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     js_to_json,
  10     unified_strdate,
  11 )
  12
  13
  14 class LnkGoIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:www\.)?lnkgo\.alfa\.lt/visi\-video/(?P<show>[^/]+)/ziurek\-(?P<display_id>[A-Za-z0-9\-]+)'
  16     _TESTS = [{
  17         'url': 'http://lnkgo.alfa.lt/visi-video/yra-kaip-yra/ziurek-yra-kaip-yra-162',
  18         'info_dict': {
  19             'id': '46712',
  20             'ext': 'mp4',
  21             'title': 'Yra kaip yra',
  22             'upload_date': '20150107',
  23             'description': 'md5:d82a5e36b775b7048617f263a0e3475e',
  24             'age_limit': 7,
  25             'duration': 3019,
  26             'thumbnail': 're:^https?://.*\.jpg$'
  27         },
  28         'params': {
  29             'skip_download': True,  # HLS download
  30         },
  31     }, {
  32         'url': 'http://lnkgo.alfa.lt/visi-video/aktualai-pratesimas/ziurek-nerdas-taiso-kompiuteri-2',
  33         'info_dict': {
  34             'id': '47289',
  35             'ext': 'mp4',
  36             'title': 'Nėrdas: Kompiuterio Valymas',
  37             'upload_date': '20150113',
  38             'description': 'md5:7352d113a242a808676ff17e69db6a69',
  39             'age_limit': 18,
  40             'duration': 346,
  41             'thumbnail': 're:^https?://.*\.jpg$'
  42         },
  43         'params': {
  44             'skip_download': True,  # HLS download
  45         },
  46     }]
  47     _AGE_LIMITS = {
  48         'N-7': 7,
  49         'N-14': 14,
  50         'S': 18,
  51     }
  52
  53     def _real_extract(self, url):
  54         mobj = re.match(self._VALID_URL, url)
  55         display_id = mobj.group('display_id')
  56
  57         webpage = self._download_webpage(
  58             url, display_id, 'Downloading player webpage')
  59
  60         video_id = self._search_regex(
  61             r'data-ep="([^"]+)"', webpage, 'video ID')
  62         title = self._og_search_title(webpage)
  63         description = self._og_search_description(webpage)
  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         upload_date = unified_strdate(self._search_regex(
  79             r'class="meta-item\sair-time">.*?<strong>([^<]+)</strong>', webpage, 'upload date', fatal=False))
  80         duration = int_or_none(self._search_regex(
  81             r'VideoDuration = "([^"]+)"', webpage, 'duration', fatal=False))
  82
  83         pg_rating = self._search_regex(
  84             r'pgrating="([^"]+)"', webpage, 'PG rating', fatal=False, default='')
  85         age_limit = self._AGE_LIMITS.get(pg_rating.upper(), 0)
  86
  87         sources_js = self._search_regex(
  88             r'(?s)sources:\s(\[.*?\]),', webpage, 'sources')
  89         sources = self._parse_json(
  90             sources_js, video_id, transform_source=js_to_json)
  91
  92         formats = []
  93         for source in sources:
  94             if source.get('provider') == 'rtmp':
  95                 m = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>[^/]+))/(?P<play_path>.+)$', source['file'])
  96                 if not m:
  97                     continue
  98                 formats.append({
  99                     'format_id': 'rtmp',
 100                     'ext': 'flv',
 101                     'url': m.group('url'),
 102                     'play_path': m.group('play_path'),
 103                     'page_url': url,
 104                 })
 105             elif source.get('file').endswith('.m3u8'):
 106                 formats.append({
 107                     'format_id': 'hls',
 108                     'ext': source.get('type', 'mp4'),
 109                     'url': source['file'],
 110                 })
 111
 112         self._sort_formats(formats)
 113
 114         return {
 115             'id': video_id,
 116             'display_id': display_id,
 117             'title': title,
 118             'formats': formats,
 119             'thumbnails': [thumbnail],
 120             'duration': duration,
 121             'description': description,
 122             'age_limit': age_limit,
 123             'upload_date': upload_date,
 124         }