(
|
||||
r'eval\("\(({.*?\\"promo\\".*?})\)"', mobile_player, 'more info').replace('\\"', '"')
|
||||
videos_info = json.loads(videos_info)
|
||||
videos_more_info = json.loads(videos_more_info)
|
||||
|
||||
if videos_more_info.get('lineup'):
|
||||
videos = [self._extract_result(info, more_info) for (info, more_info) in zip(videos_info, videos_more_info['lineup'])]
|
||||
return {
|
||||
'_type': 'playlist',
|
||||
'id': video_id,
|
||||
'title': unescapeHTML(videos_more_info['title']),
|
||||
'entries': videos,
|
||||
}
|
||||
else:
|
||||
return self._extract_result(videos_info[0], videos_more_info)
|
||||
video_info['formats'] = formats
|
||||
return video_info
|
||||
|
||||
|
||||
class OoyalaIE(OoyalaBaseIE):
|
||||
@ -117,6 +78,7 @@ class OoyalaIE(OoyalaBaseIE):
|
||||
'ext': 'mp4',
|
||||
'title': 'Explaining Data Recovery from Hard Drives and SSDs',
|
||||
'description': 'How badly damaged does a drive have to be to defeat Russell and his crew? Apparently, smashed to bits.',
|
||||
'duration': 853.386,
|
||||
},
|
||||
}, {
|
||||
# Only available for ipad
|
||||
@ -125,7 +87,7 @@ class OoyalaIE(OoyalaBaseIE):
|
||||
'id': 'x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0',
|
||||
'ext': 'mp4',
|
||||
'title': 'Simulation Overview - Levels of Simulation',
|
||||
'description': '',
|
||||
'duration': 194.948,
|
||||
},
|
||||
},
|
||||
{
|
||||
@ -136,7 +98,8 @@ class OoyalaIE(OoyalaBaseIE):
|
||||
'info_dict': {
|
||||
'id': 'FiOG81ZTrvckcchQxmalf4aQj590qTEx',
|
||||
'ext': 'mp4',
|
||||
'title': 'Ooyala video',
|
||||
'title': 'Divide Tool Path.mp4',
|
||||
'duration': 204.405,
|
||||
}
|
||||
}
|
||||
]
|
||||
@ -151,9 +114,11 @@ class OoyalaIE(OoyalaBaseIE):
|
||||
ie=cls.ie_key())
|
||||
|
||||
def _real_extract(self, url):
|
||||
url, smuggled_data = unsmuggle_url(url, {})
|
||||
embed_code = self._match_id(url)
|
||||
player_url = 'http://player.ooyala.com/player.js?embedCode=%s' % embed_code
|
||||
return self._extract(player_url, embed_code)
|
||||
domain = smuggled_data.get('domain')
|
||||
content_tree_url = 'http://player.ooyala.com/player_api/v1/content_tree/embed_code/%s/%s' % (embed_code, embed_code)
|
||||
return self._extract(content_tree_url, embed_code, domain)
|
||||
|
||||
|
||||
class OoyalaExternalIE(OoyalaBaseIE):
|
||||
@ -170,7 +135,7 @@ class OoyalaExternalIE(OoyalaBaseIE):
|
||||
.*?&pcode=
|
||||
)
|
||||
(?P<pcode>.+?)
|
||||
(&|$)
|
||||
(?:&|$)
|
||||
'''
|
||||
|
||||
_TEST = {
|
||||
@ -179,7 +144,7 @@ class OoyalaExternalIE(OoyalaBaseIE):
|
||||
'id': 'FkYWtmazr6Ed8xmvILvKLWjd4QvYZpzG',
|
||||
'ext': 'mp4',
|
||||
'title': 'dm_140128_30for30Shorts___JudgingJewellv2',
|
||||
'description': '',
|
||||
'duration': 1302000,
|
||||
},
|
||||
'params': {
|
||||
# m3u8 download
|
||||
@ -188,9 +153,6 @@ class OoyalaExternalIE(OoyalaBaseIE):
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
partner_id = mobj.group('partner_id')
|
||||
video_id = mobj.group('id')
|
||||
pcode = mobj.group('pcode')
|
||||
player_url = 'http://player.ooyala.com/player.js?externalId=%s:%s&pcode=%s' % (partner_id, video_id, pcode)
|
||||
return self._extract(player_url, video_id)
|
||||
partner_id, video_id, pcode = re.match(self._VALID_URL, url).groups()
|
||||
content_tree_url = 'http://player.ooyala.com/player_api/v1/content_tree/external_id/%s/%s:%s' % (pcode, partner_id, video_id)
|
||||
return self._extract(content_tree_url, video_id)
|
||||
|
||||
@ -1,5 +1,6 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
import json
|
||||
import random
|
||||
import collections
|
||||
@ -14,6 +15,7 @@ from ..utils import (
|
||||
ExtractorError,
|
||||
int_or_none,
|
||||
parse_duration,
|
||||
qualities,
|
||||
sanitized_Request,
|
||||
)
|
||||
|
||||
@ -140,15 +142,28 @@ class PluralsightIE(PluralsightBaseIE):
|
||||
'low': {'width': 640, 'height': 480},
|
||||
'medium': {'width': 848, 'height': 640},
|
||||
'high': {'width': 1024, 'height': 768},
|
||||
'high-widescreen': {'width': 1280, 'height': 720},
|
||||
}
|
||||
|
||||
QUALITIES_PREFERENCE = ('low', 'medium', 'high', 'high-widescreen',)
|
||||
quality_key = qualities(QUALITIES_PREFERENCE)
|
||||
|
||||
AllowedQuality = collections.namedtuple('AllowedQuality', ['ext', 'qualities'])
|
||||
|
||||
ALLOWED_QUALITIES = (
|
||||
AllowedQuality('webm', ('high',)),
|
||||
AllowedQuality('mp4', ('low', 'medium', 'high',)),
|
||||
AllowedQuality('webm', ['high', ]),
|
||||
AllowedQuality('mp4', ['low', 'medium', 'high', ]),
|
||||
)
|
||||
|
||||
# Some courses also offer widescreen resolution for high quality (see
|
||||
# https://github.com/rg3/youtube-dl/issues/7766)
|
||||
widescreen = True if re.search(
|
||||
r'courseSupportsWidescreenVideoFormats\s*:\s*true', webpage) else False
|
||||
best_quality = 'high-widescreen' if widescreen else 'high'
|
||||
if widescreen:
|
||||
for allowed_quality in ALLOWED_QUALITIES:
|
||||
allowed_quality.qualities.append(best_quality)
|
||||
|
||||
# In order to minimize the number of calls to ViewClip API and reduce
|
||||
# the probability of being throttled or banned by Pluralsight we will request
|
||||
# only single format until formats listing was explicitly requested.
|
||||
@ -157,19 +172,19 @@ class PluralsightIE(PluralsightBaseIE):
|
||||
else:
|
||||
def guess_allowed_qualities():
|
||||
req_format = self._downloader.params.get('format') or 'best'
|
||||
req_format_split = req_format.split('-')
|
||||
req_format_split = req_format.split('-', 1)
|
||||
if len(req_format_split) > 1:
|
||||
req_ext, req_quality = req_format_split
|
||||
for allowed_quality in ALLOWED_QUALITIES:
|
||||
if req_ext == allowed_quality.ext and req_quality in allowed_quality.qualities:
|
||||
return (AllowedQuality(req_ext, (req_quality, )), )
|
||||
req_ext = 'webm' if self._downloader.params.get('prefer_free_formats') else 'mp4'
|
||||
return (AllowedQuality(req_ext, ('high', )), )
|
||||
return (AllowedQuality(req_ext, (best_quality, )), )
|
||||
allowed_qualities = guess_allowed_qualities()
|
||||
|
||||
formats = []
|
||||
for ext, qualities in allowed_qualities:
|
||||
for quality in qualities:
|
||||
for ext, qualities_ in allowed_qualities:
|
||||
for quality in qualities_:
|
||||
f = QUALITIES[quality].copy()
|
||||
clip_post = {
|
||||
'a': author,
|
||||
@ -205,6 +220,7 @@ class PluralsightIE(PluralsightBaseIE):
|
||||
'url': clip_url,
|
||||
'ext': ext,
|
||||
'format_id': format_id,
|
||||
'quality': quality_key(quality),
|
||||
})
|
||||
formats.append(f)
|
||||
self._sort_formats(formats)
|
||||
|
||||
@ -147,7 +147,8 @@ class PornHubPlaylistIE(InfoExtractor):
|
||||
|
||||
entries = [
|
||||
self.url_result('http://www.pornhub.com/%s' % video_url, 'PornHub')
|
||||
for video_url in set(re.findall('href="/?(view_video\.php\?viewkey=\d+[^"]*)"', webpage))
|
||||
for video_url in set(re.findall(
|
||||
r'href="/?(view_video\.php\?.*\bviewkey=[\da-z]+[^"]*)"', webpage))
|
||||
]
|
||||
|
||||
playlist = self._parse_json(
|
||||
|
||||
117
youtube_dl/extractor/skynewsarabia.py
Normal file
117
youtube_dl/extractor/skynewsarabia.py
Normal file
@ -0,0 +1,117 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_str
|
||||
from ..utils import (
|
||||
parse_iso8601,
|
||||
parse_duration,
|
||||
)
|
||||
|
||||
|
||||
class SkyNewsArabiaBaseIE(InfoExtractor):
|
||||
_IMAGE_BASE_URL = 'http://www.skynewsarabia.com/web/images'
|
||||
|
||||
def _call_api(self, path, value):
|
||||
return self._download_json('http://api.skynewsarabia.com/web/rest/v2/%s/%s.json' % (path, value), value)
|
||||
|
||||
def _get_limelight_media_id(self, url):
|
||||
return self._search_regex(r'/media/[^/]+/([a-z0-9]{32})', url, 'limelight media id')
|
||||
|
||||
def _get_image_url(self, image_path_template, width='1600', height='1200'):
|
||||
return self._IMAGE_BASE_URL + image_path_template.format(width=width, height=height)
|
||||
|
||||
def _extract_video_info(self, video_data):
|
||||
video_id = compat_str(video_data['id'])
|
||||
topic = video_data.get('topicTitle')
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'url': 'limelight:media:%s' % self._get_limelight_media_id(video_data['videoUrl'][0]['url']),
|
||||
'id': video_id,
|
||||
'title': video_data['headline'],
|
||||
'description': video_data.get('summary'),
|
||||
'thumbnail': self._get_image_url(video_data['mediaAsset']['imageUrl']),
|
||||
'timestamp': parse_iso8601(video_data.get('date')),
|
||||
'duration': parse_duration(video_data.get('runTime')),
|
||||
'tags': video_data.get('tags', []),
|
||||
'categories': [topic] if topic else [],
|
||||
'webpage_url': 'http://www.skynewsarabia.com/web/video/%s' % video_id,
|
||||
'ie_key': 'LimelightMedia',
|
||||
}
|
||||
|
||||
|
||||
class SkyNewsArabiaIE(SkyNewsArabiaBaseIE):
|
||||
IE_NAME = 'skynewsarabia:video'
|
||||
_VALID_URL = r'https?://(?:www\.)?skynewsarabia\.com/web/video/(?P<id>[0-9]+)'
|
||||
_TEST = {
|
||||
'url': 'http://www.skynewsarabia.com/web/video/794902/%D9%86%D8%B5%D9%81-%D9%85%D9%84%D9%8A%D9%88%D9%86-%D9%85%D8%B5%D8%A8%D8%A7%D8%AD-%D8%B4%D8%AC%D8%B1%D8%A9-%D9%83%D8%B1%D9%8A%D8%B3%D9%85%D8%A7%D8%B3',
|
||||
'info_dict': {
|
||||
'id': '794902',
|
||||
'ext': 'flv',
|
||||
'title': 'نصف مليون مصباح على شجرة كريسماس',
|
||||
'description': 'md5:22f1b27f0850eeb10c7e59b1f16eb7c6',
|
||||
'upload_date': '20151128',
|
||||
'timestamp': 1448697198,
|
||||
'duration': 2119,
|
||||
},
|
||||
'params': {
|
||||
# rtmp download
|
||||
'skip_download': True,
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
video_data = self._call_api('video', video_id)
|
||||
return self._extract_video_info(video_data)
|
||||
|
||||
|
||||
class SkyNewsArabiaArticleIE(SkyNewsArabiaBaseIE):
|
||||
IE_NAME = 'skynewsarabia:video'
|
||||
_VALID_URL = r'https?://(?:www\.)?skynewsarabia\.com/web/article/(?P<id>[0-9]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.skynewsarabia.com/web/article/794549/%D8%A7%D9%94%D8%AD%D8%AF%D8%A7%D8%AB-%D8%A7%D9%84%D8%B4%D8%B1%D9%82-%D8%A7%D9%84%D8%A7%D9%94%D9%88%D8%B3%D8%B7-%D8%AE%D8%B1%D9%8A%D8%B7%D8%A9-%D8%A7%D9%84%D8%A7%D9%94%D9%84%D8%B9%D8%A7%D8%A8-%D8%A7%D9%84%D8%B0%D9%83%D9%8A%D8%A9',
|
||||
'info_dict': {
|
||||
'id': '794549',
|
||||
'ext': 'flv',
|
||||
'title': 'بالفيديو.. ألعاب ذكية تحاكي واقع المنطقة',
|
||||
'description': 'md5:0c373d29919a851e080ee4edd0c5d97f',
|
||||
'upload_date': '20151126',
|
||||
'timestamp': 1448559336,
|
||||
'duration': 281.6,
|
||||
},
|
||||
'params': {
|
||||
# rtmp download
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.skynewsarabia.com/web/article/794844/%D8%A7%D8%B3%D8%AA%D9%87%D8%AF%D8%A7%D9%81-%D9%82%D9%88%D8%A7%D8%B1%D8%A8-%D8%A7%D9%94%D8%B3%D9%84%D8%AD%D8%A9-%D9%84%D9%85%D9%8A%D9%84%D9%8A%D8%B4%D9%8A%D8%A7%D8%AA-%D8%A7%D9%84%D8%AD%D9%88%D8%AB%D9%8A-%D9%88%D8%B5%D8%A7%D9%84%D8%AD',
|
||||
'info_dict': {
|
||||
'id': '794844',
|
||||
'title': 'إحباط تهريب أسلحة لميليشيات الحوثي وصالح بجنوب اليمن',
|
||||
'description': 'md5:5c927b8b2e805796e7f693538d96fc7e',
|
||||
},
|
||||
'playlist_mincount': 2,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
article_id = self._match_id(url)
|
||||
article_data = self._call_api('article', article_id)
|
||||
media_asset = article_data['mediaAsset']
|
||||
if media_asset['type'] == 'VIDEO':
|
||||
topic = article_data.get('topicTitle')
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'url': 'limelight:media:%s' % self._get_limelight_media_id(media_asset['videoUrl'][0]['url']),
|
||||
'id': article_id,
|
||||
'title': article_data['headline'],
|
||||
'description': article_data.get('summary'),
|
||||
'thumbnail': self._get_image_url(media_asset['imageUrl']),
|
||||
'timestamp': parse_iso8601(article_data.get('date')),
|
||||
'tags': article_data.get('tags', []),
|
||||
'categories': [topic] if topic else [],
|
||||
'webpage_url': url,
|
||||
'ie_key': 'LimelightMedia',
|
||||
}
|
||||
entries = [self._extract_video_info(item) for item in article_data.get('inlineItems', []) if item['type'] == 'VIDEO']
|
||||
return self.playlist_result(entries, article_id, article_data['headline'], article_data.get('summary'))
|
||||
@ -58,7 +58,8 @@ class SpiegelIE(InfoExtractor):
|
||||
description = self._html_search_meta('description', webpage, 'description')
|
||||
|
||||
base_url = self._search_regex(
|
||||
r'var\s+server\s*=\s*"([^"]+)\"', webpage, 'server URL')
|
||||
[r'server\s*:\s*(["\'])(?P<url>.+?)\1', r'var\s+server\s*=\s*"(?P<url>[^"]+)\"'],
|
||||
webpage, 'server URL', group='url')
|
||||
|
||||
xml_url = base_url + video_id + '.xml'
|
||||
idoc = self._download_xml(xml_url, video_id)
|
||||
|
||||
@ -11,7 +11,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class SrfIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.srf\.ch/play(?:er)?/tv/[^/]+/video/(?P<display_id>[^?]+)\?id=|tp\.srgssr\.ch/p/flash\?urn=urn:srf:ais:video:)(?P<id>[0-9a-f\-]{36})'
|
||||
_VALID_URL = r'https?://(?:www\.srf\.ch/play(?:er)?/(?:tv|radio)/[^/]+/(?P<media_type>video|audio)/(?P<display_id>[^?]+)\?id=|tp\.srgssr\.ch/p/flash\?urn=urn:srf:ais:video:)(?P<id>[0-9a-f\-]{36})'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.srf.ch/play/tv/10vor10/video/snowden-beantragt-asyl-in-russland?id=28e1a57d-5b76-4399-8ab3-9097f071e6c5',
|
||||
'md5': '4cd93523723beff51bb4bee974ee238d',
|
||||
@ -35,6 +35,20 @@ class SrfIE(InfoExtractor):
|
||||
'title': 'Jaguar XK120, Shadow und Tornado-Dampflokomotive',
|
||||
'timestamp': 1373493600,
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.srf.ch/play/radio/hoerspielarchiv-srf-musikwelle/audio/saegel-ohni-wind-von-jakob-stebler?id=415bf3d3-6429-4de7-968d-95866e37cfbc',
|
||||
'md5': '',
|
||||
'info_dict': {
|
||||
'id': '415bf3d3-6429-4de7-968d-95866e37cfbc',
|
||||
'display_id': 'saegel-ohni-wind-von-jakob-stebler',
|
||||
'ext': 'mp3',
|
||||
'upload_date': '20080518',
|
||||
'title': '«Sägel ohni Wind» von Jakob Stebler',
|
||||
'timestamp': 1211112000,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True, # requires rtmpdump
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.srf.ch/player/tv/10vor10/video/snowden-beantragt-asyl-in-russland?id=28e1a57d-5b76-4399-8ab3-9097f071e6c5',
|
||||
'only_matching': True,
|
||||
@ -44,11 +58,13 @@ class SrfIE(InfoExtractor):
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
display_id = re.match(self._VALID_URL, url).group('display_id') or video_id
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
media_type = mobj.group('media_type')
|
||||
display_id = mobj.group('display_id') or video_id
|
||||
|
||||
video_data = self._download_xml(
|
||||
'http://il.srgssr.ch/integrationlayer/1.0/ue/srf/video/play/%s.xml' % video_id,
|
||||
'http://il.srgssr.ch/integrationlayer/1.0/ue/srf/%s/play/%s.xml' % (media_type, video_id),
|
||||
display_id)
|
||||
|
||||
title = xpath_text(
|
||||
@ -64,7 +80,7 @@ class SrfIE(InfoExtractor):
|
||||
for url_node in item.findall('url'):
|
||||
quality = url_node.attrib['quality']
|
||||
full_url = url_node.text
|
||||
original_ext = determine_ext(full_url)
|
||||
original_ext = determine_ext(full_url).lower()
|
||||
format_id = '%s-%s' % (quality, item.attrib['protocol'])
|
||||
if original_ext == 'f4m':
|
||||
formats.extend(self._extract_f4m_formats(
|
||||
|
||||
@ -16,6 +16,7 @@ class TeachingChannelIE(InfoExtractor):
|
||||
'ext': 'mp4',
|
||||
'title': 'A History of Teaming',
|
||||
'description': 'md5:2a9033db8da81f2edffa4c99888140b3',
|
||||
'duration': 422.255,
|
||||
},
|
||||
'params': {
|
||||
# m3u8 download
|
||||
|
||||
@ -1,80 +1,103 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import ExtractorError
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
int_or_none,
|
||||
parse_iso8601,
|
||||
)
|
||||
|
||||
|
||||
class TriluliluIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?trilulilu\.ro/(?:video-[^/]+/)?(?P<id>[^/#\?]+)'
|
||||
_TEST = {
|
||||
'url': 'http://www.trilulilu.ro/video-animatie/big-buck-bunny-1',
|
||||
'md5': 'c1450a00da251e2769b74b9005601cac',
|
||||
_VALID_URL = r'https?://(?:(?:www|m)\.)?trilulilu\.ro/(?:[^/]+/)?(?P<id>[^/#\?]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.trilulilu.ro/big-buck-bunny-1',
|
||||
'md5': '68da087b676a6196a413549212f60cc6',
|
||||
'info_dict': {
|
||||
'id': 'ae2899e124140b',
|
||||
'ext': 'mp4',
|
||||
'title': 'Big Buck Bunny',
|
||||
'description': ':) pentru copilul din noi',
|
||||
'uploader_id': 'chipy',
|
||||
'upload_date': '20120304',
|
||||
'timestamp': 1330830647,
|
||||
'uploader': 'chipy',
|
||||
'view_count': int,
|
||||
'like_count': int,
|
||||
'comment_count': int,
|
||||
},
|
||||
}
|
||||
}, {
|
||||
'url': 'http://www.trilulilu.ro/adena-ft-morreti-inocenta',
|
||||
'md5': '929dfb8729dc71750463af88bbbbf4a4',
|
||||
'info_dict': {
|
||||
'id': 'f299710e3c91c5',
|
||||
'ext': 'mp4',
|
||||
'title': 'Adena ft. Morreti - Inocenta',
|
||||
'description': 'pop music',
|
||||
'uploader_id': 'VEVOmixt',
|
||||
'upload_date': '20151204',
|
||||
'uploader': 'VEVOmixt',
|
||||
'timestamp': 1449187937,
|
||||
'view_count': int,
|
||||
'like_count': int,
|
||||
'comment_count': int,
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
media_info = self._download_json('http://m.trilulilu.ro/%s?format=json' % display_id, display_id)
|
||||
|
||||
if re.search(r'Fişierul nu este disponibil pentru vizionare în ţara dumneavoastră', webpage):
|
||||
raise ExtractorError(
|
||||
'This video is not available in your country.', expected=True)
|
||||
elif re.search('Fişierul poate fi accesat doar de către prietenii lui', webpage):
|
||||
age_limit = 0
|
||||
errors = media_info.get('errors', {})
|
||||
if errors.get('friends'):
|
||||
raise ExtractorError('This video is private.', expected=True)
|
||||
elif errors.get('geoblock'):
|
||||
raise ExtractorError('This video is not available in your country.', expected=True)
|
||||
elif errors.get('xxx_unlogged'):
|
||||
age_limit = 18
|
||||
|
||||
flashvars_str = self._search_regex(
|
||||
r'block_flash_vars\s*=\s*(\{[^\}]+\})', webpage, 'flashvars', fatal=False, default=None)
|
||||
media_class = media_info.get('class')
|
||||
if media_class not in ('video', 'audio'):
|
||||
raise ExtractorError('not a video or an audio')
|
||||
|
||||
if flashvars_str:
|
||||
flashvars = self._parse_json(flashvars_str, display_id)
|
||||
user = media_info.get('user', {})
|
||||
|
||||
thumbnail = media_info.get('cover_url')
|
||||
if thumbnail:
|
||||
thumbnail.format(width='1600', height='1200')
|
||||
|
||||
# TODO: get correct ext for audio files
|
||||
stream_type = media_info.get('stream_type')
|
||||
formats = [{
|
||||
'url': media_info['href'],
|
||||
'ext': stream_type,
|
||||
}]
|
||||
if media_info.get('is_hd'):
|
||||
formats.append({
|
||||
'format_id': 'hd',
|
||||
'url': media_info['hrefhd'],
|
||||
'ext': stream_type,
|
||||
})
|
||||
if media_class == 'audio':
|
||||
formats[0]['vcodec'] = 'none'
|
||||
else:
|
||||
raise ExtractorError(
|
||||
'This page does not contain videos', expected=True)
|
||||
|
||||
if flashvars['isMP3'] == 'true':
|
||||
raise ExtractorError(
|
||||
'Audio downloads are currently not supported', expected=True)
|
||||
|
||||
video_id = flashvars['hash']
|
||||
title = self._og_search_title(webpage)
|
||||
thumbnail = self._og_search_thumbnail(webpage)
|
||||
description = self._og_search_description(webpage, default=None)
|
||||
|
||||
format_url = ('http://fs%(server)s.trilulilu.ro/%(hash)s/'
|
||||
'video-formats2' % flashvars)
|
||||
format_doc = self._download_xml(
|
||||
format_url, video_id,
|
||||
note='Downloading formats',
|
||||
errnote='Error while downloading formats')
|
||||
|
||||
video_url_template = (
|
||||
'http://fs%(server)s.trilulilu.ro/stream.php?type=video'
|
||||
'&source=site&hash=%(hash)s&username=%(userid)s&'
|
||||
'key=ministhebest&format=%%s&sig=&exp=' %
|
||||
flashvars)
|
||||
formats = [
|
||||
{
|
||||
'format_id': fnode.text.partition('-')[2],
|
||||
'url': video_url_template % fnode.text,
|
||||
'ext': fnode.text.partition('-')[0]
|
||||
}
|
||||
|
||||
for fnode in format_doc.findall('./formats/format')
|
||||
]
|
||||
formats[0]['format_id'] = 'sd'
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'id': media_info['identifier'].split('|')[1],
|
||||
'display_id': display_id,
|
||||
'formats': formats,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'title': media_info['title'],
|
||||
'description': media_info.get('description'),
|
||||
'thumbnail': thumbnail,
|
||||
'uploader_id': user.get('username'),
|
||||
'uploader': user.get('fullname'),
|
||||
'timestamp': parse_iso8601(media_info.get('published'), ' '),
|
||||
'duration': int_or_none(media_info.get('duration')),
|
||||
'view_count': int_or_none(media_info.get('count_views')),
|
||||
'like_count': int_or_none(media_info.get('count_likes')),
|
||||
'comment_count': int_or_none(media_info.get('count_comments')),
|
||||
'age_limit': age_limit,
|
||||
}
|
||||
|
||||
@ -1,14 +1,15 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import (
|
||||
compat_HTTPError,
|
||||
compat_urllib_parse,
|
||||
compat_urllib_request,
|
||||
)
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
sanitized_Request,
|
||||
)
|
||||
|
||||
@ -18,6 +19,8 @@ class UdemyIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://www\.udemy\.com/(?:[^#]+#/lecture/|lecture/view/?\?lectureId=)(?P<id>\d+)'
|
||||
_LOGIN_URL = 'https://www.udemy.com/join/login-popup/?displayType=ajax&showSkipButton=1'
|
||||
_ORIGIN_URL = 'https://www.udemy.com'
|
||||
_SUCCESSFULLY_ENROLLED = '>You have enrolled in this course!<'
|
||||
_ALREADY_ENROLLED = '>You are already taking this course.<'
|
||||
_NETRC_MACHINE = 'udemy'
|
||||
|
||||
_TESTS = [{
|
||||
@ -33,6 +36,29 @@ class UdemyIE(InfoExtractor):
|
||||
'skip': 'Requires udemy account credentials',
|
||||
}]
|
||||
|
||||
def _enroll_course(self, webpage, course_id):
|
||||
enroll_url = self._search_regex(
|
||||
r'href=(["\'])(?P<url>https?://(?:www\.)?udemy\.com/course/subscribe/.+?)\1',
|
||||
webpage, 'enroll url', group='url',
|
||||
default='https://www.udemy.com/course/subscribe/?courseId=%s' % course_id)
|
||||
webpage = self._download_webpage(enroll_url, course_id, 'Enrolling in the course')
|
||||
if self._SUCCESSFULLY_ENROLLED in webpage:
|
||||
self.to_screen('%s: Successfully enrolled in' % course_id)
|
||||
elif self._ALREADY_ENROLLED in webpage:
|
||||
self.to_screen('%s: Already enrolled in' % course_id)
|
||||
|
||||
def _download_lecture(self, course_id, lecture_id):
|
||||
return self._download_json(
|
||||
'https://www.udemy.com/api-2.0/users/me/subscribed-courses/%s/lectures/%s?%s' % (
|
||||
course_id, lecture_id, compat_urllib_parse.urlencode({
|
||||
'video_only': '',
|
||||
'auto_play': '',
|
||||
'fields[lecture]': 'title,description,asset',
|
||||
'fields[asset]': 'asset_type,stream_url,thumbnail_url,download_urls,data',
|
||||
'instructorPreviewMode': 'False',
|
||||
})),
|
||||
lecture_id, 'Downloading lecture JSON')
|
||||
|
||||
def _handle_error(self, response):
|
||||
if not isinstance(response, dict):
|
||||
return
|
||||
@ -54,6 +80,7 @@ class UdemyIE(InfoExtractor):
|
||||
headers['X-Udemy-Client-Id'] = cookie.value
|
||||
elif cookie.name == 'access_token':
|
||||
headers['X-Udemy-Bearer-Token'] = cookie.value
|
||||
headers['X-Udemy-Authorization'] = 'Bearer %s' % cookie.value
|
||||
|
||||
if isinstance(url_or_request, compat_urllib_request.Request):
|
||||
for header, value in headers.items():
|
||||
@ -71,7 +98,7 @@ class UdemyIE(InfoExtractor):
|
||||
def _login(self):
|
||||
(username, password) = self._get_login_info()
|
||||
if username is None:
|
||||
self.raise_login_required('Udemy account is required')
|
||||
return
|
||||
|
||||
login_popup = self._download_webpage(
|
||||
self._LOGIN_URL, None, 'Downloading login popup')
|
||||
@ -109,44 +136,76 @@ class UdemyIE(InfoExtractor):
|
||||
def _real_extract(self, url):
|
||||
lecture_id = self._match_id(url)
|
||||
|
||||
lecture = self._download_json(
|
||||
'https://www.udemy.com/api-1.1/lectures/%s' % lecture_id,
|
||||
lecture_id, 'Downloading lecture JSON')
|
||||
webpage = self._download_webpage(url, lecture_id)
|
||||
|
||||
asset_type = lecture.get('assetType') or lecture.get('asset_type')
|
||||
course_id = self._search_regex(
|
||||
r'data-course-id=["\'](\d+)', webpage, 'course id')
|
||||
|
||||
try:
|
||||
lecture = self._download_lecture(course_id, lecture_id)
|
||||
except ExtractorError as e:
|
||||
# Error could possibly mean we are not enrolled in the course
|
||||
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
|
||||
self._enroll_course(webpage, course_id)
|
||||
lecture_id = self._download_lecture(course_id, lecture_id)
|
||||
else:
|
||||
raise
|
||||
|
||||
title = lecture['title']
|
||||
description = lecture.get('description')
|
||||
|
||||
asset = lecture['asset']
|
||||
|
||||
asset_type = asset.get('assetType') or asset.get('asset_type')
|
||||
if asset_type != 'Video':
|
||||
raise ExtractorError(
|
||||
'Lecture %s is not a video' % lecture_id, expected=True)
|
||||
|
||||
asset = lecture['asset']
|
||||
|
||||
stream_url = asset.get('streamUrl') or asset.get('stream_url')
|
||||
mobj = re.search(r'(https?://www\.youtube\.com/watch\?v=.*)', stream_url)
|
||||
if mobj:
|
||||
return self.url_result(mobj.group(1), 'Youtube')
|
||||
if stream_url:
|
||||
youtube_url = self._search_regex(
|
||||
r'(https?://www\.youtube\.com/watch\?v=.*)', stream_url, 'youtube URL', default=None)
|
||||
if youtube_url:
|
||||
return self.url_result(youtube_url, 'Youtube')
|
||||
|
||||
video_id = asset['id']
|
||||
thumbnail = asset.get('thumbnailUrl') or asset.get('thumbnail_url')
|
||||
duration = asset['data']['duration']
|
||||
duration = float_or_none(asset.get('data', {}).get('duration'))
|
||||
outputs = asset.get('data', {}).get('outputs', {})
|
||||
|
||||
download_url = asset.get('downloadUrl') or asset.get('download_url')
|
||||
formats = []
|
||||
for format_ in asset.get('download_urls', {}).get('Video', []):
|
||||
video_url = format_.get('file')
|
||||
if not video_url:
|
||||
continue
|
||||
format_id = format_.get('label')
|
||||
f = {
|
||||
'url': format_['file'],
|
||||
'height': int_or_none(format_id),
|
||||
}
|
||||
if format_id:
|
||||
# Some videos contain additional metadata (e.g.
|
||||
# https://www.udemy.com/ios9-swift/learn/#/lecture/3383208)
|
||||
output = outputs.get(format_id)
|
||||
if isinstance(output, dict):
|
||||
f.update({
|
||||
'format_id': '%sp' % (output.get('label') or format_id),
|
||||
'width': int_or_none(output.get('width')),
|
||||
'height': int_or_none(output.get('height')),
|
||||
'vbr': int_or_none(output.get('video_bitrate_in_kbps')),
|
||||
'vcodec': output.get('video_codec'),
|
||||
'fps': int_or_none(output.get('frame_rate')),
|
||||
'abr': int_or_none(output.get('audio_bitrate_in_kbps')),
|
||||
'acodec': output.get('audio_codec'),
|
||||
'asr': int_or_none(output.get('audio_sample_rate')),
|
||||
'tbr': int_or_none(output.get('total_bitrate_in_kbps')),
|
||||
'filesize': int_or_none(output.get('file_size_in_bytes')),
|
||||
})
|
||||
else:
|
||||
f['format_id'] = '%sp' % format_id
|
||||
formats.append(f)
|
||||
|
||||
video = download_url.get('Video') or download_url.get('video')
|
||||
video_480p = download_url.get('Video480p') or download_url.get('video_480p')
|
||||
|
||||
formats = [
|
||||
{
|
||||
'url': video_480p[0],
|
||||
'format_id': '360p',
|
||||
},
|
||||
{
|
||||
'url': video[0],
|
||||
'format_id': '720p',
|
||||
},
|
||||
]
|
||||
|
||||
title = lecture['title']
|
||||
description = lecture['description']
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
@ -160,9 +219,7 @@ class UdemyIE(InfoExtractor):
|
||||
|
||||
class UdemyCourseIE(UdemyIE):
|
||||
IE_NAME = 'udemy:course'
|
||||
_VALID_URL = r'https?://www\.udemy\.com/(?P<coursepath>[\da-z-]+)'
|
||||
_SUCCESSFULLY_ENROLLED = '>You have enrolled in this course!<'
|
||||
_ALREADY_ENROLLED = '>You are already taking this course.<'
|
||||
_VALID_URL = r'https?://www\.udemy\.com/(?P<id>[\da-z-]+)'
|
||||
_TESTS = []
|
||||
|
||||
@classmethod
|
||||
@ -170,24 +227,18 @@ class UdemyCourseIE(UdemyIE):
|
||||
return False if UdemyIE.suitable(url) else super(UdemyCourseIE, cls).suitable(url)
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
course_path = mobj.group('coursepath')
|
||||
course_path = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, course_path)
|
||||
|
||||
response = self._download_json(
|
||||
'https://www.udemy.com/api-1.1/courses/%s' % course_path,
|
||||
course_path, 'Downloading course JSON')
|
||||
|
||||
course_id = int(response['id'])
|
||||
course_title = response['title']
|
||||
course_id = response['id']
|
||||
course_title = response.get('title')
|
||||
|
||||
webpage = self._download_webpage(
|
||||
'https://www.udemy.com/course/subscribe/?courseId=%s' % course_id,
|
||||
course_id, 'Enrolling in the course')
|
||||
|
||||
if self._SUCCESSFULLY_ENROLLED in webpage:
|
||||
self.to_screen('%s: Successfully enrolled in' % course_id)
|
||||
elif self._ALREADY_ENROLLED in webpage:
|
||||
self.to_screen('%s: Already enrolled in' % course_id)
|
||||
self._enroll_course(webpage, course_id)
|
||||
|
||||
response = self._download_json(
|
||||
'https://www.udemy.com/api-1.1/courses/%s/curriculum' % course_id,
|
||||
|
||||
@ -15,6 +15,7 @@ class ViceIE(InfoExtractor):
|
||||
'id': '43cW1mYzpia9IlestBjVpd23Yu3afAfp',
|
||||
'ext': 'mp4',
|
||||
'title': 'VICE_COWBOYCAPITALISTS_PART01_v1_VICE_WM_1080p.mov',
|
||||
'duration': 725.983,
|
||||
},
|
||||
'params': {
|
||||
# Requires ffmpeg (m3u8 manifest)
|
||||
|
||||
@ -1,26 +0,0 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .novamov import NovaMovIE
|
||||
|
||||
|
||||
class VideoWeedIE(NovaMovIE):
|
||||
IE_NAME = 'videoweed'
|
||||
IE_DESC = 'VideoWeed'
|
||||
|
||||
_VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'videoweed\.(?:es|com)'}
|
||||
|
||||
_HOST = 'www.videoweed.es'
|
||||
|
||||
_FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
|
||||
_TITLE_REGEX = r'<h1 class="text_shadow">([^<]+)</h1>'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://www.videoweed.es/file/b42178afbea14',
|
||||
'md5': 'abd31a2132947262c50429e1d16c1bfd',
|
||||
'info_dict': {
|
||||
'id': 'b42178afbea14',
|
||||
'ext': 'flv',
|
||||
'title': 'optical illusion dissapeared image magic illusion',
|
||||
'description': ''
|
||||
},
|
||||
}
|
||||
@ -3,11 +3,14 @@ from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_urllib_parse
|
||||
from ..utils import sanitized_Request
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
sanitized_Request,
|
||||
)
|
||||
|
||||
|
||||
class VodlockerIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?vodlocker\.com/(?P<id>[0-9a-zA-Z]+)(?:\..*?)?'
|
||||
_VALID_URL = r'https?://(?:www\.)?vodlocker\.com/(?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:\..*?)?'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://vodlocker.com/e8wvyzz4sl42',
|
||||
@ -24,6 +27,12 @@ class VodlockerIE(InfoExtractor):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
if any(p in webpage for p in (
|
||||
'>THIS FILE WAS DELETED<',
|
||||
'>File Not Found<',
|
||||
'The file you were looking for could not be found, sorry for any inconvenience.<')):
|
||||
raise ExtractorError('Video %s does not exist' % video_id, expected=True)
|
||||
|
||||
fields = self._hidden_inputs(webpage)
|
||||
|
||||
if fields['op'] == 'download1':
|
||||
|
||||
@ -258,7 +258,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
|(?: # or the v= param in all its forms
|
||||
(?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
|
||||
(?:\?|\#!?) # the params delimiter ? or # or #!
|
||||
(?:.*?&)?? # any other preceding param (like /?s=tuff&v=xxxx)
|
||||
(?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY)
|
||||
v=
|
||||
)
|
||||
))
|
||||
@ -346,6 +346,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
'247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
|
||||
'248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
|
||||
'271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
|
||||
# itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
|
||||
'272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
|
||||
'302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'vp9'},
|
||||
'303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'vp9'},
|
||||
@ -714,6 +715,26 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
|
||||
'only_matching': True,
|
||||
},
|
||||
{
|
||||
# Video with yt:stretch=17:0
|
||||
'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
|
||||
'info_dict': {
|
||||
'id': 'Q39EVAstoRM',
|
||||
'ext': 'mp4',
|
||||
'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
|
||||
'description': 'md5:ee18a25c350637c8faff806845bddee9',
|
||||
'upload_date': '20151107',
|
||||
'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
|
||||
'uploader': 'CH GAMER DROID',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
},
|
||||
{
|
||||
'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY',
|
||||
'only_matching': True,
|
||||
}
|
||||
]
|
||||
|
||||
def __init__(self, *args, **kwargs):
|
||||
@ -1459,6 +1480,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
manifest_url = video_info['hlsvp'][0]
|
||||
url_map = self._extract_from_m3u8(manifest_url, video_id)
|
||||
formats = _map_to_format_list(url_map)
|
||||
# Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming
|
||||
for a_format in formats:
|
||||
a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = 'True'
|
||||
else:
|
||||
raise ExtractorError('no conn, hlsvp or url_encoded_fmt_stream_map information found in video info')
|
||||
|
||||
@ -1496,10 +1520,15 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
r'<meta\s+property="og:video:tag".*?content="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">',
|
||||
video_webpage)
|
||||
if stretched_m:
|
||||
ratio = float(stretched_m.group('w')) / float(stretched_m.group('h'))
|
||||
for f in formats:
|
||||
if f.get('vcodec') != 'none':
|
||||
f['stretched_ratio'] = ratio
|
||||
w = float(stretched_m.group('w'))
|
||||
h = float(stretched_m.group('h'))
|
||||
# yt:stretch may hold invalid ratio data (e.g. for Q39EVAstoRM ratio is 17:0).
|
||||
# We will only process correct ratios.
|
||||
if w > 0 and h > 0:
|
||||
ratio = w / h
|
||||
for f in formats:
|
||||
if f.get('vcodec') != 'none':
|
||||
f['stretched_ratio'] = ratio
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
@ -1538,7 +1567,7 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor, YoutubePlaylistBaseInfoExtract
|
||||
youtube\.com/
|
||||
(?:
|
||||
(?:course|view_play_list|my_playlists|artist|playlist|watch|embed/videoseries)
|
||||
\? (?:.*?&)*? (?:p|a|list)=
|
||||
\? (?:.*?[&;])*? (?:p|a|list)=
|
||||
| p/
|
||||
)
|
||||
(
|
||||
|
||||
@ -338,7 +338,7 @@ def parseOpts(overrideArguments=None):
|
||||
video_format.add_option(
|
||||
'-F', '--list-formats',
|
||||
action='store_true', dest='listformats',
|
||||
help='List all available formats')
|
||||
help='List all available formats of requested videos')
|
||||
video_format.add_option(
|
||||
'--youtube-include-dash-manifest',
|
||||
action='store_true', dest='youtube_include_dash_manifest', default=True,
|
||||
|
||||
@ -663,6 +663,16 @@ def _create_http_connection(ydl_handler, http_class, is_https, *args, **kwargs):
|
||||
return hc
|
||||
|
||||
|
||||
def handle_youtubedl_headers(headers):
|
||||
filtered_headers = headers
|
||||
|
||||
if 'Youtubedl-no-compression' in filtered_headers:
|
||||
filtered_headers = dict((k, v) for k, v in filtered_headers.items() if k.lower() != 'accept-encoding')
|
||||
del filtered_headers['Youtubedl-no-compression']
|
||||
|
||||
return filtered_headers
|
||||
|
||||
|
||||
class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
|
||||
"""Handler for HTTP requests and responses.
|
||||
|
||||
@ -670,7 +680,7 @@ class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
|
||||
the standard headers to every HTTP request and handles gzipped and
|
||||
deflated responses from web servers. If compression is to be avoided in
|
||||
a particular request, the original request in the program code only has
|
||||
to include the HTTP header "Youtubedl-No-Compression", which will be
|
||||
to include the HTTP header "Youtubedl-no-compression", which will be
|
||||
removed before making the real request.
|
||||
|
||||
Part of this code was copied from:
|
||||
@ -731,10 +741,8 @@ class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
|
||||
# The dict keys are capitalized because of this bug by urllib
|
||||
if h.capitalize() not in req.headers:
|
||||
req.add_header(h, v)
|
||||
if 'Youtubedl-no-compression' in req.headers:
|
||||
if 'Accept-encoding' in req.headers:
|
||||
del req.headers['Accept-encoding']
|
||||
del req.headers['Youtubedl-no-compression']
|
||||
|
||||
req.headers = handle_youtubedl_headers(req.headers)
|
||||
|
||||
if sys.version_info < (2, 7) and '#' in req.get_full_url():
|
||||
# Python 2.6 is brain-dead when it comes to fragments
|
||||
|
||||
@ -1,3 +1,3 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
__version__ = '2015.11.24'
|
||||
__version__ = '2015.12.06'
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user