Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/einthusan.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7
   8
   9 class EinthusanIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www\.)?einthusan\.com/movies/watch.php\?([^#]*?)id=(?P<id>[0-9]+)'
  11     _TESTS = [
  12         {
  13             'url': 'http://www.einthusan.com/movies/watch.php?id=2447',
  14             'md5': 'af244f4458cd667205e513d75da5b8b1',
  15             'info_dict': {
  16                 'id': '2447',
  17                 'ext': 'mp4',
  18                 'title': 'Ek Villain',
  19                 'thumbnail': 're:^https?://.*\.jpg$',
  20                 'description': 'md5:9d29fc91a7abadd4591fb862fa560d93',
  21             }
  22         },
  23         {
  24             'url': 'http://www.einthusan.com/movies/watch.php?id=1671',
  25             'md5': 'ef63c7a803e22315880ed182c10d1c5c',
  26             'info_dict': {
  27                 'id': '1671',
  28                 'ext': 'mp4',
  29                 'title': 'Soodhu Kavvuum',
  30                 'thumbnail': 're:^https?://.*\.jpg$',
  31                 'description': 'md5:05d8a0c0281a4240d86d76e14f2f4d51',
  32             }
  33         },
  34     ]
  35
  36     def _real_extract(self, url):
  37         mobj = re.match(self._VALID_URL, url)
  38         video_id = mobj.group('id')
  39         webpage = self._download_webpage(url, video_id)
  40
  41         video_title = self._html_search_regex(
  42             r'<h1><a class="movie-title".*?>(.*?)</a></h1>', webpage, 'title')
  43
  44         video_url = self._html_search_regex(
  45             r'''(?s)jwplayer\("mediaplayer"\)\.setup\({.*?'file': '([^']+)'.*?}\);''',
  46             webpage, 'video url')
  47
  48         description = self._html_search_meta('description', webpage)
  49         thumbnail = self._html_search_regex(
  50             r'''<a class="movie-cover-wrapper".*?><img src=["'](.*?)["'].*?/></a>''',
  51             webpage, "thumbnail url", fatal=False)
  52         if thumbnail is not None:
  53             thumbnail = thumbnail.replace('..', 'http://www.einthusan.com')
  54
  55         return {
  56             'id': video_id,
  57             'title': video_title,
  58             'url': video_url,
  59             'thumbnail': thumbnail,
  60             'description': description,
  61         }