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
282
283
284
285
286
287
288
289
290
291
292
293
|
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
fix_xml_ampersands,
float_or_none,
int_or_none,
parse_duration,
str_to_int,
xpath_text,
)
class TNAFlixNetworkBaseIE(InfoExtractor):
# May be overridden in descendants if necessary
_CONFIG_REGEX = [
r'flashvars\.config\s*=\s*escape\("([^"]+)"',
r'<input[^>]+name="config\d?" value="([^"]+)"',
]
_TITLE_REGEX = r'<input[^>]+name="title" value="([^"]+)"'
_DESCRIPTION_REGEX = r'<input[^>]+name="description" value="([^"]+)"'
_UPLOADER_REGEX = r'<input[^>]+name="username" value="([^"]+)"'
_VIEW_COUNT_REGEX = None
_COMMENT_COUNT_REGEX = None
_AVERAGE_RATING_REGEX = None
_CATEGORIES_REGEX = r'<li[^>]*>\s*<span[^>]+class="infoTitle"[^>]*>Categories:</span>\s*<span[^>]+class="listView"[^>]*>(.+?)</span>\s*</li>'
def _extract_thumbnails(self, flix_xml):
def get_child(elem, names):
for name in names:
child = elem.find(name)
if child is not None:
return child
timeline = get_child(flix_xml, ['timeline', 'rolloverBarImage'])
if timeline is None:
return
pattern_el = get_child(timeline, ['imagePattern', 'pattern'])
if pattern_el is None or not pattern_el.text:
return
first_el = get_child(timeline, ['imageFirst', 'first'])
last_el = get_child(timeline, ['imageLast', 'last'])
if first_el is None or last_el is None:
return
first_text = first_el.text
last_text = last_el.text
if not first_text.isdigit() or not last_text.isdigit():
return
first = int(first_text)
last = int(last_text)
if first > last:
return
width = int_or_none(xpath_text(timeline, './imageWidth', 'thumbnail width'))
height = int_or_none(xpath_text(timeline, './imageHeight', 'thumbnail height'))
return [{
'url': self._proto_relative_url(pattern_el.text.replace('#', compat_str(i)), 'http:'),
'width': width,
'height': height,
} for i in range(first, last + 1)]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
display_id = mobj.group('display_id') if 'display_id' in mobj.groupdict() else video_id
webpage = self._download_webpage(url, display_id)
cfg_url = self._proto_relative_url(self._html_search_regex(
self._CONFIG_REGEX, webpage, 'flashvars.config'), 'http:')
cfg_xml = self._download_xml(
cfg_url, display_id, 'Downloading metadata',
transform_source=fix_xml_ampersands)
formats = []
def extract_video_url(vl):
return re.sub('speed=\d+', 'speed=', vl.text)
video_link = cfg_xml.find('./videoLink')
if video_link is not None:
formats.append({
'url': extract_video_url(video_link),
'ext': xpath_text(cfg_xml, './videoConfig/type', 'type', default='flv'),
})
for item in cfg_xml.findall('./quality/item'):
video_link = item.find('./videoLink')
if video_link is None:
continue
res = item.find('res')
format_id = None if res is None else res.text
height = int_or_none(self._search_regex(
r'^(\d+)[pP]', format_id, 'height', default=None))
formats.append({
'url': self._proto_relative_url(extract_video_url(video_link), 'http:'),
'format_id': format_id,
'height': height,
})
self._sort_formats(formats)
thumbnail = self._proto_relative_url(
xpath_text(cfg_xml, './startThumb', 'thumbnail'), 'http:')
thumbnails = self._extract_thumbnails(cfg_xml)
title = self._html_search_regex(
self._TITLE_REGEX, webpage, 'title') if self._TITLE_REGEX else self._og_search_title(webpage)
age_limit = self._rta_search(webpage)
duration = parse_duration(self._html_search_meta(
'duration', webpage, 'duration', default=None))
def extract_field(pattern, name):
return self._html_search_regex(pattern, webpage, name, default=None) if pattern else None
description = extract_field(self._DESCRIPTION_REGEX, 'description')
uploader = extract_field(self._UPLOADER_REGEX, 'uploader')
view_count = str_to_int(extract_field(self._VIEW_COUNT_REGEX, 'view count'))
comment_count = str_to_int(extract_field(self._COMMENT_COUNT_REGEX, 'comment count'))
average_rating = float_or_none(extract_field(self._AVERAGE_RATING_REGEX, 'average rating'))
categories_str = extract_field(self._CATEGORIES_REGEX, 'categories')
categories = categories_str.split(', ') if categories_str is not None else []
return {
'id': video_id,
'display_id': display_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'thumbnails': thumbnails,
'duration': duration,
'age_limit': age_limit,
'uploader': uploader,
'view_count': view_count,
'comment_count': comment_count,
'average_rating': average_rating,
'categories': categories,
'formats': formats,
}
class TNAFlixNetworkEmbedIE(TNAFlixNetworkBaseIE):
_VALID_URL = r'https?://player\.(?:tna|emp)flix\.com/video/(?P<id>\d+)'
_TITLE_REGEX = r'<title>([^<]+)</title>'
_TESTS = [{
'url': 'https://player.tnaflix.com/video/6538',
'info_dict': {
'id': '6538',
'display_id': '6538',
'ext': 'mp4',
'title': 'Educational xxx video',
'thumbnail': 're:https?://.*\.jpg$',
'age_limit': 18,
},
'params': {
'skip_download': True,
},
}, {
'url': 'https://player.empflix.com/video/33051',
'only_matching': True,
}]
class TNAFlixIE(TNAFlixNetworkBaseIE):
_VALID_URL = r'https?://(?:www\.)?tnaflix\.com/[^/]+/(?P<display_id>[^/]+)/video(?P<id>\d+)'
_TITLE_REGEX = r'<title>(.+?) - TNAFlix Porn Videos</title>'
_DESCRIPTION_REGEX = r'<h3 itemprop="description">([^<]+)</h3>'
_UPLOADER_REGEX = r'(?s)<span[^>]+class="infoTitle"[^>]*>Uploaded By:</span>(.+?)<div'
_TESTS = [{
# anonymous uploader, no categories
'url': 'http://www.tnaflix.com/porn-stars/Carmella-Decesare-striptease/video553878',
'md5': 'ecf3498417d09216374fc5907f9c6ec0',
'info_dict': {
'id': '553878',
'display_id': 'Carmella-Decesare-striptease',
'ext': 'mp4',
'title': 'Carmella Decesare - striptease',
'thumbnail': 're:https?://.*\.jpg$',
'duration': 91,
'age_limit': 18,
'uploader': 'Anonymous',
'categories': [],
}
}, {
# non-anonymous uploader, categories
'url': 'https://www.tnaflix.com/teen-porn/Educational-xxx-video/video6538',
'md5': '0f5d4d490dbfd117b8607054248a07c0',
'info_dict': {
'id': '6538',
'display_id': 'Educational-xxx-video',
'ext': 'mp4',
'title': 'Educational xxx video',
'description': 'md5:b4fab8f88a8621c8fabd361a173fe5b8',
'thumbnail': 're:https?://.*\.jpg$',
'duration': 164,
'age_limit': 18,
'uploader': 'bobwhite39',
'categories': ['Amateur Porn', 'Squirting Videos', 'Teen Girls 18+'],
}
}, {
'url': 'https://www.tnaflix.com/amateur-porn/bunzHD-Ms.Donk/video358632',
'only_matching': True,
}]
class EMPFlixIE(TNAFlixNetworkBaseIE):
_VALID_URL = r'https?://(?:www\.)?empflix\.com/videos/(?P<display_id>.+?)-(?P<id>[0-9]+)\.html'
_UPLOADER_REGEX = r'<span[^>]+class="infoTitle"[^>]*>Uploaded By:</span>(.+?)</li>'
_TESTS = [{
'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html',
'md5': 'b1bc15b6412d33902d6e5952035fcabc',
'info_dict': {
'id': '33051',
'display_id': 'Amateur-Finger-Fuck',
'ext': 'mp4',
'title': 'Amateur Finger Fuck',
'description': 'Amateur solo finger fucking.',
'thumbnail': 're:https?://.*\.jpg$',
'duration': 83,
'age_limit': 18,
'uploader': 'cwbike',
'categories': ['Amateur', 'Anal', 'Fisting', 'Home made', 'Solo'],
}
}, {
'url': 'http://www.empflix.com/videos/[AROMA][ARMD-718]-Aoi-Yoshino-Sawa-25826.html',
'only_matching': True,
}]
class MovieFapIE(TNAFlixNetworkBaseIE):
_VALID_URL = r'https?://(?:www\.)?moviefap\.com/videos/(?P<id>[0-9a-f]+)/(?P<display_id>[^/]+)\.html'
_VIEW_COUNT_REGEX = r'<br>Views\s*<strong>([\d,.]+)</strong>'
_COMMENT_COUNT_REGEX = r'<span[^>]+id="comCount"[^>]*>([\d,.]+)</span>'
_AVERAGE_RATING_REGEX = r'Current Rating\s*<br>\s*<strong>([\d.]+)</strong>'
_CATEGORIES_REGEX = r'(?s)<div[^>]+id="vid_info"[^>]*>\s*<div[^>]*>.+?</div>(.*?)<br>'
_TESTS = [{
# normal, multi-format video
'url': 'http://www.moviefap.com/videos/be9867c9416c19f54a4a/experienced-milf-amazing-handjob.html',
'md5': '26624b4e2523051b550067d547615906',
'info_dict': {
'id': 'be9867c9416c19f54a4a',
'display_id': 'experienced-milf-amazing-handjob',
'ext': 'mp4',
'title': 'Experienced MILF Amazing Handjob',
'description': 'Experienced MILF giving an Amazing Handjob',
'thumbnail': 're:https?://.*\.jpg$',
'age_limit': 18,
'uploader': 'darvinfred06',
'view_count': int,
'comment_count': int,
'average_rating': float,
'categories': ['Amateur', 'Masturbation', 'Mature', 'Flashing'],
}
}, {
# quirky single-format case where the extension is given as fid, but the video is really an flv
'url': 'http://www.moviefap.com/videos/e5da0d3edce5404418f5/jeune-couple-russe.html',
'md5': 'fa56683e291fc80635907168a743c9ad',
'info_dict': {
'id': 'e5da0d3edce5404418f5',
'display_id': 'jeune-couple-russe',
'ext': 'flv',
'title': 'Jeune Couple Russe',
'description': 'Amateur',
'thumbnail': 're:https?://.*\.jpg$',
'age_limit': 18,
'uploader': 'whiskeyjar',
'view_count': int,
'comment_count': int,
'average_rating': float,
'categories': ['Amateur', 'Teen'],
}
}]
|
