]>
Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/tnaflix.py
   1 from __future__ 
import unicode_literals
 
   5 from .common 
import InfoExtractor
 
   6 from ..compat 
import compat_str
 
  17 class TNAFlixNetworkBaseIE(InfoExtractor
): 
  18     # May be overridden in descendants if necessary 
  20         r
'flashvars\.config\s*=\s*escape\("([^"]+)"', 
  21         r
'<input[^>]+name="config\d?" value="([^"]+)"', 
  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>' 
  31     def _extract_thumbnails(self
, flix_xml
): 
  33         def get_child(elem
, names
): 
  35                 child 
= elem
.find(name
) 
  39         timeline 
= get_child(flix_xml
, ['timeline', 'rolloverBarImage']) 
  43         pattern_el 
= get_child(timeline
, ['imagePattern', 'pattern']) 
  44         if pattern_el 
is None or not pattern_el
.text
: 
  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: 
  52         first_text 
= first_el
.text
 
  53         last_text 
= last_el
.text
 
  54         if not first_text
.isdigit() or not last_text
.isdigit(): 
  57         first 
= int(first_text
) 
  62         width 
= int_or_none(xpath_text(timeline
, './imageWidth', 'thumbnail width')) 
  63         height 
= int_or_none(xpath_text(timeline
, './imageHeight', 'thumbnail height')) 
  66             'url': self
._proto
_relative
_url
(pattern_el
.text
.replace('#', compat_str(i
)), 'http:'), 
  69         } for i 
in range(first
, last 
+ 1)] 
  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') 
  76         webpage 
= self
._download
_webpage
(url
, display_id
) 
  78         cfg_url 
= self
._proto
_relative
_url
(self
._html
_search
_regex
( 
  79             self
._CONFIG
_REGEX
, webpage
, 'flashvars.config'), 'http:') 
  81         cfg_xml 
= self
._download
_xml
( 
  82             cfg_url
, display_id
, 'Downloading metadata', 
  83             transform_source
=fix_xml_ampersands
) 
  87         def extract_video_url(vl
): 
  88             return re
.sub('speed=\d+', 'speed=', vl
.text
) 
  90         video_link 
= cfg_xml
.find('./videoLink') 
  91         if video_link 
is not None: 
  93                 'url': extract_video_url(video_link
), 
  94                 'ext': xpath_text(cfg_xml
, './videoConfig/type', 'type', default
='flv'), 
  97         for item 
in cfg_xml
.findall('./quality/item'): 
  98             video_link 
= item
.find('./videoLink') 
  99             if video_link 
is None: 
 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)) 
 106                 'url': self
._proto
_relative
_url
(extract_video_url(video_link
), 'http:'), 
 107                 'format_id': format_id
, 
 111         self
._sort
_formats
(formats
) 
 113         thumbnail 
= self
._proto
_relative
_url
( 
 114             xpath_text(cfg_xml
, './startThumb', 'thumbnail'), 'http:') 
 115         thumbnails 
= self
._extract
_thumbnails
(cfg_xml
) 
 117         title 
= self
._html
_search
_regex
( 
 118             self
._TITLE
_REGEX
, webpage
, 'title') if self
._TITLE
_REGEX 
else self
._og
_search
_title
(webpage
) 
 120         age_limit 
= self
._rta
_search
(webpage
) 
 122         duration 
= parse_duration(self
._html
_search
_meta
( 
 123             'duration', webpage
, 'duration', default
=None)) 
 125         def extract_field(pattern
, name
): 
 126             return self
._html
_search
_regex
(pattern
, webpage
, name
, default
=None) if pattern 
else None 
 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')) 
 134         categories_str 
= extract_field(self
._CATEGORIES
_REGEX
, 'categories') 
 135         categories 
= categories_str
.split(', ') if categories_str 
is not None else [] 
 139             'display_id': display_id
, 
 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
, 
 155 class TNAFlixIE(TNAFlixNetworkBaseIE
): 
 156     _VALID_URL 
= r
'https?://(?:www\.)?tnaflix\.com/[^/]+/(?P<display_id>[^/]+)/video(?P<id>\d+)' 
 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' 
 163         # anonymous uploader, no categories 
 164         'url': 'http://www.tnaflix.com/porn-stars/Carmella-Decesare-striptease/video553878', 
 165         'md5': 'ecf3498417d09216374fc5907f9c6ec0', 
 168             'display_id': 'Carmella-Decesare-striptease', 
 170             'title': 'Carmella Decesare - striptease', 
 171             'thumbnail': 're:https?://.*\.jpg$', 
 174             'uploader': 'Anonymous', 
 178         # non-anonymous uploader, categories 
 179         'url': 'https://www.tnaflix.com/teen-porn/Educational-xxx-video/video6538', 
 180         'md5': '0f5d4d490dbfd117b8607054248a07c0', 
 183             'display_id': 'Educational-xxx-video', 
 185             'title': 'Educational xxx video', 
 186             'description': 'md5:b4fab8f88a8621c8fabd361a173fe5b8', 
 187             'thumbnail': 're:https?://.*\.jpg$', 
 190             'uploader': 'bobwhite39', 
 191             'categories': ['Amateur Porn', 'Squirting Videos', 'Teen Girls 18+'], 
 194         'url': 'https://www.tnaflix.com/amateur-porn/bunzHD-Ms.Donk/video358632', 
 195         'only_matching': True, 
 199 class EMPFlixIE(TNAFlixNetworkBaseIE
): 
 200     _VALID_URL 
= r
'https?://(?:www\.)?empflix\.com/videos/(?P<display_id>.+?)-(?P<id>[0-9]+)\.html' 
 202     _UPLOADER_REGEX 
= r
'<span[^>]+class="infoTitle"[^>]*>Uploaded By:</span>(.+?)</li>' 
 205         'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html', 
 206         'md5': 'b1bc15b6412d33902d6e5952035fcabc', 
 209             'display_id': 'Amateur-Finger-Fuck', 
 211             'title': 'Amateur Finger Fuck', 
 212             'description': 'Amateur solo finger fucking.', 
 213             'thumbnail': 're:https?://.*\.jpg$', 
 216             'uploader': 'cwbike', 
 217             'categories': ['Amateur', 'Anal', 'Fisting', 'Home made', 'Solo'], 
 220         'url': 'http://www.empflix.com/videos/[AROMA][ARMD-718]-Aoi-Yoshino-Sawa-25826.html', 
 221         'only_matching': True, 
 225 class MovieFapIE(TNAFlixNetworkBaseIE
): 
 226     _VALID_URL 
= r
'https?://(?:www\.)?moviefap\.com/videos/(?P<id>[0-9a-f]+)/(?P<display_id>[^/]+)\.html' 
 228     _VIEW_COUNT_REGEX 
= r
'<br>Views\s*<strong>([\d,.]+)</strong>' 
 229     _COMMENT_COUNT_REGEX 
= r
'<span[^>]+id="comCount"[^>]*>([\d,.]+)</span>' 
 230     _AVERAGE_RATING_REGEX 
= r
'Current Rating\s*<br>\s*<strong>([\d.]+)</strong>' 
 231     _CATEGORIES_REGEX 
= r
'(?s)<div[^>]+id="vid_info"[^>]*>\s*<div[^>]*>.+?</div>(.*?)<br>' 
 234         # normal, multi-format video 
 235         'url': 'http://www.moviefap.com/videos/be9867c9416c19f54a4a/experienced-milf-amazing-handjob.html', 
 236         'md5': '26624b4e2523051b550067d547615906', 
 238             'id': 'be9867c9416c19f54a4a', 
 239             'display_id': 'experienced-milf-amazing-handjob', 
 241             'title': 'Experienced MILF Amazing Handjob', 
 242             'description': 'Experienced MILF giving an Amazing Handjob', 
 243             'thumbnail': 're:https?://.*\.jpg$', 
 245             'uploader': 'darvinfred06', 
 247             'comment_count': int, 
 248             'average_rating': float, 
 249             'categories': ['Amateur', 'Masturbation', 'Mature', 'Flashing'], 
 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', 
 256             'id': 'e5da0d3edce5404418f5', 
 257             'display_id': 'jeune-couple-russe', 
 259             'title': 'Jeune Couple Russe', 
 260             'description': 'Amateur', 
 261             'thumbnail': 're:https?://.*\.jpg$', 
 263             'uploader': 'whiskeyjar', 
 265             'comment_count': int, 
 266             'average_rating': float, 
 267             'categories': ['Amateur', 'Teen'],