Merge branch 'kuwo' of https://github.com/ping/youtube-dl into ping-kuwo
[youtube-dl] / youtube_dl / extractor / tnaflix.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from .common import InfoExtractor
6 from ..compat import compat_str
7 from ..utils import (
8     fix_xml_ampersands,
9     float_or_none,
10     int_or_none,
11     parse_duration,
12     str_to_int,
13     xpath_text,
14 )
15
16
17 class TNAFlixNetworkBaseIE(InfoExtractor):
18     # May be overridden in descendants if necessary
19     _CONFIG_REGEX = [
20         r'flashvars\.config\s*=\s*escape\("([^"]+)"',
21         r'<input[^>]+name="config\d?" value="([^"]+)"',
22     ]
23     _TITLE_REGEX = r'<input[^>]+name="title" value="([^"]+)"'
24     _DESCRIPTION_REGEX = r'<input[^>]+name="description" value="([^"]+)"'
25     _UPLOADER_REGEX = r'<input[^>]+name="username" value="([^"]+)"'
26     _VIEW_COUNT_REGEX = None
27     _COMMENT_COUNT_REGEX = None
28     _AVERAGE_RATING_REGEX = None
29     _CATEGORIES_REGEX = r'<li[^>]*>\s*<span[^>]+class="infoTitle"[^>]*>Categories:</span>\s*<span[^>]+class="listView"[^>]*>(.+?)</span>\s*</li>'
30
31     def _extract_thumbnails(self, flix_xml):
32
33         def get_child(elem, names):
34             for name in names:
35                 child = elem.find(name)
36                 if child is not None:
37                     return child
38
39         timeline = get_child(flix_xml, ['timeline', 'rolloverBarImage'])
40         if timeline is None:
41             return
42
43         pattern_el = get_child(timeline, ['imagePattern', 'pattern'])
44         if pattern_el is None or not pattern_el.text:
45             return
46
47         first_el = get_child(timeline, ['imageFirst', 'first'])
48         last_el = get_child(timeline, ['imageLast', 'last'])
49         if first_el is None or last_el is None:
50             return
51
52         first_text = first_el.text
53         last_text = last_el.text
54         if not first_text.isdigit() or not last_text.isdigit():
55             return
56
57         first = int(first_text)
58         last = int(last_text)
59         if first > last:
60             return
61
62         width = int_or_none(xpath_text(timeline, './imageWidth', 'thumbnail width'))
63         height = int_or_none(xpath_text(timeline, './imageHeight', 'thumbnail height'))
64
65         return [{
66             'url': self._proto_relative_url(pattern_el.text.replace('#', compat_str(i)), 'http:'),
67             'width': width,
68             'height': height,
69         } for i in range(first, last + 1)]
70
71     def _real_extract(self, url):
72         mobj = re.match(self._VALID_URL, url)
73         video_id = mobj.group('id')
74         display_id = mobj.group('display_id')
75
76         webpage = self._download_webpage(url, display_id)
77
78         cfg_url = self._proto_relative_url(self._html_search_regex(
79             self._CONFIG_REGEX, webpage, 'flashvars.config'), 'http:')
80
81         cfg_xml = self._download_xml(
82             cfg_url, display_id, 'Downloading metadata',
83             transform_source=fix_xml_ampersands)
84
85         formats = []
86
87         def extract_video_url(vl):
88             return re.sub('speed=\d+', 'speed=', vl.text)
89
90         video_link = cfg_xml.find('./videoLink')
91         if video_link is not None:
92             formats.append({
93                 'url': extract_video_url(video_link),
94                 'ext': xpath_text(cfg_xml, './videoConfig/type', 'type', default='flv'),
95             })
96
97         for item in cfg_xml.findall('./quality/item'):
98             video_link = item.find('./videoLink')
99             if video_link is None:
100                 continue
101             res = item.find('res')
102             format_id = None if res is None else res.text
103             height = int_or_none(self._search_regex(
104                 r'^(\d+)[pP]', format_id, 'height', default=None))
105             formats.append({
106                 'url': self._proto_relative_url(extract_video_url(video_link), 'http:'),
107                 'format_id': format_id,
108                 'height': height,
109             })
110
111         self._sort_formats(formats)
112
113         thumbnail = self._proto_relative_url(
114             xpath_text(cfg_xml, './startThumb', 'thumbnail'), 'http:')
115         thumbnails = self._extract_thumbnails(cfg_xml)
116
117         title = self._html_search_regex(
118             self._TITLE_REGEX, webpage, 'title') if self._TITLE_REGEX else self._og_search_title(webpage)
119
120         age_limit = self._rta_search(webpage)
121
122         duration = parse_duration(self._html_search_meta(
123             'duration', webpage, 'duration', default=None))
124
125         def extract_field(pattern, name):
126             return self._html_search_regex(pattern, webpage, name, default=None) if pattern else None
127
128         description = extract_field(self._DESCRIPTION_REGEX, 'description')
129         uploader = extract_field(self._UPLOADER_REGEX, 'uploader')
130         view_count = str_to_int(extract_field(self._VIEW_COUNT_REGEX, 'view count'))
131         comment_count = str_to_int(extract_field(self._COMMENT_COUNT_REGEX, 'comment count'))
132         average_rating = float_or_none(extract_field(self._AVERAGE_RATING_REGEX, 'average rating'))
133
134         categories_str = extract_field(self._CATEGORIES_REGEX, 'categories')
135         categories = categories_str.split(', ') if categories_str is not None else []
136
137         return {
138             'id': video_id,
139             'display_id': display_id,
140             'title': title,
141             'description': description,
142             'thumbnail': thumbnail,
143             'thumbnails': thumbnails,
144             'duration': duration,
145             'age_limit': age_limit,
146             'uploader': uploader,
147             'view_count': view_count,
148             'comment_count': comment_count,
149             'average_rating': average_rating,
150             'categories': categories,
151             'formats': formats,
152         }
153
154
155 class TNAFlixIE(TNAFlixNetworkBaseIE):
156     _VALID_URL = r'https?://(?:www\.)?tnaflix\.com/[^/]+/(?P<display_id>[^/]+)/video(?P<id>\d+)'
157
158     _TITLE_REGEX = r'<title>(.+?) - TNAFlix Porn Videos</title>'
159     _DESCRIPTION_REGEX = r'<h3 itemprop="description">([^<]+)</h3>'
160     _UPLOADER_REGEX = r'(?s)<span[^>]+class="infoTitle"[^>]*>Uploaded By:</span>(.+?)<div'
161
162     _TESTS = [{
163         # anonymous uploader, no categories
164         'url': 'http://www.tnaflix.com/porn-stars/Carmella-Decesare-striptease/video553878',
165         'md5': 'ecf3498417d09216374fc5907f9c6ec0',
166         'info_dict': {
167             'id': '553878',
168             'display_id': 'Carmella-Decesare-striptease',
169             'ext': 'mp4',
170             'title': 'Carmella Decesare - striptease',
171             'thumbnail': 're:https?://.*\.jpg$',
172             'duration': 91,
173             'age_limit': 18,
174             'uploader': 'Anonymous',
175             'categories': [],
176         }
177     }, {
178         # non-anonymous uploader, categories
179         'url': 'https://www.tnaflix.com/teen-porn/Educational-xxx-video/video6538',
180         'md5': '0f5d4d490dbfd117b8607054248a07c0',
181         'info_dict': {
182             'id': '6538',
183             'display_id': 'Educational-xxx-video',
184             'ext': 'mp4',
185             'title': 'Educational xxx video',
186             'description': 'md5:b4fab8f88a8621c8fabd361a173fe5b8',
187             'thumbnail': 're:https?://.*\.jpg$',
188             'duration': 164,
189             'age_limit': 18,
190             'uploader': 'bobwhite39',
191             'categories': ['Amateur Porn', 'Squirting Videos', 'Teen Girls 18+'],
192         }
193     }, {
194         'url': 'https://www.tnaflix.com/amateur-porn/bunzHD-Ms.Donk/video358632',
195         'only_matching': True,
196     }]
197
198
199 class EMPFlixIE(TNAFlixNetworkBaseIE):
200     _VALID_URL = r'https?://(?:www\.)?empflix\.com/videos/(?P<display_id>.+?)-(?P<id>[0-9]+)\.html'
201
202     _UPLOADER_REGEX = r'<span[^>]+class="infoTitle"[^>]*>Uploaded By:</span>(.+?)</li>'
203
204     _TESTS = [{
205         'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html',
206         'md5': 'b1bc15b6412d33902d6e5952035fcabc',
207         'info_dict': {
208             'id': '33051',
209             'display_id': 'Amateur-Finger-Fuck',
210             'ext': 'mp4',
211             'title': 'Amateur Finger Fuck',
212             'description': 'Amateur solo finger fucking.',
213             'thumbnail': 're:https?://.*\.jpg$',
214             'duration': 83,
215             'age_limit': 18,
216             'uploader': 'cwbike',
217             'categories': ['Amateur', 'Anal', 'Fisting', 'Home made', 'Solo'],
218         }
219     }, {
220         'url': 'http://www.empflix.com/videos/[AROMA][ARMD-718]-Aoi-Yoshino-Sawa-25826.html',
221         'only_matching': True,
222     }]
223
224
225 class MovieFapIE(TNAFlixNetworkBaseIE):
226     _VALID_URL = r'https?://(?:www\.)?moviefap\.com/videos/(?P<id>[0-9a-f]+)/(?P<display_id>[^/]+)\.html'
227
228     _VIEW_COUNT_REGEX = r'<br>Views\s*<strong>([\d,.]+)</strong>'
229     _COMMENT_COUNT_REGEX = r'<span[^>]+id="comCount"[^>]*>([\d,.]+)</span>'
230     _AVERAGE_RATING_REGEX = r'Current Rating\s*<br>\s*<strong>([\d.]+)</strong>'
231     _CATEGORIES_REGEX = r'(?s)<div[^>]+id="vid_info"[^>]*>\s*<div[^>]*>.+?</div>(.*?)<br>'
232
233     _TESTS = [{
234         # normal, multi-format video
235         'url': 'http://www.moviefap.com/videos/be9867c9416c19f54a4a/experienced-milf-amazing-handjob.html',
236         'md5': '26624b4e2523051b550067d547615906',
237         'info_dict': {
238             'id': 'be9867c9416c19f54a4a',
239             'display_id': 'experienced-milf-amazing-handjob',
240             'ext': 'mp4',
241             'title': 'Experienced MILF Amazing Handjob',
242             'description': 'Experienced MILF giving an Amazing Handjob',
243             'thumbnail': 're:https?://.*\.jpg$',
244             'age_limit': 18,
245             'uploader': 'darvinfred06',
246             'view_count': int,
247             'comment_count': int,
248             'average_rating': float,
249             'categories': ['Amateur', 'Masturbation', 'Mature', 'Flashing'],
250         }
251     }, {
252         # quirky single-format case where the extension is given as fid, but the video is really an flv
253         'url': 'http://www.moviefap.com/videos/e5da0d3edce5404418f5/jeune-couple-russe.html',
254         'md5': 'fa56683e291fc80635907168a743c9ad',
255         'info_dict': {
256             'id': 'e5da0d3edce5404418f5',
257             'display_id': 'jeune-couple-russe',
258             'ext': 'flv',
259             'title': 'Jeune Couple Russe',
260             'description': 'Amateur',
261             'thumbnail': 're:https?://.*\.jpg$',
262             'age_limit': 18,
263             'uploader': 'whiskeyjar',
264             'view_count': int,
265             'comment_count': int,
266             'average_rating': float,
267             'categories': ['Amateur', 'Teen'],
268         }
269     }]