1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
|
import base64
import datetime
import itertools
import netrc
import os
import re
import socket
import time
import email.utils
import xml.etree.ElementTree
import random
import math
import operator
import hashlib
import binascii
import urllib
from .utils import *
from .extractor.common import InfoExtractor, SearchInfoExtractor
from .extractor.ard import ARDIE
from .extractor.arte import ArteTvIE
from .extractor.bandcamp import BandcampIE
from .extractor.bliptv import BlipTVIE, BlipTVUserIE
from .extractor.comedycentral import ComedyCentralIE
from .extractor.collegehumor import CollegeHumorIE
from .extractor.dailymotion import DailymotionIE
from .extractor.depositfiles import DepositFilesIE
from .extractor.eighttracks import EightTracksIE
from .extractor.escapist import EscapistIE
from .extractor.facebook import FacebookIE
from .extractor.flickr import FlickrIE
from .extractor.funnyordie import FunnyOrDieIE
from .extractor.gametrailers import GametrailersIE
from .extractor.generic import GenericIE
from .extractor.googleplus import GooglePlusIE
from .extractor.googlesearch import GoogleSearchIE
from .extractor.howcast import HowcastIE
from .extractor.hypem import HypemIE
from .extractor.ina import InaIE
from .extractor.infoq import InfoQIE
from .extractor.justintv import JustinTVIE
from .extractor.keek import KeekIE
from .extractor.liveleak import LiveLeakIE
from .extractor.metacafe import MetacafeIE
from .extractor.mixcloud import MixcloudIE
from .extractor.mtv import MTVIE
from .extractor.myspass import MySpassIE
from .extractor.myvideo import MyVideoIE
from .extractor.nba import NBAIE
from .extractor.statigram import StatigramIE
from .extractor.photobucket import PhotobucketIE
from .extractor.pornotube import PornotubeIE
from .extractor.rbmaradio import RBMARadioIE
from .extractor.redtube import RedTubeIE
from .extractor.soundcloud import SoundcloudIE, SoundcloudSetIE
from .extractor.spiegel import SpiegelIE
from .extractor.stanfordoc import StanfordOpenClassroomIE
from .extractor.steam import SteamIE
from .extractor.ted import TEDIE
from .extractor.tumblr import TumblrIE
from .extractor.ustream import UstreamIE
from .extractor.vbox7 import Vbox7IE
from .extractor.vimeo import VimeoIE
from .extractor.vine import VineIE
from .extractor.worldstarhiphop import WorldStarHipHopIE
from .extractor.xnxx import XNXXIE
from .extractor.xvideos import XVideosIE
from .extractor.yahoo import YahooIE, YahooSearchIE
from .extractor.youjizz import YouJizzIE
from .extractor.youku import YoukuIE
from .extractor.youporn import YouPornIE
from .extractor.youtube import YoutubeIE, YoutubePlaylistIE, YoutubeSearchIE, YoutubeUserIE, YoutubeChannelIE
from .extractor.zdf import ZDFIE
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+?)"',
webpage, u'video id')
self.report_extraction(video_id)
video_title = self._html_search_regex(r'<meta property="og:title" content="(.+?)"',
webpage, u'title')
thumbnail = self._html_search_regex(r'<meta property="og:image" content="(.+?)"',
webpage, u'thumbnail', fatal=False)
video_description = self._html_search_regex(r'<meta property="og:description" content="(.*?)"',
webpage, u'description', fatal=False)
data_url = 'http://teamcoco.com/cvp/2.0/%s.xml' % video_id
data = self._download_webpage(data_url, video_id, 'Downloading data webpage')
video_url = self._html_search_regex(r'<file type="high".*?>(.*?)</file>',
data, u'video URL')
return [{
'id': video_id,
'url': video_url,
'ext': 'mp4',
'title': video_title,
'thumbnail': thumbnail,
'description': video_description,
}]
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')
mrss_url = 'http://xhamster.com/movies/%s/.html' % video_id
webpage = self._download_webpage(mrss_url, video_id)
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>',
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)
if mobj:
video_upload_date = mobj.group('upload_date_Y')+mobj.group('upload_date_m')+mobj.group('upload_date_d')
else:
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>[^<]+)',
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
}]
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(),
VimeoIE(),
MyVideoIE(),
ComedyCentralIE(),
EscapistIE(),
CollegeHumorIE(),
XVideosIE(),
SoundcloudSetIE(),
SoundcloudIE(),
InfoQIE(),
MixcloudIE(),
StanfordOpenClassroomIE(),
MTVIE(),
YoukuIE(),
XNXXIE(),
YouJizzIE(),
PornotubeIE(),
YouPornIE(),
GooglePlusIE(),
ArteTvIE(),
NBAIE(),
WorldStarHipHopIE(),
JustinTVIE(),
FunnyOrDieIE(),
SteamIE(),
UstreamIE(),
RBMARadioIE(),
EightTracksIE(),
KeekIE(),
TEDIE(),
MySpassIE(),
SpiegelIE(),
LiveLeakIE(),
ARDIE(),
ZDFIE(),
TumblrIE(),
BandcampIE(),
RedTubeIE(),
InaIE(),
HowcastIE(),
VineIE(),
FlickrIE(),
TeamcocoIE(),
XHamsterIE(),
HypemIE(),
Vbox7IE(),
GametrailersIE(),
StatigramIE(),
GenericIE()
]
def get_info_extractor(ie_name):
"""Returns the info extractor class with the given ie_name"""
return globals()[ie_name+'IE']
|
