yt_dlp/extractor/apa.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     determine_ext,
   9     int_or_none,
  10     url_or_none,
  11 )
  12
  13
  14 class APAIE(InfoExtractor):
  15     _VALID_URL = r'(?P<base_url>https?://[^/]+\.apa\.at)/embed/(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
  16     _TESTS = [{
  17         'url': 'http://uvp.apa.at/embed/293f6d17-692a-44e3-9fd5-7b178f3a1029',
  18         'md5': '2b12292faeb0a7d930c778c7a5b4759b',
  19         'info_dict': {
  20             'id': '293f6d17-692a-44e3-9fd5-7b178f3a1029',
  21             'ext': 'mp4',
  22             'title': '293f6d17-692a-44e3-9fd5-7b178f3a1029',
  23             'thumbnail': r're:^https?://.*\.jpg$',
  24         },
  25     }, {
  26         'url': 'https://uvp-apapublisher.sf.apa.at/embed/2f94e9e6-d945-4db2-9548-f9a41ebf7b78',
  27         'only_matching': True,
  28     }, {
  29         'url': 'http://uvp-rma.sf.apa.at/embed/70404cca-2f47-4855-bbb8-20b1fae58f76',
  30         'only_matching': True,
  31     }, {
  32         'url': 'http://uvp-kleinezeitung.sf.apa.at/embed/f1c44979-dba2-4ebf-b021-e4cf2cac3c81',
  33         'only_matching': True,
  34     }]
  35
  36     @staticmethod
  37     def _extract_urls(webpage):
  38         return [
  39             mobj.group('url')
  40             for mobj in re.finditer(
  41                 r'<iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//[^/]+\.apa\.at/embed/[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}.*?)\1',
  42                 webpage)]
  43
  44     def _real_extract(self, url):
  45         mobj = self._match_valid_url(url)
  46         video_id, base_url = mobj.group('id', 'base_url')
  47
  48         webpage = self._download_webpage(
  49             '%s/player/%s' % (base_url, video_id), video_id)
  50
  51         jwplatform_id = self._search_regex(
  52             r'media[iI]d\s*:\s*["\'](?P<id>[a-zA-Z0-9]{8})', webpage,
  53             'jwplatform id', default=None)
  54
  55         if jwplatform_id:
  56             return self.url_result(
  57                 'jwplatform:' + jwplatform_id, ie='JWPlatform',
  58                 video_id=video_id)
  59
  60         def extract(field, name=None):
  61             return self._search_regex(
  62                 r'\b%s["\']\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1' % field,
  63                 webpage, name or field, default=None, group='value')
  64
  65         title = extract('title') or video_id
  66         description = extract('description')
  67         thumbnail = extract('poster', 'thumbnail')
  68
  69         formats = []
  70         for format_id in ('hls', 'progressive'):
  71             source_url = url_or_none(extract(format_id))
  72             if not source_url:
  73                 continue
  74             ext = determine_ext(source_url)
  75             if ext == 'm3u8':
  76                 formats.extend(self._extract_m3u8_formats(
  77                     source_url, video_id, 'mp4', entry_protocol='m3u8_native',
  78                     m3u8_id='hls', fatal=False))
  79             else:
  80                 height = int_or_none(self._search_regex(
  81                     r'(\d+)\.mp4', source_url, 'height', default=None))
  82                 formats.append({
  83                     'url': source_url,
  84                     'format_id': format_id,
  85                     'height': height,
  86                 })
  87         self._sort_formats(formats)
  88
  89         return {
  90             'id': video_id,
  91             'title': title,
  92             'description': description,
  93             'thumbnail': thumbnail,
  94             'formats': formats,
  95         }