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