Merge remote-tracking branch 'rg3/master'
This commit is contained in:
Muratcan Simsek
commit
10623012a8
@ -319,7 +319,7 @@ 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 of specified
|
||||
-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
|
||||
|
||||
@ -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**
|
||||
|
||||
@ -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,
|
||||
}
|
||||
@ -23,7 +23,7 @@ class BBCCoUkIE(InfoExtractor):
|
||||
IE_NAME = 'bbc.co.uk'
|
||||
IE_DESC = 'BBC iPlayer'
|
||||
_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
|
||||
_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
|
||||
@ -47,9 +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
|
||||
@ -112,7 +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',
|
||||
@ -454,6 +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',
|
||||
@ -473,7 +474,9 @@ class BBCCoUkIE(InfoExtractor):
|
||||
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)
|
||||
|
||||
@ -587,6 +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,
|
||||
@ -729,6 +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)
|
||||
|
||||
@ -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
|
||||
|
||||
@ -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
|
||||
|
||||
@ -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):
|
||||
|
||||
@ -64,7 +64,8 @@ class MixcloudIE(InfoExtractor):
|
||||
|
||||
preview_url = self._search_regex(
|
||||
r'\s(?:data-preview-url|m-preview)="([^"]+)"', webpage, 'preview url')
|
||||
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',
|
||||
}
|
||||
}
|
||||
@ -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)
|
||||
|
||||
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'))
|
||||
@ -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,
|
||||
}
|
||||
|
||||
@ -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': ''
|
||||
},
|
||||
}
|
||||
@ -1,3 +1,3 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
__version__ = '2015.11.27.1'
|
||||
__version__ = '2015.12.06'
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user