2013-01-01 15:07:37 -05:00
|
|
|
import base64
|
2012-03-24 21:07:37 -04:00
|
|
|
import datetime
|
2013-01-26 21:01:23 -05:00
|
|
|
import itertools
|
2012-03-24 21:07:37 -04:00
|
|
|
import netrc
|
|
|
|
import os
|
|
|
|
import re
|
|
|
|
import socket
|
|
|
|
import time
|
|
|
|
import email.utils
|
2012-05-01 11:01:51 -04:00
|
|
|
import xml.etree.ElementTree
|
2012-08-08 14:04:02 -04:00
|
|
|
import random
|
|
|
|
import math
|
2013-02-26 04:39:26 -05:00
|
|
|
import operator
|
2013-05-15 17:38:44 -04:00
|
|
|
import hashlib
|
|
|
|
import binascii
|
|
|
|
import urllib
|
2012-03-24 21:07:37 -04:00
|
|
|
|
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
|
2013-06-23 14:24:07 -04:00
|
|
|
|
|
|
|
from .extractor.ard import ARDIE
|
|
|
|
from .extractor.arte import ArteTvIE
|
2013-06-23 16:24:58 -04:00
|
|
|
from .extractor.bandcamp import BandcampIE
|
2013-06-23 14:44:48 -04:00
|
|
|
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
|
2013-06-23 14:55:15 -04:00
|
|
|
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
|
2013-06-23 16:23:19 -04:00
|
|
|
from .extractor.liveleak import LiveLeakIE
|
2013-06-23 14:07:51 -04:00
|
|
|
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 16:20:45 -04:00
|
|
|
from .extractor.myspass import MySpassIE
|
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
|
2013-06-23 14:07:51 -04:00
|
|
|
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 16:22:08 -04:00
|
|
|
from .extractor.spiegel import SpiegelIE
|
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 16:24:07 -04:00
|
|
|
from .extractor.tumblr import TumblrIE
|
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
|
2013-06-23 15:11:47 -04:00
|
|
|
from .extractor.xvideos import XVideosIE
|
2013-06-23 14:41:54 -04:00
|
|
|
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
|
2013-06-23 14:28:15 -04:00
|
|
|
from .extractor.youtube import YoutubeIE, YoutubePlaylistIE, YoutubeSearchIE, YoutubeUserIE, YoutubeChannelIE
|
2013-06-23 14:24:07 -04:00
|
|
|
from .extractor.zdf import ZDFIE
|
2013-05-11 17:04:56 -04:00
|
|
|
|
2013-01-01 14:43:43 -05:00
|
|
|
|
2012-03-24 21:07:37 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
2012-08-15 19:54:03 -04:00
|
|
|
|
2012-08-08 14:04:02 -04:00
|
|
|
|
2012-08-19 12:39:43 -04:00
|
|
|
|
|
|
|
|
2012-10-09 04:48:49 -04:00
|
|
|
|
|
|
|
|
2012-12-13 15:27:57 -05:00
|
|
|
|
2012-12-16 03:50:41 -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
|
|
|
|
|
|
|
|
2013-02-26 04:39:26 -05:00
|
|
|
|
2013-01-05 15:42:35 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-02-08 02:25:55 -05:00
|
|
|
|
|
|
|
|
2013-02-16 07:46:13 -05:00
|
|
|
|
2013-03-11 20:08:54 -04:00
|
|
|
|
2013-03-26 16:37:08 -04:00
|
|
|
|
2013-05-23 15:42:03 -04:00
|
|
|
|
|
|
|
|
2013-04-22 15:07:49 -04:00
|
|
|
|
2013-05-01 09:55:46 -04:00
|
|
|
|
2013-05-03 14:07:35 -04:00
|
|
|
class RedTubeIE(InfoExtractor):
|
2013-05-03 13:57:16 -04:00
|
|
|
"""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)
|
|
|
|
|
2013-05-03 13:57:16 -04:00
|
|
|
video_id = mobj.group('id')
|
|
|
|
video_extension = 'mp4'
|
|
|
|
webpage = self._download_webpage(url, video_id)
|
2013-06-06 07:27:27 -04:00
|
|
|
|
2013-05-03 13:57:16 -04:00
|
|
|
self.report_extraction(video_id)
|
2013-05-03 14:07:35 -04:00
|
|
|
|
2013-06-09 05:57:13 -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
|
|
|
|
2013-06-09 05:57:13 -04:00
|
|
|
video_title = self._html_search_regex('<h1 class="videoTitle slidePanelMovable">(.+?)</h1>',
|
2013-06-06 07:27:27 -04:00
|
|
|
webpage, u'title')
|
2013-05-03 13:57:16 -04:00
|
|
|
|
|
|
|
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"""
|
2013-05-18 13:17:19 -04:00
|
|
|
_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
|
|
|
|
2013-06-09 05:57:13 -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
|
|
|
|
2013-05-18 13:17:19 -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+)'
|
2013-05-18 13:17:19 -04:00
|
|
|
|
|
|
|
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')
|
2013-05-18 13:17:19 -04:00
|
|
|
|
2013-06-09 05:57:13 -04:00
|
|
|
video_title = self._html_search_regex(r'<meta content=(?:"([^"]+)"|\'([^\']+)\') property=\'og:title\'',
|
2013-06-06 07:27:27 -04:00
|
|
|
webpage, u'title')
|
2013-05-18 13:17:19 -04:00
|
|
|
|
2013-06-09 05:57:13 -04:00
|
|
|
video_description = self._html_search_regex(r'<meta content=(?:"([^"]+)"|\'([^\']+)\') name=\'description\'',
|
2013-06-06 07:27:27 -04:00
|
|
|
webpage, u'description', fatal=False)
|
2013-05-18 13:17:19 -04:00
|
|
|
|
2013-06-09 05:57:13 -04:00
|
|
|
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
|
|
|
|
2013-05-18 13:17:19 -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,
|
2013-05-18 13:17:19 -04:00
|
|
|
}]
|
|
|
|
|
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)
|
|
|
|
|
2013-05-20 02:31:03 -04:00
|
|
|
self.report_extraction(video_id)
|
|
|
|
|
2013-06-09 05:57:13 -04:00
|
|
|
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
|
|
|
|
2013-06-09 05:57:13 -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
|
|
|
|
2013-06-09 05:57:13 -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)
|
2013-05-20 02:31:03 -04:00
|
|
|
|
2013-06-09 05:57:13 -04:00
|
|
|
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)
|
2013-05-20 02:31:03 -04:00
|
|
|
|
2013-05-19 18:25:26 -04:00
|
|
|
return [{
|
2013-05-20 02:31:03 -04:00
|
|
|
'id': video_id,
|
|
|
|
'url': video_url,
|
|
|
|
'ext': 'mp4',
|
|
|
|
'title': video_title,
|
|
|
|
'thumbnail': thumbnail,
|
|
|
|
'uploader': uploader,
|
2013-05-19 18:25:26 -04:00
|
|
|
}]
|
|
|
|
|
2013-05-20 17:18:40 -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+).*'
|
2013-05-20 17:18:40 -04:00
|
|
|
|
|
|
|
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')
|
2013-05-20 17:18:40 -04:00
|
|
|
|
|
|
|
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')
|
2013-05-20 17:18:40 -04:00
|
|
|
|
2013-06-09 05:57:13 -04:00
|
|
|
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')
|
2013-05-20 17:18:40 -04:00
|
|
|
|
|
|
|
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)
|
2013-05-20 17:18:40 -04:00
|
|
|
|
|
|
|
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))
|
|
|
|
|
2013-06-09 05:57:13 -04:00
|
|
|
video_title = self._html_search_regex(r'<meta property="og:title" content=(?:"([^"]+)"|\'([^\']+)\')',
|
2013-06-06 07:27:27 -04:00
|
|
|
webpage, u'video title')
|
2013-05-20 17:18:40 -04:00
|
|
|
|
2013-06-09 05:57:13 -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)
|
2013-05-20 17:18:40 -04:00
|
|
|
|
2013-06-09 05:57:13 -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)
|
2013-05-20 17:18:40 -04:00
|
|
|
|
|
|
|
return [{
|
2013-05-21 10:07:27 -04:00
|
|
|
'id': video_id,
|
|
|
|
'url': video_url,
|
|
|
|
'ext': 'mp4',
|
|
|
|
'title': video_title,
|
2013-05-20 17:18:40 -04:00
|
|
|
'description': video_description,
|
2013-05-21 10:07:27 -04:00
|
|
|
'thumbnail': thumbnail,
|
2013-05-20 17:18:40 -04:00
|
|
|
'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)
|
|
|
|
|
2013-06-09 05:57:13 -04:00
|
|
|
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)
|
|
|
|
|
2013-06-09 05:57:13 -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')
|
2013-05-21 08:37:32 -04:00
|
|
|
|
2013-06-09 05:57:13 -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
|
|
|
|
2013-06-09 05:57:13 -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
|
|
|
|
2013-06-09 05:57:13 -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
|
|
|
|
2013-06-04 08:30:54 -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
|
2013-06-04 08:30:54 -04:00
|
|
|
webpage = self._download_webpage(mrss_url, video_id)
|
2013-06-07 05:46:03 -04:00
|
|
|
|
2013-06-04 08:30:54 -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]
|
|
|
|
|
2013-06-09 05:57:13 -04:00
|
|
|
video_title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>',
|
2013-06-07 05:46:03 -04:00
|
|
|
webpage, u'title')
|
2013-06-04 08:30:54 -04:00
|
|
|
|
2013-06-07 06:10:02 -04:00
|
|
|
# Can't see the description anywhere in the UI
|
2013-06-09 05:57:13 -04:00
|
|
|
# video_description = self._html_search_regex(r'<span>Description: </span>(?P<description>[^<]+)',
|
2013-06-07 06:10:02 -04:00
|
|
|
# webpage, u'description', fatal=False)
|
|
|
|
# if video_description: video_description = unescapeHTML(video_description)
|
2013-06-04 08:30:54 -04:00
|
|
|
|
|
|
|
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')
|
2013-06-04 08:30:54 -04:00
|
|
|
else:
|
2013-06-07 05:46:03 -04:00
|
|
|
video_upload_date = None
|
|
|
|
self._downloader.report_warning(u'Unable to extract upload date')
|
2013-06-04 08:30:54 -04:00
|
|
|
|
2013-06-09 08:21:42 -04:00
|
|
|
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)
|
2013-06-04 08:30:54 -04:00
|
|
|
|
|
|
|
return [{
|
|
|
|
'id': video_id,
|
|
|
|
'url': video_url,
|
|
|
|
'ext': video_extension,
|
|
|
|
'title': video_title,
|
2013-06-07 06:10:02 -04:00
|
|
|
# 'description': video_description,
|
2013-06-04 08:30:54 -04:00
|
|
|
'upload_date': video_upload_date,
|
|
|
|
'uploader_id': video_uploader_id,
|
|
|
|
'thumbnail': video_thumbnail
|
|
|
|
}]
|
2013-05-20 17:18:40 -04:00
|
|
|
|
2013-06-05 10:16:53 -04:00
|
|
|
class HypemIE(InfoExtractor):
|
|
|
|
"""Information Extractor for hypem"""
|
|
|
|
_VALID_URL = r'(?:http://)?(?:www\.)?hypem\.com/track/([^/]+)/([^/]+)'
|
|
|
|
|
2013-06-06 06:02:36 -04:00
|
|
|
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)
|
2013-06-06 06:02:36 -04:00
|
|
|
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)
|
2013-06-06 06:02:36 -04:00
|
|
|
complete_url = url + "?" + data_encoded
|
2013-06-05 10:16:53 -04:00
|
|
|
request = compat_urllib_request.Request(complete_url)
|
2013-06-06 06:02:36 -04:00
|
|
|
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', '')
|
2013-06-06 06:02:36 -04:00
|
|
|
|
|
|
|
self.report_extraction(track_id)
|
2013-06-07 05:46:03 -04:00
|
|
|
|
2013-06-09 05:57:13 -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)
|
2013-06-06 06:02:36 -04:00
|
|
|
track = track_list[u'tracks'][0]
|
2013-06-05 10:16:53 -04:00
|
|
|
except ValueError:
|
2013-06-06 06:02:36 -04:00
|
|
|
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)
|
2013-06-06 06:02:36 -04:00
|
|
|
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"]
|
2013-06-06 06:02:36 -04:00
|
|
|
|
2013-06-05 10:16:53 -04:00
|
|
|
return [{
|
2013-06-06 06:02:36 -04:00
|
|
|
'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')
|
2013-06-08 04:47:52 -04:00
|
|
|
(final_url, thumbnail_url) = map(lambda x: x.split('=')[1], info_response.split('&'))
|
2013-06-08 03:44:38 -04:00
|
|
|
|
|
|
|
return [{
|
2013-06-08 04:47:52 -04:00
|
|
|
'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(),
|
2013-05-28 09:12:39 -04:00
|
|
|
BlipTVUserIE(),
|
2013-01-01 13:37:07 -05:00
|
|
|
VimeoIE(),
|
|
|
|
MyVideoIE(),
|
|
|
|
ComedyCentralIE(),
|
|
|
|
EscapistIE(),
|
|
|
|
CollegeHumorIE(),
|
|
|
|
XVideosIE(),
|
2013-03-23 21:24:07 -04:00
|
|
|
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(),
|
2013-03-29 10:13:24 -04:00
|
|
|
LiveLeakIE(),
|
2013-04-07 09:23:48 -04:00
|
|
|
ARDIE(),
|
2013-05-23 15:42:03 -04:00
|
|
|
ZDFIE(),
|
2013-04-22 15:07:49 -04:00
|
|
|
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(),
|
2013-05-18 13:17:19 -04:00
|
|
|
HowcastIE(),
|
2013-05-19 18:25:26 -04:00
|
|
|
VineIE(),
|
2013-05-20 17:18:40 -04:00
|
|
|
FlickrIE(),
|
2013-05-21 08:37:32 -04:00
|
|
|
TeamcocoIE(),
|
2013-06-04 08:30:54 -04:00
|
|
|
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()
|
|
|
|
]
|
2013-04-20 06:42:57 -04:00
|
|
|
|
|
|
|
def get_info_extractor(ie_name):
|
|
|
|
"""Returns the info extractor class with the given ie_name"""
|
|
|
|
return globals()[ie_name+'IE']
|