_ Git - youtube-dl/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     _AGE_LIMITS = {
  47         'N-7': 7,
  48         'N-14': 14,
  49         'S': 18,
  50     }
  51
  52     def _real_extract(self, url):
  53         display_id = self._match_id(url)
  54
  55         webpage = self._download_webpage(
  56             url, display_id, 'Downloading player webpage')
  57
  58         video_id = self._search_regex(
  59             r'data-ep="([^"]+)"', webpage, 'video ID')
  60         title = self._og_search_title(webpage)
  61         description = self._og_search_description(webpage)
  62         upload_date = unified_strdate(self._search_regex(
  63             r'class="[^"]*meta-item[^"]*air-time[^"]*">.*?<strong>([^<]+)</strong>', webpage, 'upload date', fatal=False))
  64
  65         thumbnail_w = int_or_none(
  66             self._og_search_property('image:width', webpage, 'thumbnail width', fatal=False))
  67         thumbnail_h = int_or_none(
  68             self._og_search_property('image:height', webpage, 'thumbnail height', fatal=False))
  69         thumbnail = {
  70             'url': self._og_search_thumbnail(webpage),
  71         }
  72         if thumbnail_w and thumbnail_h:
  73             thumbnail.update({
  74                 'width': thumbnail_w,
  75                 'height': thumbnail_h,
  76             })
  77
  78         config = self._parse_json(self._search_regex(
  79             r'episodePlayer\((\{.*?\}),\s*\{', webpage, 'sources'), video_id)
  80
  81         if config.get('pGeo'):
  82             self.report_warning(
  83                 'This content might not be available in your country due to copyright reasons')
  84
  85         formats = [{
  86             'format_id': 'hls',
  87             'ext': 'mp4',
  88             'url': config['EpisodeVideoLink_HLS'],
  89         }]
  90
  91         m = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>[^/]+))/(?P<play_path>.+)$', config['EpisodeVideoLink'])
  92         if m:
  93             formats.append({
  94                 'format_id': 'rtmp',
  95                 'ext': 'flv',
  96                 'url': m.group('url'),
  97                 'play_path': m.group('play_path'),
  98                 'page_url': url,
  99             })
 100
 101         self._sort_formats(formats)
 102
 103         return {
 104             'id': video_id,
 105             'display_id': display_id,
 106             'title': title,
 107             'formats': formats,
 108             'thumbnails': [thumbnail],
 109             'duration': int_or_none(config.get('VideoTime')),
 110             'description': description,
 111             'age_limit': self._AGE_LIMITS.get(config.get('PGRating'), 0),
 112             'upload_date': upload_date,
 113         }