_ Git - youtube-dl/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 ..utils import (
   8     qualities,
   9 )
  10
  11
  12 class ImdbIE(InfoExtractor):
  13     IE_NAME = 'imdb'
  14     IE_DESC = 'Internet Movie Database trailers'
  15     _VALID_URL = r'https?://(?:www|m)\.imdb\.com/video/[^/]+/vi(?P<id>\d+)'
  16
  17     _TESTS = [{
  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         'url': 'http://www.imdb.com/video/_/vi2524815897',
  27         'only_matching': True,
  28     }]
  29
  30     def _real_extract(self, url):
  31         video_id = self._match_id(url)
  32         webpage = self._download_webpage('http://www.imdb.com/video/imdb/vi%s' % video_id, video_id)
  33         descr = self._html_search_regex(
  34             r'(?s)<span itemprop="description">(.*?)</span>',
  35             webpage, 'description', fatal=False)
  36         player_url = 'http://www.imdb.com/video/imdb/vi%s/imdb/single' % video_id
  37         player_page = self._download_webpage(
  38             player_url, video_id, 'Downloading player page')
  39         # the player page contains the info for the default format, we have to
  40         # fetch other pages for the rest of the formats
  41         extra_formats = re.findall(r'href="(?P<url>%s.*?)".*?>(?P<name>.*?)<' % re.escape(player_url), player_page)
  42         format_pages = [
  43             self._download_webpage(
  44                 f_url, video_id, 'Downloading info for %s format' % f_name)
  45             for f_url, f_name in extra_formats]
  46         format_pages.append(player_page)
  47
  48         quality = qualities(('SD', '480p', '720p', '1080p'))
  49         formats = []
  50         for format_page in format_pages:
  51             json_data = self._search_regex(
  52                 r'<script[^>]+class="imdb-player-data"[^>]*?>(.*?)</script>',
  53                 format_page, 'json data', flags=re.DOTALL)
  54             info = json.loads(json_data)
  55             format_info = info['videoPlayerObject']['video']
  56             f_id = format_info['ffname']
  57             formats.append({
  58                 'format_id': f_id,
  59                 'url': format_info['videoInfoList'][0]['videoUrl'],
  60                 'quality': quality(f_id),
  61             })
  62         self._sort_formats(formats)
  63
  64         return {
  65             'id': video_id,
  66             'title': self._og_search_title(webpage),
  67             'formats': formats,
  68             'description': descr,
  69             'thumbnail': format_info['slate'],
  70         }
  71
  72
  73 class ImdbListIE(InfoExtractor):
  74     IE_NAME = 'imdb:list'
  75     IE_DESC = 'Internet Movie Database lists'
  76     _VALID_URL = r'https?://www\.imdb\.com/list/(?P<id>[\da-zA-Z_-]{11})'
  77     _TEST = {
  78         'url': 'http://www.imdb.com/list/JFs9NWw6XI0',
  79         'info_dict': {
  80             'id': 'JFs9NWw6XI0',
  81             'title': 'March 23, 2012 Releases',
  82         },
  83         'playlist_count': 7,
  84     }
  85
  86     def _real_extract(self, url):
  87         list_id = self._match_id(url)
  88         webpage = self._download_webpage(url, list_id)
  89         entries = [
  90             self.url_result('http://www.imdb.com' + m, 'Imdb')
  91             for m in re.findall(r'href="(/video/imdb/vi[^"]+)"\s+data-type="playlist"', webpage)]
  92
  93         list_title = self._html_search_regex(
  94             r'<h1 class="header">(.*?)</h1>', webpage, 'list title')
  95
  96         return self.playlist_result(entries, list_id, list_title)