_ Git - youtube-dl/blob - youtube_dl/extractor/pornovoisines.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5 import datetime
   6 import random
   7
   8 from ..compat import compat_urllib_parse
   9 from .common import InfoExtractor
  10
  11 class PornoVoisinesIE(InfoExtractor):
  12     _VALID_URL = r'^((?:http://)?(?:www\.)?pornovoisines.com)/showvideo/(\d+)/([^/]+)'
  13
  14     VIDEO_URL_TEMPLATE = 'http://stream%d.pornovoisines.com' \
  15         '/static/media/video/transcoded/%s-640x360-1000-trscded.mp4'
  16
  17     SERVER_NUMBERS = (1, 2)
  18
  19     _TEST = {
  20         'url': 'http://www.pornovoisines.com/showvideo/1285/recherche-appartement/',
  21         'md5': '5ac670803bc12e9e7f9f662ce64cf1d1',
  22         'info_dict': {
  23             'id': '1285',
  24             'display_id': 'recherche-appartement',
  25             'ext': 'mp4',
  26             'title': "Recherche appartement",
  27             'upload_date': '20140925',
  28             'view_count': int,
  29             'duration': 120,
  30             'categories': ["Débutante", "Scénario", "Sodomie"],
  31             'description': 're:^Pour la .+ original...$',
  32             'thumbnail': 're:^http://',
  33             'uploader': "JMTV",
  34             'average_rating': float,
  35             'comment_count': int,
  36             'age_limit': 18,
  37         }
  38     }
  39
  40     @classmethod
  41     def build_video_url(cls, id):
  42         server_nr = random.choice(cls.SERVER_NUMBERS)
  43         return cls.VIDEO_URL_TEMPLATE % (server_nr, id)
  44
  45     @staticmethod
  46     def parse_upload_date(str):
  47         return datetime.datetime.strptime(str, "%d-%m-%Y").strftime("%Y%m%d")
  48
  49     @staticmethod
  50     def parse_categories(str):
  51         return map(lambda s: s.strip(), str.split(','))
  52
  53     def _real_extract(self, url):
  54         mobj = re.match(self._VALID_URL, url)
  55         url_prefix = mobj.group(1)
  56         id = mobj.group(2)
  57         display_id = mobj.group(3)
  58
  59         webpage = self._download_webpage(url, id)
  60
  61         title = self._html_search_regex(r'<h1>(.+?)</h1>', webpage, 'title',
  62             flags=re.DOTALL)
  63         url = self.build_video_url(id)
  64         upload_date = self.parse_upload_date(
  65             self._search_regex(r'Publié le (\d\d-\d\d-\d{4})', webpage,
  66             'upload date'))
  67         view_count = int(self._search_regex(r'(\d+) vues', webpage, 'view count'))
  68         duration = int(self._search_regex('Durée (\d+)', webpage, 'duration'))
  69         categories = self.parse_categories(self._html_search_regex(
  70             r'<li class="categorie">(.+?)</li>', webpage, "categories",
  71             flags=re.DOTALL))
  72         description = self._html_search_regex(
  73             r'<article id="descriptif">(.+?)</article>', webpage, "description",
  74             flags=re.DOTALL)
  75         thumbnail = url_prefix + self._html_search_regex(re.compile(
  76             '<div id="mediaspace' + id + '">.*?<img src="(.+?)"', re.DOTALL),
  77             webpage, "thumbnail")
  78         uploader = re.sub(r' *\| *$', '',
  79             self._html_search_regex(r'<li class="auteur">(.+?)</li>', webpage,
  80             "uploader", flags=re.DOTALL))
  81         average_rating = float(self._search_regex(r'Note : (\d+,\d+)',
  82             webpage, "average rating").replace(',', '.'))
  83         comment_count = int(self._search_regex(r'\((\d+)\)', webpage,
  84             "comment count"))
  85
  86         return {
  87             'id': id,
  88             'display_id': display_id,
  89             'url': url,
  90             'title': title,
  91             'upload_date': upload_date,
  92             'view_count': view_count,
  93             'duration': duration,
  94             'categories': categories,
  95             'description': description,
  96             'thumbnail': thumbnail,
  97             'uploader': uploader,
  98             'average_rating': average_rating,
  99             'comment_count': comment_count,
 100             'age_limit': 18,
 101         }