mirror of
https://github.com/ytdl-org/youtube-dl
synced 2024-12-05 00:52:55 +01:00
c73e330e7a
This simplifies code for callers of `_find_jwplayer_data()` which no longer have to run `_parse_json()` on the return value. It also makes sure that `_find_jwplayer_data()` returns either a `dict` or `None` and nothing else.
49 lines
1.6 KiB
Python
49 lines
1.6 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
from .common import InfoExtractor
|
|
from ..utils import (
|
|
clean_html,
|
|
get_element_by_class,
|
|
js_to_json,
|
|
)
|
|
|
|
|
|
class TVNoeIE(InfoExtractor):
|
|
_VALID_URL = r'https?://(?:www\.)?tvnoe\.cz/video/(?P<id>[0-9]+)'
|
|
_TEST = {
|
|
'url': 'http://www.tvnoe.cz/video/10362',
|
|
'md5': 'aee983f279aab96ec45ab6e2abb3c2ca',
|
|
'info_dict': {
|
|
'id': '10362',
|
|
'ext': 'mp4',
|
|
'series': 'Noční univerzita',
|
|
'title': 'prof. Tomáš Halík, Th.D. - Návrat náboženství a střet civilizací',
|
|
'description': 'md5:f337bae384e1a531a52c55ebc50fff41',
|
|
}
|
|
}
|
|
|
|
def _real_extract(self, url):
|
|
video_id = self._match_id(url)
|
|
webpage = self._download_webpage(url, video_id)
|
|
|
|
iframe_url = self._search_regex(
|
|
r'<iframe[^>]+src="([^"]+)"', webpage, 'iframe URL')
|
|
|
|
ifs_page = self._download_webpage(iframe_url, video_id)
|
|
jwplayer_data = self._find_jwplayer_data(
|
|
ifs_page, video_id, transform_source=js_to_json)
|
|
info_dict = self._parse_jwplayer_data(
|
|
jwplayer_data, video_id, require_title=False, base_url=iframe_url)
|
|
|
|
info_dict.update({
|
|
'id': video_id,
|
|
'title': clean_html(get_element_by_class(
|
|
'field-name-field-podnazev', webpage)),
|
|
'description': clean_html(get_element_by_class(
|
|
'field-name-body', webpage)),
|
|
'series': clean_html(get_element_by_class('title', webpage))
|
|
})
|
|
|
|
return info_dict
|