yt-dlp/youtube_dl/InfoExtractors.py

959 lines
35 KiB
Python
Raw Normal View History

2013-01-01 21:07:37 +01:00
import base64
import datetime
2013-01-27 03:01:23 +01:00
import itertools
import netrc
import os
import re
import socket
import time
import email.utils
import xml.etree.ElementTree
2012-08-08 20:04:02 +02:00
import random
import math
import operator
2013-05-15 23:38:44 +02:00
import hashlib
import binascii
import urllib
2012-11-28 03:34:40 +01:00
from .utils import *
2013-06-23 19:57:38 +02:00
from .extractor.common import InfoExtractor, SearchInfoExtractor
from .extractor.ard import ARDIE
from .extractor.arte import ArteTvIE
from .extractor.bliptv import BlipTVIE, BlipTVUserIE
2013-06-23 20:50:22 +02:00
from .extractor.comedycentral import ComedyCentralIE
2013-06-23 21:10:21 +02:00
from .extractor.collegehumor import CollegeHumorIE
2013-06-23 20:09:47 +02:00
from .extractor.dailymotion import DailymotionIE
2013-06-23 21:06:20 +02:00
from .extractor.depositfiles import DepositFilesIE
2013-06-23 21:08:17 +02:00
from .extractor.escapist import EscapistIE
2013-06-23 21:00:34 +02:00
from .extractor.facebook import FacebookIE
2013-06-23 22:05:23 +02:00
from .extractor.funnyordie import FunnyOrDieIE
2013-06-23 20:29:46 +02:00
from .extractor.gametrailers import GametrailersIE
2013-06-23 20:31:45 +02:00
from .extractor.generic import GenericIE
from .extractor.googleplus import GooglePlusIE
from .extractor.googlesearch import GoogleSearchIE
2013-06-23 21:14:19 +02:00
from .extractor.infoq import InfoQIE
2013-06-23 22:07:27 +02:00
from .extractor.justintv import JustinTVIE
from .extractor.metacafe import MetacafeIE
2013-06-23 21:59:15 +02:00
from .extractor.mixcloud import MixcloudIE
2013-06-23 21:27:38 +02:00
from .extractor.mtv import MTVIE
2013-06-23 20:48:32 +02:00
from .extractor.myvideo import MyVideoIE
2013-06-23 21:18:00 +02:00
from .extractor.nba import NBAIE
from .extractor.statigram import StatigramIE
2013-06-23 20:12:18 +02:00
from .extractor.photobucket import PhotobucketIE
2013-06-23 22:09:32 +02:00
from .extractor.rbmaradio import RBMARadioIE
2013-06-23 20:57:44 +02:00
from .extractor.soundcloud import SoundcloudIE, SoundcloudSetIE
2013-06-23 21:16:32 +02:00
from .extractor.stanfordoc import StanfordOpenClassroomIE
2013-06-23 22:02:56 +02:00
from .extractor.steam import SteamIE
2013-06-23 21:55:53 +02:00
from .extractor.ted import TEDIE
2013-06-23 22:08:28 +02:00
from .extractor.ustream import UstreamIE
2013-06-23 20:18:21 +02:00
from .extractor.vimeo import VimeoIE
2013-06-23 22:04:08 +02:00
from .extractor.worldstarhiphop import WorldStarHipHopIE
2013-06-23 22:02:56 +02:00
from .extractor.xnxx import XNXXIE
from .extractor.xvideos import XVideosIE
from .extractor.yahoo import YahooIE, YahooSearchIE
2013-06-23 22:01:02 +02:00
from .extractor.youku import YoukuIE
from .extractor.youtube import YoutubeIE, YoutubePlaylistIE, YoutubeSearchIE, YoutubeUserIE, YoutubeChannelIE
from .extractor.zdf import ZDFIE
2013-01-01 20:43:43 +01:00
2012-08-16 01:54:03 +02:00
2012-08-08 20:04:02 +02:00
2012-12-13 21:27:57 +01:00
2012-12-20 21:28:27 +01:00
2012-12-27 01:38:41 +01:00
2013-01-12 13:49:14 +01:00
2013-01-01 19:37:07 +01:00
2013-03-07 06:09:55 +01:00
2013-01-01 19:37:07 +01:00
2013-01-05 21:42:35 +01:00
class YouPornIE(InfoExtractor):
"""Information extractor for youporn.com."""
_VALID_URL = r'^(?:https?://)?(?:\w+\.)?youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+)'
2013-01-05 21:42:35 +01:00
def _print_formats(self, formats):
"""Print all available formats"""
2013-01-12 15:17:04 +01:00
print(u'Available formats:')
print(u'ext\t\tformat')
print(u'---------------------------------')
2013-01-05 21:42:35 +01:00
for format in formats:
print(u'%s\t\t%s' % (format['ext'], format['format']))
2013-01-05 21:42:35 +01:00
def _specific(self, req_format, formats):
for x in formats:
if(x["format"]==req_format):
return x
return None
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group('videoid')
2013-01-05 21:42:35 +01:00
req = compat_urllib_request.Request(url)
req.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(req, video_id)
2013-01-05 21:42:35 +01:00
# Get JSON parameters
json_params = self._search_regex(r'var currentVideo = new Video\((.*)\);', webpage, u'JSON parameters')
try:
params = json.loads(json_params)
except:
raise ExtractorError(u'Invalid JSON')
2013-01-05 21:42:35 +01:00
self.report_extraction(video_id)
try:
video_title = params['title']
upload_date = unified_strdate(params['release_date_f'])
video_description = params['description']
video_uploader = params['submitted_by']
thumbnail = params['thumbnails'][0]['image']
except KeyError:
raise ExtractorError('Missing JSON parameter: ' + sys.exc_info()[1])
2013-01-05 21:42:35 +01:00
# Get all of the formats available
DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>'
2013-06-06 13:27:27 +02:00
download_list_html = self._search_regex(DOWNLOAD_LIST_RE,
webpage, u'download list').strip()
2013-01-05 21:42:35 +01:00
# Get all of the links from the page
LINK_RE = r'(?s)<a href="(?P<url>[^"]+)">'
links = re.findall(LINK_RE, download_list_html)
2013-01-05 21:42:35 +01:00
if(len(links) == 0):
raise ExtractorError(u'ERROR: no known formats available for video')
self.to_screen(u'Links found: %d' % len(links))
2013-01-05 21:42:35 +01:00
formats = []
for link in links:
# A link looks like this:
# http://cdn1.download.youporn.phncdn.com/201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4?nvb=20121113051249&nva=20121114051249&ir=1200&sr=1200&hash=014b882080310e95fb6a0
# A path looks like this:
# /201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4
video_url = unescapeHTML( link )
path = compat_urllib_parse_urlparse( video_url ).path
2013-01-05 21:42:35 +01:00
extension = os.path.splitext( path )[1][1:]
format = path.split('/')[4].split('_')[:2]
size = format[0]
bitrate = format[1]
format = "-".join( format )
# title = u'%s-%s-%s' % (video_title, size, bitrate)
2013-01-05 21:42:35 +01:00
formats.append({
'id': video_id,
'url': video_url,
'uploader': video_uploader,
'upload_date': upload_date,
'title': video_title,
2013-01-05 21:42:35 +01:00
'ext': extension,
'format': format,
'thumbnail': thumbnail,
'description': video_description
2013-01-05 21:42:35 +01:00
})
if self._downloader.params.get('listformats', None):
self._print_formats(formats)
return
req_format = self._downloader.params.get('format', None)
self.to_screen(u'Format: %s' % req_format)
2013-01-05 21:42:35 +01:00
if req_format is None or req_format == 'best':
return [formats[0]]
elif req_format == 'worst':
return [formats[-1]]
elif req_format in ('-1', 'all'):
return formats
else:
format = self._specific( req_format, formats )
if result is None:
raise ExtractorError(u'Requested format not available')
2013-01-05 21:42:35 +01:00
return [format]
2013-01-05 21:42:35 +01:00
class PornotubeIE(InfoExtractor):
"""Information extractor for pornotube.com."""
_VALID_URL = r'^(?:https?://)?(?:\w+\.)?pornotube\.com(/c/(?P<channel>[0-9]+))?(/m/(?P<videoid>[0-9]+))(/(?P<title>.+))$'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
2013-01-05 21:42:35 +01:00
video_id = mobj.group('videoid')
video_title = mobj.group('title')
2013-01-05 21:42:35 +01:00
# Get webpage content
webpage = self._download_webpage(url, video_id)
2013-01-05 21:42:35 +01:00
# Get the video URL
VIDEO_URL_RE = r'url: "(?P<url>http://video[0-9].pornotube.com/.+\.flv)",'
2013-06-06 13:27:27 +02:00
video_url = self._search_regex(VIDEO_URL_RE, webpage, u'video url')
video_url = compat_urllib_parse.unquote(video_url)
2013-01-05 21:42:35 +01:00
#Get the uploaded date
VIDEO_UPLOADED_RE = r'<div class="video_added_by">Added (?P<date>[0-9\/]+) by'
upload_date = self._html_search_regex(VIDEO_UPLOADED_RE, webpage, u'upload date', fatal=False)
2013-06-06 13:27:27 +02:00
if upload_date: upload_date = unified_strdate(upload_date)
2013-01-05 21:42:35 +01:00
info = {'id': video_id,
'url': video_url,
'uploader': None,
'upload_date': upload_date,
'title': video_title,
'ext': 'flv',
2013-01-12 15:17:04 +01:00
'format': 'flv'}
2013-01-05 21:42:35 +01:00
return [info]
class YouJizzIE(InfoExtractor):
"""Information extractor for youjizz.com."""
_VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+).html$'
2013-01-05 21:42:35 +01:00
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group('videoid')
# Get webpage content
webpage = self._download_webpage(url, video_id)
2013-01-05 21:42:35 +01:00
# Get the video title
video_title = self._html_search_regex(r'<title>(?P<title>.*)</title>',
2013-06-06 13:27:27 +02:00
webpage, u'title').strip()
2013-01-05 21:42:35 +01:00
# Get the embed page
2013-01-12 16:36:51 +01:00
result = re.search(r'https?://www.youjizz.com/videos/embed/(?P<videoid>[0-9]+)', webpage)
2013-01-05 21:42:35 +01:00
if result is None:
2013-01-12 16:36:51 +01:00
raise ExtractorError(u'ERROR: unable to extract embed page')
2013-01-05 21:42:35 +01:00
embed_page_url = result.group(0).strip()
video_id = result.group('videoid')
webpage = self._download_webpage(embed_page_url, video_id)
2013-01-05 21:42:35 +01:00
# Get the video URL
2013-06-06 13:27:27 +02:00
video_url = self._search_regex(r'so.addVariable\("file",encodeURIComponent\("(?P<source>[^"]+)"\)\);',
webpage, u'video URL')
2013-01-05 21:42:35 +01:00
info = {'id': video_id,
'url': video_url,
'title': video_title,
'ext': 'flv',
'format': 'flv',
'player_url': embed_page_url}
return [info]
2013-01-27 03:01:23 +01:00
class EightTracksIE(InfoExtractor):
IE_NAME = '8tracks'
2013-01-27 04:15:12 +01:00
_VALID_URL = r'https?://8tracks.com/(?P<user>[^/]+)/(?P<id>[^/#]+)(?:#.*)?$'
2013-01-27 03:01:23 +01:00
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
playlist_id = mobj.group('id')
webpage = self._download_webpage(url, playlist_id)
2013-06-06 13:27:27 +02:00
json_like = self._search_regex(r"PAGE.mix = (.*?);\n", webpage, u'trax information', flags=re.DOTALL)
2013-01-27 03:01:23 +01:00
data = json.loads(json_like)
session = str(random.randint(0, 1000000000))
mix_id = data['id']
track_count = data['tracks_count']
first_url = 'http://8tracks.com/sets/%s/play?player=sm&mix_id=%s&format=jsonh' % (session, mix_id)
next_url = first_url
res = []
for i in itertools.count():
api_json = self._download_webpage(next_url, playlist_id,
note=u'Downloading song information %s/%s' % (str(i+1), track_count),
errnote=u'Failed to download song information')
api_data = json.loads(api_json)
track_data = api_data[u'set']['track']
info = {
'id': track_data['id'],
'url': track_data['track_file_stream_url'],
2013-01-27 04:05:53 +01:00
'title': track_data['performer'] + u' - ' + track_data['name'],
'raw_title': track_data['name'],
'uploader_id': data['user']['login'],
2013-01-27 03:01:23 +01:00
'ext': 'm4a',
}
res.append(info)
if api_data['set']['at_last_track']:
break
next_url = 'http://8tracks.com/sets/%s/next?player=sm&mix_id=%s&format=jsonh&track_id=%s' % (session, mix_id, track_data['id'])
return res
2013-01-05 21:42:35 +01:00
2013-02-08 08:25:55 +01:00
class KeekIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?keek\.com/(?:!|\w+/keeks/)(?P<videoID>\w+)'
IE_NAME = u'keek'
def _real_extract(self, url):
m = re.match(self._VALID_URL, url)
video_id = m.group('videoID')
2013-06-06 13:27:27 +02:00
2013-02-08 08:25:55 +01:00
video_url = u'http://cdn.keek.com/keek/video/%s' % video_id
thumbnail = u'http://cdn.keek.com/keek/thumbnail/%s/w100/h75' % video_id
webpage = self._download_webpage(url, video_id)
2013-06-06 13:27:27 +02:00
video_title = self._html_search_regex(r'<meta property="og:title" content="(?P<title>.*?)"',
2013-06-06 13:27:27 +02:00
webpage, u'title')
uploader = self._html_search_regex(r'<div class="user-name-and-bio">[\S\s]+?<h2>(?P<uploader>.+?)</h2>',
2013-06-06 13:27:27 +02:00
webpage, u'uploader', fatal=False)
2013-02-08 08:25:55 +01:00
info = {
2013-03-20 12:13:52 +01:00
'id': video_id,
'url': video_url,
2013-02-08 08:25:55 +01:00
'ext': 'mp4',
2013-06-06 13:27:27 +02:00
'title': video_title,
2013-02-08 08:25:55 +01:00
'thumbnail': thumbnail,
'uploader': uploader
2013-02-08 11:00:28 +01:00
}
2013-02-08 08:25:55 +01:00
return [info]
2013-02-18 18:45:09 +01:00
class MySpassIE(InfoExtractor):
2013-02-16 13:46:13 +01:00
_VALID_URL = r'http://www.myspass.de/.*'
2013-02-16 13:46:13 +01:00
def _real_extract(self, url):
META_DATA_URL_TEMPLATE = 'http://www.myspass.de/myspass/includes/apps/video/getvideometadataxml.php?id=%s'
2013-02-18 18:45:09 +01:00
2013-02-16 13:46:13 +01:00
# video id is the last path element of the URL
# usually there is a trailing slash, so also try the second but last
url_path = compat_urllib_parse_urlparse(url).path
url_parent_path, video_id = os.path.split(url_path)
if not video_id:
_, video_id = os.path.split(url_parent_path)
2013-02-16 13:46:13 +01:00
# get metadata
metadata_url = META_DATA_URL_TEMPLATE % video_id
metadata_text = self._download_webpage(metadata_url, video_id)
metadata = xml.etree.ElementTree.fromstring(metadata_text.encode('utf-8'))
2013-02-16 13:46:13 +01:00
# extract values from metadata
url_flv_el = metadata.find('url_flv')
if url_flv_el is None:
raise ExtractorError(u'Unable to extract download url')
2013-02-16 13:46:13 +01:00
video_url = url_flv_el.text
extension = os.path.splitext(video_url)[1][1:]
title_el = metadata.find('title')
if title_el is None:
raise ExtractorError(u'Unable to extract title')
2013-02-16 13:46:13 +01:00
title = title_el.text
format_id_el = metadata.find('format_id')
if format_id_el is None:
format = ext
else:
format = format_id_el.text
description_el = metadata.find('description')
if description_el is not None:
description = description_el.text
else:
description = None
imagePreview_el = metadata.find('imagePreview')
if imagePreview_el is not None:
thumbnail = imagePreview_el.text
else:
thumbnail = None
info = {
'id': video_id,
'url': video_url,
'title': title,
'ext': extension,
'format': format,
'thumbnail': thumbnail,
'description': description
}
return [info]
2013-03-12 01:08:54 +01:00
class SpiegelIE(InfoExtractor):
2013-03-29 15:31:38 +01:00
_VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<videoID>[0-9]+)(?:\.html)?(?:#.*)?$'
2013-03-12 01:08:54 +01:00
def _real_extract(self, url):
m = re.match(self._VALID_URL, url)
video_id = m.group('videoID')
webpage = self._download_webpage(url, video_id)
2013-06-06 13:27:27 +02:00
video_title = self._html_search_regex(r'<div class="module-title">(.*?)</div>',
2013-06-06 13:27:27 +02:00
webpage, u'title')
2013-03-12 01:08:54 +01:00
xml_url = u'http://video2.spiegel.de/flash/' + video_id + u'.xml'
xml_code = self._download_webpage(xml_url, video_id,
note=u'Downloading XML', errnote=u'Failed to download XML')
idoc = xml.etree.ElementTree.fromstring(xml_code)
last_type = idoc[-1]
filename = last_type.findall('./filename')[0].text
duration = float(last_type.findall('./duration')[0].text)
video_url = 'http://video2.spiegel.de/flash/' + filename
video_ext = filename.rpartition('.')[2]
info = {
'id': video_id,
'url': video_url,
'ext': video_ext,
'title': video_title,
'duration': duration,
}
return [info]
class LiveLeakIE(InfoExtractor):
2013-03-26 21:37:08 +01:00
_VALID_URL = r'^(?:http?://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<video_id>[\w_]+)(?:.*)'
2013-03-26 21:37:08 +01:00
IE_NAME = u'liveleak'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
2013-03-26 21:37:08 +01:00
video_id = mobj.group('video_id')
2013-03-26 21:37:08 +01:00
webpage = self._download_webpage(url, video_id)
2013-06-06 13:27:27 +02:00
video_url = self._search_regex(r'file: "(.*?)",',
webpage, u'video URL')
video_title = self._html_search_regex(r'<meta property="og:title" content="(?P<title>.*?)"',
webpage, u'title').replace('LiveLeak.com -', '').strip()
2013-03-26 21:37:08 +01:00
video_description = self._html_search_regex(r'<meta property="og:description" content="(?P<desc>.*?)"',
2013-06-06 13:27:27 +02:00
webpage, u'description', fatal=False)
2013-03-26 21:37:08 +01:00
video_uploader = self._html_search_regex(r'By:.*?(\w+)</a>',
2013-06-06 13:27:27 +02:00
webpage, u'uploader', fatal=False)
2013-03-26 21:37:08 +01:00
info = {
'id': video_id,
'url': video_url,
'ext': 'mp4',
2013-06-06 13:27:27 +02:00
'title': video_title,
'description': video_description,
'uploader': video_uploader
2013-03-26 21:37:08 +01:00
}
return [info]
class TumblrIE(InfoExtractor):
_VALID_URL = r'http://(?P<blog_name>.*?)\.tumblr\.com/((post)|(video))/(?P<id>\d*)/(.*?)'
def _real_extract(self, url):
m_url = re.match(self._VALID_URL, url)
video_id = m_url.group('id')
blog = m_url.group('blog_name')
url = 'http://%s.tumblr.com/post/%s/' % (blog, video_id)
webpage = self._download_webpage(url, video_id)
re_video = r'src=\\x22(?P<video_url>http://%s\.tumblr\.com/video_file/%s/(.*?))\\x22 type=\\x22video/(?P<ext>.*?)\\x22' % (blog, video_id)
video = re.search(re_video, webpage)
if video is None:
2013-06-06 13:27:27 +02:00
raise ExtractorError(u'Unable to extract video')
video_url = video.group('video_url')
ext = video.group('ext')
2013-06-06 13:27:27 +02:00
video_thumbnail = self._search_regex(r'posters(.*?)\[\\x22(?P<thumb>.*?)\\x22',
webpage, u'thumbnail', fatal=False) # We pick the first poster
if video_thumbnail: video_thumbnail = video_thumbnail.replace('\\', '')
# The only place where you can get a title, it's not complete,
# but searching in other places doesn't work for all videos
video_title = self._html_search_regex(r'<title>(?P<title>.*?)</title>',
2013-06-06 13:27:27 +02:00
webpage, u'title', flags=re.DOTALL)
return [{'id': video_id,
'url': video_url,
2013-06-06 13:27:27 +02:00
'title': video_title,
'thumbnail': video_thumbnail,
'ext': ext
}]
2013-05-01 15:55:46 +02:00
class BandcampIE(InfoExtractor):
_VALID_URL = r'http://.*?\.bandcamp\.com/track/(?P<title>.*)'
2013-05-01 15:55:46 +02:00
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
title = mobj.group('title')
webpage = self._download_webpage(url, title)
# We get the link to the free download page
m_download = re.search(r'freeDownloadPage: "(.*?)"', webpage)
if m_download is None:
2013-06-06 13:27:27 +02:00
raise ExtractorError(u'No free songs found')
2013-05-01 15:55:46 +02:00
download_link = m_download.group(1)
id = re.search(r'var TralbumData = {(.*?)id: (?P<id>\d*?)$',
webpage, re.MULTILINE|re.DOTALL).group('id')
download_webpage = self._download_webpage(download_link, id,
'Downloading free downloads page')
# We get the dictionary of the track from some javascrip code
info = re.search(r'items: (.*?),$',
download_webpage, re.MULTILINE).group(1)
info = json.loads(info)[0]
# We pick mp3-320 for now, until format selection can be easily implemented.
mp3_info = info[u'downloads'][u'mp3-320']
# If we try to use this url it says the link has expired
initial_url = mp3_info[u'url']
re_url = r'(?P<server>http://(.*?)\.bandcamp\.com)/download/track\?enc=mp3-320&fsig=(?P<fsig>.*?)&id=(?P<id>.*?)&ts=(?P<ts>.*)$'
2013-05-01 15:55:46 +02:00
m_url = re.match(re_url, initial_url)
#We build the url we will use to get the final track url
# This url is build in Bandcamp in the script download_bunde_*.js
request_url = '%s/statdownload/track?enc=mp3-320&fsig=%s&id=%s&ts=%s&.rand=665028774616&.vrs=1' % (m_url.group('server'), m_url.group('fsig'), id, m_url.group('ts'))
final_url_webpage = self._download_webpage(request_url, id, 'Requesting download url')
# If we could correctly generate the .rand field the url would be
#in the "download_url" key
final_url = re.search(r'"retry_url":"(.*?)"', final_url_webpage).group(1)
track_info = {'id':id,
'title' : info[u'title'],
2013-06-06 13:27:27 +02:00
'ext' : 'mp3',
'url' : final_url,
2013-05-01 15:55:46 +02:00
'thumbnail' : info[u'thumb_url'],
2013-06-06 13:27:27 +02:00
'uploader' : info[u'artist']
2013-05-01 15:55:46 +02:00
}
return [track_info]
2013-05-03 20:07:35 +02:00
class RedTubeIE(InfoExtractor):
"""Information Extractor for redtube"""
_VALID_URL = r'(?:http://)?(?:www\.)?redtube\.com/(?P<id>[0-9]+)'
def _real_extract(self,url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
2013-05-03 20:07:35 +02:00
raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group('id')
video_extension = 'mp4'
webpage = self._download_webpage(url, video_id)
2013-06-06 13:27:27 +02:00
self.report_extraction(video_id)
2013-05-03 20:07:35 +02:00
video_url = self._html_search_regex(r'<source src="(.+?)" type="video/mp4">',
2013-06-06 13:27:27 +02:00
webpage, u'video URL')
2013-05-03 20:07:35 +02:00
video_title = self._html_search_regex('<h1 class="videoTitle slidePanelMovable">(.+?)</h1>',
2013-06-06 13:27:27 +02:00
webpage, u'title')
return [{
'id': video_id,
'url': video_url,
'ext': video_extension,
'title': video_title,
}]
2013-05-05 16:07:19 +02:00
class InaIE(InfoExtractor):
"""Information Extractor for Ina.fr"""
_VALID_URL = r'(?:http://)?(?:www\.)?ina\.fr/video/(?P<id>I[0-9]+)/.*'
2013-05-05 20:57:19 +02:00
2013-05-05 16:07:19 +02:00
def _real_extract(self,url):
mobj = re.match(self._VALID_URL, url)
2013-05-05 20:57:19 +02:00
2013-05-05 16:07:19 +02:00
video_id = mobj.group('id')
2013-05-05 20:57:19 +02:00
mrss_url='http://player.ina.fr/notices/%s.mrss' % video_id
video_extension = 'mp4'
webpage = self._download_webpage(mrss_url, video_id)
2013-05-05 16:07:19 +02:00
2013-06-06 13:27:27 +02:00
self.report_extraction(video_id)
2013-05-05 20:57:19 +02:00
video_url = self._html_search_regex(r'<media:player url="(?P<mp4url>http://mp4.ina.fr/[^"]+\.mp4)',
2013-06-06 13:27:27 +02:00
webpage, u'video URL')
video_title = self._search_regex(r'<title><!\[CDATA\[(?P<titre>.*?)]]></title>',
webpage, u'title')
2013-05-05 16:07:19 +02:00
return [{
'id': video_id,
'url': video_url,
'ext': video_extension,
'title': video_title,
}]
2013-03-12 01:08:54 +01:00
class HowcastIE(InfoExtractor):
2013-05-20 00:25:26 +02:00
"""Information Extractor for Howcast.com"""
_VALID_URL = r'(?:https?://)?(?:www\.)?howcast\.com/videos/(?P<id>\d+)'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage_url = 'http://www.howcast.com/videos/' + video_id
webpage = self._download_webpage(webpage_url, video_id)
2013-05-20 08:39:41 +02:00
self.report_extraction(video_id)
2013-06-06 13:27:27 +02:00
video_url = self._search_regex(r'\'?file\'?: "(http://mobile-media\.howcast\.com/[0-9]+\.mp4)',
webpage, u'video URL')
video_title = self._html_search_regex(r'<meta content=(?:"([^"]+)"|\'([^\']+)\') property=\'og:title\'',
2013-06-06 13:27:27 +02:00
webpage, u'title')
video_description = self._html_search_regex(r'<meta content=(?:"([^"]+)"|\'([^\']+)\') name=\'description\'',
2013-06-06 13:27:27 +02:00
webpage, u'description', fatal=False)
thumbnail = self._html_search_regex(r'<meta content=\'(.+?)\' property=\'og:image\'',
2013-06-06 13:27:27 +02:00
webpage, u'thumbnail', fatal=False)
2013-05-20 08:39:41 +02:00
return [{
'id': video_id,
'url': video_url,
'ext': 'mp4',
'title': video_title,
'description': video_description,
2013-05-20 08:39:41 +02:00
'thumbnail': thumbnail,
}]
2013-05-20 00:25:26 +02:00
class VineIE(InfoExtractor):
"""Information Extractor for Vine.co"""
_VALID_URL = r'(?:https?://)?(?:www\.)?vine\.co/v/(?P<id>\w+)'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage_url = 'https://vine.co/v/' + video_id
webpage = self._download_webpage(webpage_url, video_id)
self.report_extraction(video_id)
video_url = self._html_search_regex(r'<meta property="twitter:player:stream" content="(.+?)"',
2013-06-06 13:27:27 +02:00
webpage, u'video URL')
2013-05-20 00:25:26 +02:00
video_title = self._html_search_regex(r'<meta property="og:title" content="(.+?)"',
2013-06-06 13:27:27 +02:00
webpage, u'title')
2013-05-20 00:25:26 +02:00
thumbnail = self._html_search_regex(r'<meta property="og:image" content="(.+?)(\?.*?)?"',
2013-06-06 13:27:27 +02:00
webpage, u'thumbnail', fatal=False)
uploader = self._html_search_regex(r'<div class="user">.*?<h2>(.+?)</h2>',
2013-06-06 13:27:27 +02:00
webpage, u'uploader', fatal=False, flags=re.DOTALL)
2013-05-20 00:25:26 +02:00
return [{
'id': video_id,
'url': video_url,
'ext': 'mp4',
'title': video_title,
'thumbnail': thumbnail,
'uploader': uploader,
2013-05-20 00:25:26 +02:00
}]
class FlickrIE(InfoExtractor):
"""Information Extractor for Flickr videos"""
2013-05-21 16:07:27 +02:00
_VALID_URL = r'(?:https?://)?(?:www\.)?flickr\.com/photos/(?P<uploader_id>[\w\-_@]+)/(?P<id>\d+).*'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
video_uploader_id = mobj.group('uploader_id')
webpage_url = 'http://www.flickr.com/photos/' + video_uploader_id + '/' + video_id
webpage = self._download_webpage(webpage_url, video_id)
2013-06-06 13:27:27 +02:00
secret = self._search_regex(r"photo_secret: '(\w+)'", webpage, u'secret')
first_url = 'https://secure.flickr.com/apps/video/video_mtl_xml.gne?v=x&photo_id=' + video_id + '&secret=' + secret + '&bitrate=700&target=_self'
2013-05-21 16:07:27 +02:00
first_xml = self._download_webpage(first_url, video_id, 'Downloading first data webpage')
node_id = self._html_search_regex(r'<Item id="id">(\d+-\d+)</Item>',
2013-06-06 13:27:27 +02:00
first_xml, u'node_id')
second_url = 'https://secure.flickr.com/video_playlist.gne?node_id=' + node_id + '&tech=flash&mode=playlist&bitrate=700&secret=' + secret + '&rd=video.yahoo.com&noad=1'
2013-05-21 16:07:27 +02:00
second_xml = self._download_webpage(second_url, video_id, 'Downloading second data webpage')
self.report_extraction(video_id)
mobj = re.search(r'<STREAM APP="(.+?)" FULLPATH="(.+?)"', second_xml)
if mobj is None:
raise ExtractorError(u'Unable to extract video url')
video_url = mobj.group(1) + unescapeHTML(mobj.group(2))
video_title = self._html_search_regex(r'<meta property="og:title" content=(?:"([^"]+)"|\'([^\']+)\')',
2013-06-06 13:27:27 +02:00
webpage, u'video title')
video_description = self._html_search_regex(r'<meta property="og:description" content=(?:"([^"]+)"|\'([^\']+)\')',
2013-06-06 13:27:27 +02:00
webpage, u'description', fatal=False)
thumbnail = self._html_search_regex(r'<meta property="og:image" content=(?:"([^"]+)"|\'([^\']+)\')',
2013-06-06 13:27:27 +02:00
webpage, u'thumbnail', fatal=False)
return [{
2013-05-21 16:07:27 +02:00
'id': video_id,
'url': video_url,
'ext': 'mp4',
'title': video_title,
'description': video_description,
2013-05-21 16:07:27 +02:00
'thumbnail': thumbnail,
'uploader_id': video_uploader_id,
}]
2013-05-21 14:37:32 +02:00
class TeamcocoIE(InfoExtractor):
_VALID_URL = r'http://teamcoco\.com/video/(?P<url_title>.*)'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
url_title = mobj.group('url_title')
webpage = self._download_webpage(url, url_title)
video_id = self._html_search_regex(r'<article class="video" data-id="(\d+?)"',
2013-06-06 13:27:27 +02:00
webpage, u'video id')
2013-05-21 14:37:32 +02:00
self.report_extraction(video_id)
video_title = self._html_search_regex(r'<meta property="og:title" content="(.+?)"',
2013-06-06 13:27:27 +02:00
webpage, u'title')
2013-05-21 14:37:32 +02:00
thumbnail = self._html_search_regex(r'<meta property="og:image" content="(.+?)"',
2013-06-06 13:27:27 +02:00
webpage, u'thumbnail', fatal=False)
2013-05-21 14:37:32 +02:00
video_description = self._html_search_regex(r'<meta property="og:description" content="(.*?)"',
2013-06-06 13:27:27 +02:00
webpage, u'description', fatal=False)
2013-05-21 14:37:32 +02:00
data_url = 'http://teamcoco.com/cvp/2.0/%s.xml' % video_id
data = self._download_webpage(data_url, video_id, 'Downloading data webpage')
2013-06-06 13:27:27 +02:00
video_url = self._html_search_regex(r'<file type="high".*?>(.*?)</file>',
2013-06-06 13:27:27 +02:00
data, u'video URL')
2013-05-21 14:37:32 +02:00
return [{
'id': video_id,
'url': video_url,
'ext': 'mp4',
'title': video_title,
'thumbnail': thumbnail,
2013-06-06 13:27:27 +02:00
'description': video_description,
2013-05-21 14:37:32 +02:00
}]
2013-06-07 11:46:03 +02:00
class XHamsterIE(InfoExtractor):
"""Information Extractor for xHamster"""
_VALID_URL = r'(?:http://)?(?:www.)?xhamster\.com/movies/(?P<id>[0-9]+)/.*\.html'
def _real_extract(self,url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
2013-06-07 11:46:03 +02:00
mrss_url = 'http://xhamster.com/movies/%s/.html' % video_id
webpage = self._download_webpage(mrss_url, video_id)
2013-06-07 11:46:03 +02:00
mobj = re.search(r'\'srv\': \'(?P<server>[^\']*)\',\s*\'file\': \'(?P<file>[^\']+)\',', webpage)
if mobj is None:
raise ExtractorError(u'Unable to extract media URL')
if len(mobj.group('server')) == 0:
video_url = compat_urllib_parse.unquote(mobj.group('file'))
else:
video_url = mobj.group('server')+'/key='+mobj.group('file')
video_extension = video_url.split('.')[-1]
video_title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>',
2013-06-07 11:46:03 +02:00
webpage, u'title')
# Can't see the description anywhere in the UI
# video_description = self._html_search_regex(r'<span>Description: </span>(?P<description>[^<]+)',
# webpage, u'description', fatal=False)
# if video_description: video_description = unescapeHTML(video_description)
mobj = re.search(r'hint=\'(?P<upload_date_Y>[0-9]{4})-(?P<upload_date_m>[0-9]{2})-(?P<upload_date_d>[0-9]{2}) [0-9]{2}:[0-9]{2}:[0-9]{2} [A-Z]{3,4}\'', webpage)
2013-06-07 11:46:03 +02:00
if mobj:
video_upload_date = mobj.group('upload_date_Y')+mobj.group('upload_date_m')+mobj.group('upload_date_d')
else:
2013-06-07 11:46:03 +02:00
video_upload_date = None
self._downloader.report_warning(u'Unable to extract upload date')
video_uploader_id = self._html_search_regex(r'<a href=\'/user/[^>]+>(?P<uploader_id>[^<]+)',
2013-06-07 11:46:03 +02:00
webpage, u'uploader id', default=u'anonymous')
video_thumbnail = self._search_regex(r'\'image\':\'(?P<thumbnail>[^\']+)\'',
webpage, u'thumbnail', fatal=False)
return [{
'id': video_id,
'url': video_url,
'ext': video_extension,
'title': video_title,
# 'description': video_description,
'upload_date': video_upload_date,
'uploader_id': video_uploader_id,
'thumbnail': video_thumbnail
}]
2013-06-05 16:16:53 +02:00
class HypemIE(InfoExtractor):
"""Information Extractor for hypem"""
_VALID_URL = r'(?:http://)?(?:www\.)?hypem\.com/track/([^/]+)/([^/]+)'
def _real_extract(self, url):
2013-06-05 16:16:53 +02:00
mobj = re.match(self._VALID_URL, url)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
track_id = mobj.group(1)
data = { 'ax': 1, 'ts': time.time() }
2013-06-05 16:16:53 +02:00
data_encoded = compat_urllib_parse.urlencode(data)
complete_url = url + "?" + data_encoded
2013-06-05 16:16:53 +02:00
request = compat_urllib_request.Request(complete_url)
response, urlh = self._download_webpage_handle(request, track_id, u'Downloading webpage with the url')
2013-06-05 16:16:53 +02:00
cookie = urlh.headers.get('Set-Cookie', '')
self.report_extraction(track_id)
2013-06-07 11:46:03 +02:00
html_tracks = self._html_search_regex(r'<script type="application/json" id="displayList-data">(.*?)</script>',
2013-06-07 11:46:03 +02:00
response, u'tracks', flags=re.MULTILINE|re.DOTALL).strip()
2013-06-05 16:16:53 +02:00
try:
track_list = json.loads(html_tracks)
track = track_list[u'tracks'][0]
2013-06-05 16:16:53 +02:00
except ValueError:
raise ExtractorError(u'Hypemachine contained invalid JSON.')
key = track[u"key"]
track_id = track[u"id"]
artist = track[u"artist"]
title = track[u"song"]
serve_url = "http://hypem.com/serve/source/%s/%s" % (compat_str(track_id), compat_str(key))
2013-06-05 16:16:53 +02:00
request = compat_urllib_request.Request(serve_url, "" , {'Content-Type': 'application/json'})
request.add_header('cookie', cookie)
song_data_json = self._download_webpage(request, track_id, u'Downloading metadata')
try:
song_data = json.loads(song_data_json)
except ValueError:
raise ExtractorError(u'Hypemachine contained invalid JSON.')
2013-06-05 16:16:53 +02:00
final_url = song_data[u"url"]
2013-06-05 16:16:53 +02:00
return [{
'id': track_id,
2013-06-05 16:16:53 +02:00
'url': final_url,
'ext': "mp3",
'title': title,
'artist': artist,
}]
2013-06-08 09:44:38 +02:00
class Vbox7IE(InfoExtractor):
"""Information Extractor for Vbox7"""
_VALID_URL = r'(?:http://)?(?:www\.)?vbox7\.com/play:([^/]+)'
def _real_extract(self,url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group(1)
redirect_page, urlh = self._download_webpage_handle(url, video_id)
2013-06-17 19:47:44 +02:00
new_location = self._search_regex(r'window\.location = \'(.*)\';', redirect_page, u'redirect location')
redirect_url = urlh.geturl() + new_location
2013-06-08 09:44:38 +02:00
webpage = self._download_webpage(redirect_url, video_id, u'Downloading redirect page')
2013-06-17 19:47:44 +02:00
title = self._html_search_regex(r'<title>(.*)</title>',
webpage, u'title').split('/')[0].strip()
2013-06-08 09:44:38 +02:00
ext = "flv"
info_url = "http://vbox7.com/play/magare.do"
data = compat_urllib_parse.urlencode({'as3':'1','vid':video_id})
info_request = compat_urllib_request.Request(info_url, data)
info_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
info_response = self._download_webpage(info_request, video_id, u'Downloading info webpage')
if info_response is None:
raise ExtractorError(u'Unable to extract the media url')
(final_url, thumbnail_url) = map(lambda x: x.split('=')[1], info_response.split('&'))
2013-06-08 09:44:38 +02:00
return [{
'id': video_id,
'url': final_url,
'ext': ext,
'title': title,
'thumbnail': thumbnail_url,
2013-06-08 09:44:38 +02:00
}]
2013-06-05 16:16:53 +02:00
2013-06-16 20:34:45 +02:00
2013-01-01 19:37:07 +01:00
def gen_extractors():
""" Return a list of an instance of every supported extractor.
The order does matter; the first extractor matched is the one handling the URL.
"""
return [
YoutubePlaylistIE(),
YoutubeChannelIE(),
YoutubeUserIE(),
YoutubeSearchIE(),
YoutubeIE(),
MetacafeIE(),
DailymotionIE(),
GoogleSearchIE(),
PhotobucketIE(),
YahooIE(),
YahooSearchIE(),
DepositFilesIE(),
FacebookIE(),
BlipTVIE(),
BlipTVUserIE(),
2013-01-01 19:37:07 +01:00
VimeoIE(),
MyVideoIE(),
ComedyCentralIE(),
EscapistIE(),
CollegeHumorIE(),
XVideosIE(),
SoundcloudSetIE(),
2013-01-01 19:37:07 +01:00
SoundcloudIE(),
InfoQIE(),
MixcloudIE(),
StanfordOpenClassroomIE(),
MTVIE(),
YoukuIE(),
XNXXIE(),
2013-01-06 21:52:33 +01:00
YouJizzIE(),
PornotubeIE(),
YouPornIE(),
2013-01-01 19:37:07 +01:00
GooglePlusIE(),
ArteTvIE(),
NBAIE(),
2013-03-07 06:09:55 +01:00
WorldStarHipHopIE(),
2013-01-01 19:37:07 +01:00
JustinTVIE(),
FunnyOrDieIE(),
SteamIE(),
UstreamIE(),
2013-01-12 17:58:39 +01:00
RBMARadioIE(),
2013-01-27 03:01:23 +01:00
EightTracksIE(),
2013-02-08 08:25:55 +01:00
KeekIE(),
2013-02-17 17:13:06 +01:00
TEDIE(),
2013-02-18 18:45:09 +01:00
MySpassIE(),
2013-03-12 01:08:54 +01:00
SpiegelIE(),
LiveLeakIE(),
ARDIE(),
ZDFIE(),
TumblrIE(),
2013-05-01 15:55:46 +02:00
BandcampIE(),
2013-05-03 20:07:35 +02:00
RedTubeIE(),
2013-05-05 20:57:19 +02:00
InaIE(),
HowcastIE(),
2013-05-20 00:25:26 +02:00
VineIE(),
FlickrIE(),
2013-05-21 14:37:32 +02:00
TeamcocoIE(),
XHamsterIE(),
2013-06-05 16:16:53 +02:00
HypemIE(),
2013-06-08 09:44:38 +02:00
Vbox7IE(),
2013-06-16 20:34:45 +02:00
GametrailersIE(),
2013-06-23 18:58:53 +02:00
StatigramIE(),
2013-01-01 19:37:07 +01:00
GenericIE()
]
def get_info_extractor(ie_name):
"""Returns the info extractor class with the given ie_name"""
return globals()[ie_name+'IE']