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

   1 import re
   2 import xml.etree.ElementTree
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     determine_ext,
   7 )
   8
   9
  10 class AppleTrailersIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?trailers.apple.com/trailers/(?P<company>[^/]+)/(?P<movie>[^/]+)'
  12     _TEST = {
  13         u"url": u"http://trailers.apple.com/trailers/wb/manofsteel/",
  14         u"playlist": [
  15             {
  16                 u"file": u"manofsteel-trailer4.mov",
  17                 u"md5": u"11874af099d480cc09e103b189805d5f",
  18                 u"info_dict": {
  19                     u"duration": 111,
  20                     u"thumbnail": u"http://trailers.apple.com/trailers/wb/manofsteel/images/thumbnail_11624.jpg",
  21                     u"title": u"Trailer 4",
  22                     u"upload_date": u"20130523",
  23                     u"uploader_id": u"wb",
  24                 },
  25             },
  26             {
  27                 u"file": u"manofsteel-trailer3.mov",
  28                 u"md5": u"07a0a262aae5afe68120eed61137ab34",
  29                 u"info_dict": {
  30                     u"duration": 182,
  31                     u"thumbnail": u"http://trailers.apple.com/trailers/wb/manofsteel/images/thumbnail_10793.jpg",
  32                     u"title": u"Trailer 3",
  33                     u"upload_date": u"20130417",
  34                     u"uploader_id": u"wb",
  35                 },
  36             },
  37             {
  38                 u"file": u"manofsteel-trailer.mov",
  39                 u"md5": u"e401fde0813008e3307e54b6f384cff1",
  40                 u"info_dict": {
  41                     u"duration": 148,
  42                     u"thumbnail": u"http://trailers.apple.com/trailers/wb/manofsteel/images/thumbnail_8703.jpg",
  43                     u"title": u"Trailer",
  44                     u"upload_date": u"20121212",
  45                     u"uploader_id": u"wb",
  46                 },
  47             },
  48             {
  49                 u"file": u"manofsteel-teaser.mov",
  50                 u"md5": u"76b392f2ae9e7c98b22913c10a639c97",
  51                 u"info_dict": {
  52                     u"duration": 93,
  53                     u"thumbnail": u"http://trailers.apple.com/trailers/wb/manofsteel/images/thumbnail_6899.jpg",
  54                     u"title": u"Teaser",
  55                     u"upload_date": u"20120721",
  56                     u"uploader_id": u"wb",
  57                 },
  58             }
  59         ]
  60     }
  61
  62     def _real_extract(self, url):
  63         mobj = re.match(self._VALID_URL, url)
  64         movie = mobj.group('movie')
  65         uploader_id = mobj.group('company')
  66
  67         playlist_url = url.partition(u'?')[0] + u'/includes/playlists/web.inc'
  68         playlist_snippet = self._download_webpage(playlist_url, movie)
  69         playlist_cleaned = re.sub(r'(?s)<script>.*?</script>', u'', playlist_snippet)
  70         playlist_html = u'<html>' + playlist_cleaned + u'</html>'
  71
  72         size_cache = {}
  73
  74         doc = xml.etree.ElementTree.fromstring(playlist_html)
  75         playlist = []
  76         for li in doc.findall('./div/ul/li'):
  77             title = li.find('.//h3').text
  78             video_id = movie + '-' + re.sub(r'[^a-zA-Z0-9]', '', title).lower()
  79             thumbnail = li.find('.//img').attrib['src']
  80
  81             date_el = li.find('.//p')
  82             upload_date = None
  83             m = re.search(r':\s?(?P<month>[0-9]{2})/(?P<day>[0-9]{2})/(?P<year>[0-9]{2})', date_el.text)
  84             if m:
  85                 upload_date = u'20' + m.group('year') + m.group('month') + m.group('day')
  86             runtime_el = date_el.find('./br')
  87             m = re.search(r':\s?(?P<minutes>[0-9]+):(?P<seconds>[0-9]{1,2})', runtime_el.tail)
  88             duration = None
  89             if m:
  90                 duration = 60 * int(m.group('minutes')) + int(m.group('seconds'))
  91
  92             formats = []
  93             for formats_el in li.findall('.//a'):
  94                 if formats_el.attrib['class'] != 'OverlayPanel':
  95                     continue
  96                 target = formats_el.attrib['target']
  97
  98                 format_code = formats_el.text
  99                 if 'Automatic' in format_code:
 100                     continue
 101
 102                 size_q = formats_el.attrib['href']
 103                 size_id = size_q.rpartition('#videos-')[2]
 104                 if size_id not in size_cache:
 105                     size_url = url + size_q
 106                     sizepage_html = self._download_webpage(
 107                         size_url, movie,
 108                         note=u'Downloading size info %s' % size_id,
 109                         errnote=u'Error while downloading size info %s' % size_id,
 110                     )
 111                     _doc = xml.etree.ElementTree.fromstring(sizepage_html)
 112                     size_cache[size_id] = _doc
 113
 114                 sizepage_doc = size_cache[size_id]
 115                 links = sizepage_doc.findall('.//{http://www.w3.org/1999/xhtml}ul/{http://www.w3.org/1999/xhtml}li/{http://www.w3.org/1999/xhtml}a')
 116                 for vid_a in links:
 117                     href = vid_a.get('href')
 118                     if not href.endswith(target):
 119                         continue
 120                     detail_q = href.partition('#')[0]
 121                     detail_url = url + '/' + detail_q
 122
 123                     m = re.match(r'includes/(?P<detail_id>[^/]+)/', detail_q)
 124                     detail_id = m.group('detail_id')
 125
 126                     detail_html = self._download_webpage(
 127                         detail_url, movie,
 128                         note=u'Downloading detail %s %s' % (detail_id, size_id),
 129                         errnote=u'Error while downloading detail %s %s' % (detail_id, size_id)
 130                     )
 131                     detail_doc = xml.etree.ElementTree.fromstring(detail_html)
 132                     movie_link_el = detail_doc.find('.//{http://www.w3.org/1999/xhtml}a')
 133                     assert movie_link_el.get('class') == 'movieLink'
 134                     movie_link = movie_link_el.get('href').partition('?')[0].replace('_', '_h')
 135                     ext = determine_ext(movie_link)
 136                     assert ext == 'mov'
 137
 138                     formats.append({
 139                         'format': format_code,
 140                         'ext': ext,
 141                         'url': movie_link,
 142                     })
 143
 144             info = {
 145                 '_type': 'video',
 146                 'id': video_id,
 147                 'title': title,
 148                 'formats': formats,
 149                 'title': title,
 150                 'duration': duration,
 151                 'thumbnail': thumbnail,
 152                 'upload_date': upload_date,
 153                 'uploader_id': uploader_id,
 154                 'user_agent': 'QuickTime compatible (youtube-dl)',
 155             }
 156             # TODO: Remove when #980 has been merged
 157             info['url'] = formats[-1]['url']
 158             info['ext'] = formats[-1]['ext']
 159
 160             playlist.append(info)
 161
 162         return {
 163             '_type': 'playlist',
 164             'id': movie,
 165             'entries': playlist,
 166         }