yt-dlp/youtube_dl/InfoExtractors.py

719 lines
26 KiB
Python
Raw Normal View History

2013-01-01 15:07:37 -05:00
import base64
import datetime
2013-01-26 21:01:23 -05:00
import itertools
import netrc
import os
import re
import socket
import time
import email.utils
import xml.etree.ElementTree
2012-08-08 14:04:02 -04:00
import random
import math
import operator
2013-05-15 17:38:44 -04:00
import hashlib
import binascii
import urllib
2012-11-27 21:34:40 -05:00
from .utils import *
2013-06-23 13:57:38 -04:00
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 14:50:22 -04:00
from .extractor.comedycentral import ComedyCentralIE
2013-06-23 15:10:21 -04:00
from .extractor.collegehumor import CollegeHumorIE
2013-06-23 14:09:47 -04:00
from .extractor.dailymotion import DailymotionIE
2013-06-23 15:06:20 -04:00
from .extractor.depositfiles import DepositFilesIE
2013-06-23 16:15:50 -04:00
from .extractor.eighttracks import EightTracksIE
2013-06-23 15:08:17 -04:00
from .extractor.escapist import EscapistIE
2013-06-23 15:00:34 -04:00
from .extractor.facebook import FacebookIE
2013-06-23 16:05:23 -04:00
from .extractor.funnyordie import FunnyOrDieIE
2013-06-23 14:29:46 -04:00
from .extractor.gametrailers import GametrailersIE
2013-06-23 14:31:45 -04:00
from .extractor.generic import GenericIE
from .extractor.googleplus import GooglePlusIE
from .extractor.googlesearch import GoogleSearchIE
2013-06-23 15:14:19 -04:00
from .extractor.infoq import InfoQIE
2013-06-23 16:07:27 -04:00
from .extractor.justintv import JustinTVIE
2013-06-23 16:16:41 -04:00
from .extractor.keek import KeekIE
from .extractor.metacafe import MetacafeIE
2013-06-23 15:59:15 -04:00
from .extractor.mixcloud import MixcloudIE
2013-06-23 15:27:38 -04:00
from .extractor.mtv import MTVIE
2013-06-23 14:48:32 -04:00
from .extractor.myvideo import MyVideoIE
2013-06-23 15:18:00 -04:00
from .extractor.nba import NBAIE
from .extractor.statigram import StatigramIE
2013-06-23 14:12:18 -04:00
from .extractor.photobucket import PhotobucketIE
2013-06-23 16:13:32 -04:00
from .extractor.pornotube import PornotubeIE
2013-06-23 16:09:32 -04:00
from .extractor.rbmaradio import RBMARadioIE
2013-06-23 14:57:44 -04:00
from .extractor.soundcloud import SoundcloudIE, SoundcloudSetIE
2013-06-23 15:16:32 -04:00
from .extractor.stanfordoc import StanfordOpenClassroomIE
2013-06-23 16:02:56 -04:00
from .extractor.steam import SteamIE
2013-06-23 15:55:53 -04:00
from .extractor.ted import TEDIE
2013-06-23 16:08:28 -04:00
from .extractor.ustream import UstreamIE
2013-06-23 14:18:21 -04:00
from .extractor.vimeo import VimeoIE
2013-06-23 16:04:08 -04:00
from .extractor.worldstarhiphop import WorldStarHipHopIE
2013-06-23 16:02:56 -04:00
from .extractor.xnxx import XNXXIE
from .extractor.xvideos import XVideosIE
from .extractor.yahoo import YahooIE, YahooSearchIE
2013-06-23 16:14:22 -04:00
from .extractor.youjizz import YouJizzIE
2013-06-23 16:01:02 -04:00
from .extractor.youku import YoukuIE
2013-06-23 16:12:14 -04:00
from .extractor.youporn import YouPornIE
from .extractor.youtube import YoutubeIE, YoutubePlaylistIE, YoutubeSearchIE, YoutubeUserIE, YoutubeChannelIE
from .extractor.zdf import ZDFIE
2013-01-01 14:43:43 -05:00
2012-08-15 19:54:03 -04:00
2012-08-08 14:04:02 -04:00
2012-12-13 15:27:57 -05:00
2012-12-20 15:28:27 -05:00
2012-12-26 19:38:41 -05:00
2013-01-12 07:49:14 -05:00
2013-01-01 13:37:07 -05:00
2013-03-07 00:09:55 -05:00
2013-01-01 13:37:07 -05:00
2013-01-05 15:42:35 -05:00
2013-01-05 15:42:35 -05:00
2013-02-08 02:25:55 -05:00
2013-02-18 12:45:09 -05:00
class MySpassIE(InfoExtractor):
2013-02-16 07:46:13 -05:00
_VALID_URL = r'http://www.myspass.de/.*'
2013-02-16 07:46:13 -05:00
def _real_extract(self, url):
META_DATA_URL_TEMPLATE = 'http://www.myspass.de/myspass/includes/apps/video/getvideometadataxml.php?id=%s'
2013-02-18 12:45:09 -05:00
2013-02-16 07:46:13 -05:00
# 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 07:46:13 -05:00
# 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 07:46:13 -05:00
# 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 07:46:13 -05:00
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 07:46:13 -05:00
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]
2013-03-11 20:08:54 -04:00
class SpiegelIE(InfoExtractor):
2013-03-29 10:31:38 -04:00
_VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<videoID>[0-9]+)(?:\.html)?(?:#.*)?$'
2013-03-11 20:08:54 -04:00
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 07:27:27 -04:00
video_title = self._html_search_regex(r'<div class="module-title">(.*?)</div>',
2013-06-06 07:27:27 -04:00
webpage, u'title')
2013-03-11 20:08:54 -04:00
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 16:37:08 -04:00
_VALID_URL = r'^(?:http?://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<video_id>[\w_]+)(?:.*)'
2013-03-26 16:37:08 -04:00
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 16:37:08 -04:00
video_id = mobj.group('video_id')
2013-03-26 16:37:08 -04:00
webpage = self._download_webpage(url, video_id)
2013-06-06 07:27:27 -04:00
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 16:37:08 -04:00
video_description = self._html_search_regex(r'<meta property="og:description" content="(?P<desc>.*?)"',
2013-06-06 07:27:27 -04:00
webpage, u'description', fatal=False)
2013-03-26 16:37:08 -04:00
video_uploader = self._html_search_regex(r'By:.*?(\w+)</a>',
2013-06-06 07:27:27 -04:00
webpage, u'uploader', fatal=False)
2013-03-26 16:37:08 -04:00
info = {
'id': video_id,
'url': video_url,
'ext': 'mp4',
2013-06-06 07:27:27 -04:00
'title': video_title,
'description': video_description,
'uploader': video_uploader
2013-03-26 16:37:08 -04:00
}
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 07:27:27 -04:00
raise ExtractorError(u'Unable to extract video')
video_url = video.group('video_url')
ext = video.group('ext')
2013-06-06 07:27:27 -04:00
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 07:27:27 -04:00
webpage, u'title', flags=re.DOTALL)
return [{'id': video_id,
'url': video_url,
2013-06-06 07:27:27 -04:00
'title': video_title,
'thumbnail': video_thumbnail,
'ext': ext
}]
2013-05-01 09:55:46 -04:00
class BandcampIE(InfoExtractor):
_VALID_URL = r'http://.*?\.bandcamp\.com/track/(?P<title>.*)'
2013-05-01 09:55:46 -04:00
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 07:27:27 -04:00
raise ExtractorError(u'No free songs found')
2013-05-01 09:55:46 -04:00
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 09:55:46 -04:00
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 07:27:27 -04:00
'ext' : 'mp3',
'url' : final_url,
2013-05-01 09:55:46 -04:00
'thumbnail' : info[u'thumb_url'],
2013-06-06 07:27:27 -04:00
'uploader' : info[u'artist']
2013-05-01 09:55:46 -04:00
}
return [track_info]
2013-05-03 14:07:35 -04:00
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 14:07:35 -04:00
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 07:27:27 -04:00
self.report_extraction(video_id)
2013-05-03 14:07:35 -04:00
video_url = self._html_search_regex(r'<source src="(.+?)" type="video/mp4">',
2013-06-06 07:27:27 -04:00
webpage, u'video URL')
2013-05-03 14:07:35 -04:00
video_title = self._html_search_regex('<h1 class="videoTitle slidePanelMovable">(.+?)</h1>',
2013-06-06 07:27:27 -04:00
webpage, u'title')
return [{
'id': video_id,
'url': video_url,
'ext': video_extension,
'title': video_title,
}]
2013-05-05 10:07:19 -04:00
class InaIE(InfoExtractor):
"""Information Extractor for Ina.fr"""
_VALID_URL = r'(?:http://)?(?:www\.)?ina\.fr/video/(?P<id>I[0-9]+)/.*'
2013-05-05 14:57:19 -04:00
2013-05-05 10:07:19 -04:00
def _real_extract(self,url):
mobj = re.match(self._VALID_URL, url)
2013-05-05 14:57:19 -04:00
2013-05-05 10:07:19 -04:00
video_id = mobj.group('id')
2013-05-05 14:57:19 -04:00
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 10:07:19 -04:00
2013-06-06 07:27:27 -04:00
self.report_extraction(video_id)
2013-05-05 14:57:19 -04:00
video_url = self._html_search_regex(r'<media:player url="(?P<mp4url>http://mp4.ina.fr/[^"]+\.mp4)',
2013-06-06 07:27:27 -04:00
webpage, u'video URL')
video_title = self._search_regex(r'<title><!\[CDATA\[(?P<titre>.*?)]]></title>',
webpage, u'title')
2013-05-05 10:07:19 -04:00
return [{
'id': video_id,
'url': video_url,
'ext': video_extension,
'title': video_title,
}]
2013-03-11 20:08:54 -04:00
class HowcastIE(InfoExtractor):
2013-05-19 18:25:26 -04:00
"""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 02:39:41 -04:00
self.report_extraction(video_id)
2013-06-06 07:27:27 -04:00
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 07:27:27 -04:00
webpage, u'title')
video_description = self._html_search_regex(r'<meta content=(?:"([^"]+)"|\'([^\']+)\') name=\'description\'',
2013-06-06 07:27:27 -04:00
webpage, u'description', fatal=False)
thumbnail = self._html_search_regex(r'<meta content=\'(.+?)\' property=\'og:image\'',
2013-06-06 07:27:27 -04:00
webpage, u'thumbnail', fatal=False)
2013-05-20 02:39:41 -04:00
return [{
'id': video_id,
'url': video_url,
'ext': 'mp4',
'title': video_title,
'description': video_description,
2013-05-20 02:39:41 -04:00
'thumbnail': thumbnail,
}]
2013-05-19 18:25:26 -04:00
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 07:27:27 -04:00
webpage, u'video URL')
2013-05-19 18:25:26 -04:00
video_title = self._html_search_regex(r'<meta property="og:title" content="(.+?)"',
2013-06-06 07:27:27 -04:00
webpage, u'title')
2013-05-19 18:25:26 -04:00
thumbnail = self._html_search_regex(r'<meta property="og:image" content="(.+?)(\?.*?)?"',
2013-06-06 07:27:27 -04:00
webpage, u'thumbnail', fatal=False)
uploader = self._html_search_regex(r'<div class="user">.*?<h2>(.+?)</h2>',
2013-06-06 07:27:27 -04:00
webpage, u'uploader', fatal=False, flags=re.DOTALL)
2013-05-19 18:25:26 -04:00
return [{
'id': video_id,
'url': video_url,
'ext': 'mp4',
'title': video_title,
'thumbnail': thumbnail,
'uploader': uploader,
2013-05-19 18:25:26 -04:00
}]
class FlickrIE(InfoExtractor):
"""Information Extractor for Flickr videos"""
2013-05-21 10:07:27 -04:00
_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 07:27:27 -04:00
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 10:07:27 -04:00
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 07:27:27 -04:00
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 10:07:27 -04:00
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 07:27:27 -04:00
webpage, u'video title')
video_description = self._html_search_regex(r'<meta property="og:description" content=(?:"([^"]+)"|\'([^\']+)\')',
2013-06-06 07:27:27 -04:00
webpage, u'description', fatal=False)
thumbnail = self._html_search_regex(r'<meta property="og:image" content=(?:"([^"]+)"|\'([^\']+)\')',
2013-06-06 07:27:27 -04:00
webpage, u'thumbnail', fatal=False)
return [{
2013-05-21 10:07:27 -04:00
'id': video_id,
'url': video_url,
'ext': 'mp4',
'title': video_title,
'description': video_description,
2013-05-21 10:07:27 -04:00
'thumbnail': thumbnail,
'uploader_id': video_uploader_id,
}]
2013-05-21 08:37:32 -04:00
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 07:27:27 -04:00
webpage, u'video id')
2013-05-21 08:37:32 -04:00
self.report_extraction(video_id)
video_title = self._html_search_regex(r'<meta property="og:title" content="(.+?)"',
2013-06-06 07:27:27 -04:00
webpage, u'title')
2013-05-21 08:37:32 -04:00
thumbnail = self._html_search_regex(r'<meta property="og:image" content="(.+?)"',
2013-06-06 07:27:27 -04:00
webpage, u'thumbnail', fatal=False)
2013-05-21 08:37:32 -04:00
video_description = self._html_search_regex(r'<meta property="og:description" content="(.*?)"',
2013-06-06 07:27:27 -04:00
webpage, u'description', fatal=False)
2013-05-21 08:37:32 -04:00
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 07:27:27 -04:00
video_url = self._html_search_regex(r'<file type="high".*?>(.*?)</file>',
2013-06-06 07:27:27 -04:00
data, u'video URL')
2013-05-21 08:37:32 -04:00
return [{
'id': video_id,
'url': video_url,
'ext': 'mp4',
'title': video_title,
'thumbnail': thumbnail,
2013-06-06 07:27:27 -04:00
'description': video_description,
2013-05-21 08:37:32 -04:00
}]
2013-06-07 05:46:03 -04:00
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 05:46:03 -04:00
mrss_url = 'http://xhamster.com/movies/%s/.html' % video_id
webpage = self._download_webpage(mrss_url, video_id)
2013-06-07 05:46:03 -04:00
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 05:46:03 -04:00
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 05:46:03 -04:00
if mobj:
video_upload_date = mobj.group('upload_date_Y')+mobj.group('upload_date_m')+mobj.group('upload_date_d')
else:
2013-06-07 05:46:03 -04:00
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 05:46:03 -04:00
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 10:16:53 -04:00
class HypemIE(InfoExtractor):
"""Information Extractor for hypem"""
_VALID_URL = r'(?:http://)?(?:www\.)?hypem\.com/track/([^/]+)/([^/]+)'
def _real_extract(self, url):
2013-06-05 10:16:53 -04:00
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 10:16:53 -04:00
data_encoded = compat_urllib_parse.urlencode(data)
complete_url = url + "?" + data_encoded
2013-06-05 10:16:53 -04:00
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 10:16:53 -04:00
cookie = urlh.headers.get('Set-Cookie', '')
self.report_extraction(track_id)
2013-06-07 05:46:03 -04:00
html_tracks = self._html_search_regex(r'<script type="application/json" id="displayList-data">(.*?)</script>',
2013-06-07 05:46:03 -04:00
response, u'tracks', flags=re.MULTILINE|re.DOTALL).strip()
2013-06-05 10:16:53 -04:00
try:
track_list = json.loads(html_tracks)
track = track_list[u'tracks'][0]
2013-06-05 10:16:53 -04:00
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 10:16:53 -04:00
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 10:16:53 -04:00
final_url = song_data[u"url"]
2013-06-05 10:16:53 -04:00
return [{
'id': track_id,
2013-06-05 10:16:53 -04:00
'url': final_url,
'ext': "mp3",
'title': title,
'artist': artist,
}]
2013-06-08 03:44:38 -04:00
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 13:47:44 -04:00
new_location = self._search_regex(r'window\.location = \'(.*)\';', redirect_page, u'redirect location')
redirect_url = urlh.geturl() + new_location
2013-06-08 03:44:38 -04:00
webpage = self._download_webpage(redirect_url, video_id, u'Downloading redirect page')
2013-06-17 13:47:44 -04:00
title = self._html_search_regex(r'<title>(.*)</title>',
webpage, u'title').split('/')[0].strip()
2013-06-08 03:44:38 -04:00
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 03:44:38 -04:00
return [{
'id': video_id,
'url': final_url,
'ext': ext,
'title': title,
'thumbnail': thumbnail_url,
2013-06-08 03:44:38 -04:00
}]
2013-06-05 10:16:53 -04:00
2013-06-16 14:34:45 -04:00
2013-01-01 13:37:07 -05:00
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 13:37:07 -05:00
VimeoIE(),
MyVideoIE(),
ComedyCentralIE(),
EscapistIE(),
CollegeHumorIE(),
XVideosIE(),
SoundcloudSetIE(),
2013-01-01 13:37:07 -05:00
SoundcloudIE(),
InfoQIE(),
MixcloudIE(),
StanfordOpenClassroomIE(),
MTVIE(),
YoukuIE(),
XNXXIE(),
2013-01-06 15:52:33 -05:00
YouJizzIE(),
PornotubeIE(),
YouPornIE(),
2013-01-01 13:37:07 -05:00
GooglePlusIE(),
ArteTvIE(),
NBAIE(),
2013-03-07 00:09:55 -05:00
WorldStarHipHopIE(),
2013-01-01 13:37:07 -05:00
JustinTVIE(),
FunnyOrDieIE(),
SteamIE(),
UstreamIE(),
2013-01-12 11:58:39 -05:00
RBMARadioIE(),
2013-01-26 21:01:23 -05:00
EightTracksIE(),
2013-02-08 02:25:55 -05:00
KeekIE(),
2013-02-17 11:13:06 -05:00
TEDIE(),
2013-02-18 12:45:09 -05:00
MySpassIE(),
2013-03-11 20:08:54 -04:00
SpiegelIE(),
LiveLeakIE(),
ARDIE(),
ZDFIE(),
TumblrIE(),
2013-05-01 09:55:46 -04:00
BandcampIE(),
2013-05-03 14:07:35 -04:00
RedTubeIE(),
2013-05-05 14:57:19 -04:00
InaIE(),
HowcastIE(),
2013-05-19 18:25:26 -04:00
VineIE(),
FlickrIE(),
2013-05-21 08:37:32 -04:00
TeamcocoIE(),
XHamsterIE(),
2013-06-05 10:16:53 -04:00
HypemIE(),
2013-06-08 03:44:38 -04:00
Vbox7IE(),
2013-06-16 14:34:45 -04:00
GametrailersIE(),
2013-06-23 12:58:53 -04:00
StatigramIE(),
2013-01-01 13:37:07 -05:00
GenericIE()
]
def get_info_extractor(ie_name):
"""Returns the info extractor class with the given ie_name"""
return globals()[ie_name+'IE']