]>
Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/joj.py
2 from __future__
import unicode_literals
6 from .common
import InfoExtractor
7 from ..compat
import compat_str
15 class JojIE(InfoExtractor
):
19 https?://media\.joj\.sk/embed/
24 'url': 'https://media.joj.sk/embed/a388ec4c-6019-4a4a-9312-b1bee194e932',
26 'id': 'a388ec4c-6019-4a4a-9312-b1bee194e932',
28 'title': 'NOVÉ BÝVANIE',
29 'thumbnail': r
're:^https?://.*\.jpg$',
33 'url': 'https://media.joj.sk/embed/9i1cxv',
34 'only_matching': True,
36 'url': 'joj:a388ec4c-6019-4a4a-9312-b1bee194e932',
37 'only_matching': True,
40 'only_matching': True,
44 def _extract_urls(webpage
):
47 for mobj
in re
.finditer(
48 r
'<iframe\b[^>]+\bsrc=(["\'])(?P
<url
>(?
:https?
:)?
//media\
.joj\
.sk
/embed
/(?
:(?
!\
1).)+)\
1',
51 def _real_extract(self, url):
52 video_id = self._match_id(url)
54 webpage = self._download_webpage(
55 'https
://media
.joj
.sk
/embed
/%s' % video_id, video_id)
57 title = self._search_regex(
58 (r'videoTitle\s
*:\s
*(["\'])(?P<title>(?:(?!\1).)+)\1',
59 r'<title>(?P<title>[^<]+)'), webpage, 'title',
60 default=None, group='title') or self._og_search_title(webpage)
62 bitrates = self._parse_json(
64 r'(?s)(?:src|bitrates)\s*=\s*({.+?});', webpage, 'bitrates',
66 video_id, transform_source=js_to_json, fatal=False)
69 for format_url in try_get(bitrates, lambda x: x['mp4'], list) or []:
70 if isinstance(format_url, compat_str):
71 height = self._search_regex(
72 r'(\d+)[pP]\.', format_url, 'height', default=None)
75 'format_id': '%sp' % height if height else None,
76 'height': int(height),
79 playlist = self._download_xml(
80 'https://media.joj.sk/services/Video.php?clip=%s' % video_id,
82 for file_el in playlist.findall('./files/file'):
83 path = file_el.get('path')
86 format_id = file_el.get('id') or file_el.get('label')
88 'url': 'http://n16.joj.sk/storage/%s' % path.replace(
90 'format_id': format_id,
91 'height': int_or_none(self._search_regex(
92 r'(\d+)[pP]', format_id or path, 'height',
95 self._sort_formats(formats)
97 thumbnail = self._og_search_thumbnail(webpage)
99 duration = int_or_none(self._search_regex(
100 r'videoDuration\s*:\s*(\d+)', webpage, 'duration', fatal=False))
105 'thumbnail': thumbnail,
106 'duration': duration,