1
mirror of https://github.com/yt-dlp/yt-dlp synced 2024-12-04 13:45:17 +01:00
yt-dlp/yt_dlp/extractor/tvnoe.py
Pccode66 7a5c1cfe93
Completely change project name to yt-dlp (#85)
* All modules and binary names are changed
* All documentation references changed
* yt-dlp no longer loads youtube-dlc config files
* All URLs changed to point to organization account

Co-authored-by: Pccode66
Co-authored-by: pukkandan
2021-02-25 00:15:56 +05:30

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