youtube_dl/extractor/ruutu.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import compat_urllib_parse_urlparse
   6 from ..utils import (
   7     determine_ext,
   8     int_or_none,
   9     xpath_text,
  10 )
  11
  12
  13 class RuutuIE(InfoExtractor):
  14     _VALID_URL = r'http://(?:www\.)?ruutu\.fi/ohjelmat/(?:[^/?#]+/)*(?P<id>[^/?#]+)'
  15     _TESTS = [
  16         {
  17             'url': 'http://www.ruutu.fi/ohjelmat/oletko-aina-halunnut-tietaa-mita-tapahtuu-vain-hetki-ennen-lahetysta-nyt-se-selvisi',
  18             'md5': 'ab2093f39be1ca8581963451b3c0234f',
  19             'info_dict': {
  20                 'id': '2058907',
  21                 'display_id': 'oletko-aina-halunnut-tietaa-mita-tapahtuu-vain-hetki-ennen-lahetysta-nyt-se-selvisi',
  22                 'ext': 'mp4',
  23                 'title': 'Oletko aina halunnut tietää mitä tapahtuu vain hetki ennen lähetystä? - Nyt se selvisi!',
  24                 'description': 'md5:cfc6ccf0e57a814360df464a91ff67d6',
  25                 'thumbnail': 're:^https?://.*\.jpg$',
  26                 'duration': 114,
  27                 'age_limit': 0,
  28             },
  29         },
  30         {
  31             'url': 'http://www.ruutu.fi/ohjelmat/superpesis/superpesis-katso-koko-kausi-ruudussa',
  32             'md5': '065a10ae4d5b8cfd9d0c3d332465e3d9',
  33             'info_dict': {
  34                 'id': '2057306',
  35                 'display_id': 'superpesis-katso-koko-kausi-ruudussa',
  36                 'ext': 'mp4',
  37                 'title': 'Superpesis: katso koko kausi Ruudussa',
  38                 'description': 'md5:44c44a99fdbe5b380ab74ebd75f0af77',
  39                 'thumbnail': 're:^https?://.*\.jpg$',
  40                 'duration': 40,
  41                 'age_limit': 0,
  42             },
  43         },
  44     ]
  45
  46     def _real_extract(self, url):
  47         display_id = self._match_id(url)
  48
  49         webpage = self._download_webpage(url, display_id)
  50
  51         video_id = self._search_regex(
  52             r'data-media-id="(\d+)"', webpage, 'media id')
  53
  54         video_xml_url = None
  55
  56         media_data = self._search_regex(
  57             r'jQuery\.extend\([^,]+,\s*(.+?)\);', webpage,
  58             'media data', default=None)
  59         if media_data:
  60             media_json = self._parse_json(media_data, display_id, fatal=False)
  61             if media_json:
  62                 xml_url = media_json.get('ruutuplayer', {}).get('xmlUrl')
  63                 if xml_url:
  64                     video_xml_url = xml_url.replace('{ID}', video_id)
  65
  66         if not video_xml_url:
  67             video_xml_url = 'http://gatling.ruutu.fi/media-xml-cache?id=%s' % video_id
  68
  69         video_xml = self._download_xml(video_xml_url, video_id)
  70
  71         formats = []
  72         processed_urls = []
  73
  74         def extract_formats(node):
  75             for child in node:
  76                 if child.tag.endswith('Files'):
  77                     extract_formats(child)
  78                 elif child.tag.endswith('File'):
  79                     video_url = child.text
  80                     if not video_url or video_url in processed_urls or 'NOT_USED' in video_url:
  81                         return
  82                     processed_urls.append(video_url)
  83                     ext = determine_ext(video_url)
  84                     if ext == 'm3u8':
  85                         formats.extend(self._extract_m3u8_formats(
  86                             video_url, video_id, 'mp4', m3u8_id='hls'))
  87                     elif ext == 'f4m':
  88                         formats.extend(self._extract_f4m_formats(
  89                             video_url, video_id, f4m_id='hds'))
  90                     else:
  91                         proto = compat_urllib_parse_urlparse(video_url).scheme
  92                         if not child.tag.startswith('HTTP') and proto != 'rtmp':
  93                             continue
  94                         preference = -1 if proto == 'rtmp' else 1
  95                         label = child.get('label')
  96                         tbr = int_or_none(child.get('bitrate'))
  97                         width, height = [int_or_none(x) for x in child.get('resolution', '').split('x')]
  98                         formats.append({
  99                             'format_id': '%s-%s' % (proto, label if label else tbr),
 100                             'url': video_url,
 101                             'width': width,
 102                             'height': height,
 103                             'tbr': tbr,
 104                             'preference': preference,
 105                         })
 106
 107         extract_formats(video_xml.find('./Clip'))
 108         self._sort_formats(formats)
 109
 110         return {
 111             'id': video_id,
 112             'display_id': display_id,
 113             'title': self._og_search_title(webpage),
 114             'description': self._og_search_description(webpage),
 115             'thumbnail': self._og_search_thumbnail(webpage),
 116             'duration': int_or_none(xpath_text(video_xml, './/Runtime', 'duration')),
 117             'age_limit': int_or_none(xpath_text(video_xml, './/AgeLimit', 'age limit')),
 118             'formats': formats,
 119         }