youtube_dl/extractor/einthusan.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import compat_urlparse
   6 from ..utils import (
   7     remove_start,
   8     sanitized_Request,
   9 )
  10
  11
  12 class EinthusanIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:www\.)?einthusan\.com/movies/watch.php\?([^#]*?)id=(?P<id>[0-9]+)'
  14     _TESTS = [
  15         {
  16             'url': 'http://www.einthusan.com/movies/watch.php?id=2447',
  17             'md5': 'd71379996ff5b7f217eca034c34e3461',
  18             'info_dict': {
  19                 'id': '2447',
  20                 'ext': 'mp4',
  21                 'title': 'Ek Villain',
  22                 'thumbnail': 're:^https?://.*\.jpg$',
  23                 'description': 'md5:9d29fc91a7abadd4591fb862fa560d93',
  24             }
  25         },
  26         {
  27             'url': 'http://www.einthusan.com/movies/watch.php?id=1671',
  28             'md5': 'b16a6fd3c67c06eb7c79c8a8615f4213',
  29             'info_dict': {
  30                 'id': '1671',
  31                 'ext': 'mp4',
  32                 'title': 'Soodhu Kavvuum',
  33                 'thumbnail': 're:^https?://.*\.jpg$',
  34                 'description': 'md5:b40f2bf7320b4f9414f3780817b2af8c',
  35             }
  36         },
  37     ]
  38
  39     def _real_extract(self, url):
  40         video_id = self._match_id(url)
  41
  42         request = sanitized_Request(url)
  43         request.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:43.0) Gecko/20100101 Firefox/43.0')
  44         webpage = self._download_webpage(request, video_id)
  45
  46         title = self._html_search_regex(
  47             r'<h1><a[^>]+class=["\']movie-title["\'][^>]*>(.+?)</a></h1>',
  48             webpage, 'title')
  49
  50         video_id = self._search_regex(
  51             r'data-movieid=["\'](\d+)', webpage, 'video id', default=video_id)
  52
  53         m3u8_url = self._download_webpage(
  54             'http://cdn.einthusan.com/geturl/%s/hd/London,Washington,Toronto,Dallas,San,Sydney/'
  55             % video_id, video_id, headers={'Referer': url})
  56         formats = self._extract_m3u8_formats(
  57             m3u8_url, video_id, ext='mp4', entry_protocol='m3u8_native')
  58
  59         description = self._html_search_meta('description', webpage)
  60         thumbnail = self._html_search_regex(
  61             r'''<a class="movie-cover-wrapper".*?><img src=["'](.*?)["'].*?/></a>''',
  62             webpage, "thumbnail url", fatal=False)
  63         if thumbnail is not None:
  64             thumbnail = compat_urlparse.urljoin(url, remove_start(thumbnail, '..'))
  65
  66         return {
  67             'id': video_id,
  68             'title': title,
  69             'formats': formats,
  70             'thumbnail': thumbnail,
  71             'description': description,
  72         }