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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     mimetype2ext,
   8     qualities,
   9     remove_end,
  10 )
  11
  12
  13 class ImdbIE(InfoExtractor):
  14     IE_NAME = 'imdb'
  15     IE_DESC = 'Internet Movie Database trailers'
  16     _VALID_URL = r'https?://(?:www|m)\.imdb\.com/(?:video/[^/]+/|title/tt\d+.*?#lb-|videoplayer/)vi(?P<id>\d+)'
  17
  18     _TESTS = [{
  19         'url': 'http://www.imdb.com/video/imdb/vi2524815897',
  20         'info_dict': {
  21             'id': '2524815897',
  22             'ext': 'mp4',
  23             'title': 'Ice Age: Continental Drift Trailer (No. 2)',
  24             'description': 'md5:9061c2219254e5d14e03c25c98e96a81',
  25         }
  26     }, {
  27         'url': 'http://www.imdb.com/video/_/vi2524815897',
  28         'only_matching': True,
  29     }, {
  30         'url': 'http://www.imdb.com/title/tt1667889/?ref_=ext_shr_eml_vi#lb-vi2524815897',
  31         'only_matching': True,
  32     }, {
  33         'url': 'http://www.imdb.com/title/tt1667889/#lb-vi2524815897',
  34         'only_matching': True,
  35     }, {
  36         'url': 'http://www.imdb.com/videoplayer/vi1562949145',
  37         'only_matching': True,
  38     }]
  39
  40     def _real_extract(self, url):
  41         video_id = self._match_id(url)
  42         webpage = self._download_webpage('http://www.imdb.com/video/imdb/vi%s' % video_id, video_id)
  43         descr = self._html_search_regex(
  44             r'(?s)<span itemprop="description">(.*?)</span>',
  45             webpage, 'description', fatal=False)
  46         player_url = 'http://www.imdb.com/video/imdb/vi%s/imdb/single' % video_id
  47         player_page = self._download_webpage(
  48             player_url, video_id, 'Downloading player page')
  49         # the player page contains the info for the default format, we have to
  50         # fetch other pages for the rest of the formats
  51         extra_formats = re.findall(r'href="(?P<url>%s.*?)".*?>(?P<name>.*?)<' % re.escape(player_url), player_page)
  52         format_pages = [
  53             self._download_webpage(
  54                 f_url, video_id, 'Downloading info for %s format' % f_name)
  55             for f_url, f_name in extra_formats]
  56         format_pages.append(player_page)
  57
  58         quality = qualities(('SD', '480p', '720p', '1080p'))
  59         formats = []
  60         for format_page in format_pages:
  61             json_data = self._search_regex(
  62                 r'<script[^>]+class="imdb-player-data"[^>]*?>(.*?)</script>',
  63                 format_page, 'json data', flags=re.DOTALL)
  64             info = self._parse_json(json_data, video_id, fatal=False)
  65             if not info:
  66                 continue
  67             format_info = info.get('videoPlayerObject', {}).get('video', {})
  68             if not format_info:
  69                 continue
  70             video_info_list = format_info.get('videoInfoList')
  71             if not video_info_list or not isinstance(video_info_list, list):
  72                 continue
  73             video_info = video_info_list[0]
  74             if not video_info or not isinstance(video_info, dict):
  75                 continue
  76             video_url = video_info.get('videoUrl')
  77             if not video_url:
  78                 continue
  79             format_id = format_info.get('ffname')
  80             formats.append({
  81                 'format_id': format_id,
  82                 'url': video_url,
  83                 'ext': mimetype2ext(video_info.get('videoMimeType')),
  84                 'quality': quality(format_id),
  85             })
  86         self._sort_formats(formats)
  87
  88         return {
  89             'id': video_id,
  90             'title': remove_end(self._og_search_title(webpage), ' - IMDb'),
  91             'formats': formats,
  92             'description': descr,
  93             'thumbnail': format_info.get('slate'),
  94         }
  95
  96
  97 class ImdbListIE(InfoExtractor):
  98     IE_NAME = 'imdb:list'
  99     IE_DESC = 'Internet Movie Database lists'
 100     _VALID_URL = r'https?://(?:www\.)?imdb\.com/list/(?P<id>[\da-zA-Z_-]{11})'
 101     _TEST = {
 102         'url': 'http://www.imdb.com/list/JFs9NWw6XI0',
 103         'info_dict': {
 104             'id': 'JFs9NWw6XI0',
 105             'title': 'March 23, 2012 Releases',
 106         },
 107         'playlist_count': 7,
 108     }
 109
 110     def _real_extract(self, url):
 111         list_id = self._match_id(url)
 112         webpage = self._download_webpage(url, list_id)
 113         entries = [
 114             self.url_result('http://www.imdb.com' + m, 'Imdb')
 115             for m in re.findall(r'href="(/video/imdb/vi[^"]+)"\s+data-type="playlist"', webpage)]
 116
 117         list_title = self._html_search_regex(
 118             r'<h1 class="header">(.*?)</h1>', webpage, 'list title')
 119
 120         return self.playlist_result(entries, list_id, list_title)