_ 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 ..compat import compat_str
   7 from ..utils import (
   8     determine_ext,
   9     mimetype2ext,
  10     qualities,
  11     remove_end,
  12 )
  13
  14
  15 class ImdbIE(InfoExtractor):
  16     IE_NAME = 'imdb'
  17     IE_DESC = 'Internet Movie Database trailers'
  18     _VALID_URL = r'https?://(?:www|m)\.imdb\.com/(?:video|title).+?[/-]vi(?P<id>\d+)'
  19
  20     _TESTS = [{
  21         'url': 'http://www.imdb.com/video/imdb/vi2524815897',
  22         'info_dict': {
  23             'id': '2524815897',
  24             'ext': 'mp4',
  25             'title': 'Ice Age: Continental Drift Trailer (No. 2)',
  26             'description': 'md5:9061c2219254e5d14e03c25c98e96a81',
  27         }
  28     }, {
  29         'url': 'http://www.imdb.com/video/_/vi2524815897',
  30         'only_matching': True,
  31     }, {
  32         'url': 'http://www.imdb.com/title/tt1667889/?ref_=ext_shr_eml_vi#lb-vi2524815897',
  33         'only_matching': True,
  34     }, {
  35         'url': 'http://www.imdb.com/title/tt1667889/#lb-vi2524815897',
  36         'only_matching': True,
  37     }, {
  38         'url': 'http://www.imdb.com/videoplayer/vi1562949145',
  39         'only_matching': True,
  40     }, {
  41         'url': 'http://www.imdb.com/title/tt4218696/videoplayer/vi2608641561',
  42         'only_matching': True,
  43     }]
  44
  45     def _real_extract(self, url):
  46         video_id = self._match_id(url)
  47         webpage = self._download_webpage('http://www.imdb.com/video/imdb/vi%s' % video_id, video_id)
  48         descr = self._html_search_regex(
  49             r'(?s)<span itemprop="description">(.*?)</span>',
  50             webpage, 'description', fatal=False)
  51         player_url = 'http://www.imdb.com/video/imdb/vi%s/imdb/single' % video_id
  52         player_page = self._download_webpage(
  53             player_url, video_id, 'Downloading player page')
  54         # the player page contains the info for the default format, we have to
  55         # fetch other pages for the rest of the formats
  56         extra_formats = re.findall(r'href="(?P<url>%s.*?)".*?>(?P<name>.*?)<' % re.escape(player_url), player_page)
  57         format_pages = [
  58             self._download_webpage(
  59                 f_url, video_id, 'Downloading info for %s format' % f_name)
  60             for f_url, f_name in extra_formats]
  61         format_pages.append(player_page)
  62
  63         quality = qualities(('SD', '480p', '720p', '1080p'))
  64         formats = []
  65         for format_page in format_pages:
  66             json_data = self._search_regex(
  67                 r'<script[^>]+class="imdb-player-data"[^>]*?>(.*?)</script>',
  68                 format_page, 'json data', flags=re.DOTALL)
  69             info = self._parse_json(json_data, video_id, fatal=False)
  70             if not info:
  71                 continue
  72             format_info = info.get('videoPlayerObject', {}).get('video', {})
  73             if not format_info:
  74                 continue
  75             video_info_list = format_info.get('videoInfoList')
  76             if not video_info_list or not isinstance(video_info_list, list):
  77                 continue
  78             for video_info in video_info_list:
  79                 if not video_info or not isinstance(video_info, dict):
  80                     continue
  81                 video_url = video_info.get('videoUrl')
  82                 if not video_url or not isinstance(video_url, compat_str):
  83                     continue
  84                 if (video_info.get('videoMimeType') == 'application/x-mpegURL' or
  85                         determine_ext(video_url) == 'm3u8'):
  86                     formats.extend(self._extract_m3u8_formats(
  87                         video_url, video_id, 'mp4', entry_protocol='m3u8_native',
  88                         m3u8_id='hls', fatal=False))
  89                     continue
  90                 format_id = format_info.get('ffname')
  91                 formats.append({
  92                     'format_id': format_id,
  93                     'url': video_url,
  94                     'ext': mimetype2ext(video_info.get('videoMimeType')),
  95                     'quality': quality(format_id),
  96                 })
  97         self._sort_formats(formats)
  98
  99         return {
 100             'id': video_id,
 101             'title': remove_end(self._og_search_title(webpage), ' - IMDb'),
 102             'formats': formats,
 103             'description': descr,
 104             'thumbnail': format_info.get('slate'),
 105         }
 106
 107
 108 class ImdbListIE(InfoExtractor):
 109     IE_NAME = 'imdb:list'
 110     IE_DESC = 'Internet Movie Database lists'
 111     _VALID_URL = r'https?://(?:www\.)?imdb\.com/list/(?P<id>[\da-zA-Z_-]{11})'
 112     _TEST = {
 113         'url': 'http://www.imdb.com/list/JFs9NWw6XI0',
 114         'info_dict': {
 115             'id': 'JFs9NWw6XI0',
 116             'title': 'March 23, 2012 Releases',
 117         },
 118         'playlist_count': 7,
 119     }
 120
 121     def _real_extract(self, url):
 122         list_id = self._match_id(url)
 123         webpage = self._download_webpage(url, list_id)
 124         entries = [
 125             self.url_result('http://www.imdb.com' + m, 'Imdb')
 126             for m in re.findall(r'href="(/video/imdb/vi[^"]+)"\s+data-type="playlist"', webpage)]
 127
 128         list_title = self._html_search_regex(
 129             r'<h1 class="header">(.*?)</h1>', webpage, 'list title')
 130
 131         return self.playlist_result(entries, list_id, list_title)