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

   1 from __future__ import unicode_literals
   2
   3 import re
   4 import json
   5
   6 from .common import InfoExtractor
   7 from ..compat import (
   8     compat_urlparse,
   9 )
  10
  11
  12 class ImdbIE(InfoExtractor):
  13     IE_NAME = 'imdb'
  14     IE_DESC = 'Internet Movie Database trailers'
  15     _VALID_URL = r'http://(?:www|m)\.imdb\.com/video/imdb/vi(?P<id>\d+)'
  16
  17     _TEST = {
  18         'url': 'http://www.imdb.com/video/imdb/vi2524815897',
  19         'info_dict': {
  20             'id': '2524815897',
  21             'ext': 'mp4',
  22             'title': 'Ice Age: Continental Drift Trailer (No. 2) - IMDb',
  23             'description': 'md5:9061c2219254e5d14e03c25c98e96a81',
  24         }
  25     }
  26
  27     def _real_extract(self, url):
  28         video_id = self._match_id(url)
  29         webpage = self._download_webpage('http://www.imdb.com/video/imdb/vi%s' % video_id, video_id)
  30         descr = self._html_search_regex(
  31             r'(?s)<span itemprop="description">(.*?)</span>',
  32             webpage, 'description', fatal=False)
  33         available_formats = re.findall(
  34             r'case \'(?P<f_id>.*?)\' :$\s+url = \'(?P<path>.*?)\'', webpage,
  35             flags=re.MULTILINE)
  36         formats = []
  37         for f_id, f_path in available_formats:
  38             f_path = f_path.strip()
  39             format_page = self._download_webpage(
  40                 compat_urlparse.urljoin(url, f_path),
  41                 'Downloading info for %s format' % f_id)
  42             json_data = self._search_regex(
  43                 r'<script[^>]+class="imdb-player-data"[^>]*?>(.*?)</script>',
  44                 format_page, 'json data', flags=re.DOTALL)
  45             info = json.loads(json_data)
  46             format_info = info['videoPlayerObject']['video']
  47             formats.append({
  48                 'format_id': f_id,
  49                 'url': format_info['url'],
  50             })
  51
  52         return {
  53             'id': video_id,
  54             'title': self._og_search_title(webpage),
  55             'formats': formats,
  56             'description': descr,
  57             'thumbnail': format_info['slate'],
  58         }
  59
  60
  61 class ImdbListIE(InfoExtractor):
  62     IE_NAME = 'imdb:list'
  63     IE_DESC = 'Internet Movie Database lists'
  64     _VALID_URL = r'http://www\.imdb\.com/list/(?P<id>[\da-zA-Z_-]{11})'
  65     _TEST = {
  66         'url': 'http://www.imdb.com/list/JFs9NWw6XI0',
  67         'info_dict': {
  68             'id': 'JFs9NWw6XI0',
  69             'title': 'March 23, 2012 Releases',
  70         },
  71         'playlist_count': 7,
  72     }
  73
  74     def _real_extract(self, url):
  75         list_id = self._match_id(url)
  76         webpage = self._download_webpage(url, list_id)
  77         entries = [
  78             self.url_result('http://www.imdb.com' + m, 'Imdb')
  79             for m in re.findall(r'href="(/video/imdb/vi[^"]+)"\s+data-type="playlist"', webpage)]
  80
  81         list_title = self._html_search_regex(
  82             r'<h1 class="header">(.*?)</h1>', webpage, 'list title')
  83
  84         return self.playlist_result(entries, list_id, list_title)