Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/lnkgo.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     int_or_none,
   9     unified_strdate,
  10 )
  11
  12
  13 class LnkGoIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?lnkgo\.(?:alfa\.)?lt/visi-video/(?P<show>[^/]+)/ziurek-(?P<id>[A-Za-z0-9-]+)'
  15     _TESTS = [{
  16         'url': 'http://lnkgo.alfa.lt/visi-video/yra-kaip-yra/ziurek-yra-kaip-yra-162',
  17         'info_dict': {
  18             'id': '46712',
  19             'ext': 'mp4',
  20             'title': 'Yra kaip yra',
  21             'upload_date': '20150107',
  22             'description': 'md5:d82a5e36b775b7048617f263a0e3475e',
  23             'age_limit': 7,
  24             'duration': 3019,
  25             'thumbnail': r're:^https?://.*\.jpg$'
  26         },
  27         'params': {
  28             'skip_download': True,  # HLS download
  29         },
  30     }, {
  31         'url': 'http://lnkgo.alfa.lt/visi-video/aktualai-pratesimas/ziurek-nerdas-taiso-kompiuteri-2',
  32         'info_dict': {
  33             'id': '47289',
  34             'ext': 'mp4',
  35             'title': 'Nėrdas: Kompiuterio Valymas',
  36             'upload_date': '20150113',
  37             'description': 'md5:7352d113a242a808676ff17e69db6a69',
  38             'age_limit': 18,
  39             'duration': 346,
  40             'thumbnail': r're:^https?://.*\.jpg$'
  41         },
  42         'params': {
  43             'skip_download': True,  # HLS download
  44         },
  45     }, {
  46         'url': 'http://www.lnkgo.lt/visi-video/aktualai-pratesimas/ziurek-putka-trys-klausimai',
  47         'only_matching': True,
  48     }]
  49     _AGE_LIMITS = {
  50         'N-7': 7,
  51         'N-14': 14,
  52         'S': 18,
  53     }
  54
  55     def _real_extract(self, url):
  56         display_id = self._match_id(url)
  57
  58         webpage = self._download_webpage(
  59             url, display_id, 'Downloading player webpage')
  60
  61         video_id = self._search_regex(
  62             r'data-ep="([^"]+)"', webpage, 'video ID')
  63         title = self._og_search_title(webpage)
  64         description = self._og_search_description(webpage)
  65         upload_date = unified_strdate(self._search_regex(
  66             r'class="[^"]*meta-item[^"]*air-time[^"]*">.*?<strong>([^<]+)</strong>', webpage, 'upload date', fatal=False))
  67
  68         thumbnail_w = int_or_none(
  69             self._og_search_property('image:width', webpage, 'thumbnail width', fatal=False))
  70         thumbnail_h = int_or_none(
  71             self._og_search_property('image:height', webpage, 'thumbnail height', fatal=False))
  72         thumbnail = {
  73             'url': self._og_search_thumbnail(webpage),
  74         }
  75         if thumbnail_w and thumbnail_h:
  76             thumbnail.update({
  77                 'width': thumbnail_w,
  78                 'height': thumbnail_h,
  79             })
  80
  81         config = self._parse_json(self._search_regex(
  82             r'episodePlayer\((\{.*?\}),\s*\{', webpage, 'sources'), video_id)
  83
  84         if config.get('pGeo'):
  85             self.report_warning(
  86                 'This content might not be available in your country due to copyright reasons')
  87
  88         formats = [{
  89             'format_id': 'hls',
  90             'ext': 'mp4',
  91             'url': config['EpisodeVideoLink_HLS'],
  92         }]
  93
  94         m = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>[^/]+))/(?P<play_path>.+)$', config['EpisodeVideoLink'])
  95         if m:
  96             formats.append({
  97                 'format_id': 'rtmp',
  98                 'ext': 'flv',
  99                 'url': m.group('url'),
 100                 'play_path': m.group('play_path'),
 101                 'page_url': url,
 102             })
 103
 104         self._sort_formats(formats)
 105
 106         return {
 107             'id': video_id,
 108             'display_id': display_id,
 109             'title': title,
 110             'formats': formats,
 111             'thumbnails': [thumbnail],
 112             'duration': int_or_none(config.get('VideoTime')),
 113             'description': description,
 114             'age_limit': self._AGE_LIMITS.get(config.get('PGRating'), 0),
 115             'upload_date': upload_date,
 116         }