_ 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     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 = self._og_search_thumbnail(webpage)
  66         thumbnail_w = int_or_none(
  67             self._og_search_property('image:width', webpage, 'thumbnail width', fatal=False))
  68         thumbnail_h = int_or_none(
  69             self._og_search_property('image:height', webpage, 'thumbnail height', fatal=False))
  70         thumbnails = [{
  71             'url': thumbnail,
  72             'width': thumbnail_w,
  73             'height': thumbnail_h,
  74         }]
  75
  76         upload_date = unified_strdate(self._search_regex(
  77             r'class="meta-item\sair-time">.*?<strong>([^<]+)</strong>', webpage, 'upload date', fatal=False))
  78         duration = int_or_none(self._search_regex(
  79             r'VideoDuration = "([^"]+)"', webpage, 'duration', fatal=False))
  80
  81         pg_rating = self._search_regex(
  82             r'pgrating="([^"]+)"', webpage, 'PG rating', fatal=False, default='')
  83         age_limit = self._AGE_LIMITS.get(pg_rating, 0)
  84
  85         sources_js = self._search_regex(
  86             r'(?s)sources:\s(\[.*?\]),', webpage, 'sources')
  87         sources = self._parse_json(
  88             sources_js, video_id, transform_source=js_to_json)
  89
  90         formats = []
  91         for source in sources:
  92             if source.get('provider') == 'rtmp':
  93                 m = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>[^/]+))/(?P<play_path>.+)$', source['file'])
  94                 if not m:
  95                     continue
  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             elif source.get('file').endswith('.m3u8'):
 104                 formats.append({
 105                     'format_id': 'hls',
 106                     'ext': source.get('type', 'mp4'),
 107                     'url': source['file'],
 108                 })
 109
 110         self._sort_formats(formats)
 111
 112         return {
 113             'id': video_id,
 114             'display_id': display_id,
 115             'title': title,
 116             'formats': formats,
 117             'thumbnails': thumbnails,
 118             'duration': duration,
 119             'description': description,
 120             'age_limit': age_limit,
 121             'upload_date': upload_date,
 122         }