1
0
Fork 0
mirror of https://codeberg.org/polarisfm/youtube-dl.git synced 2024-12-26 09:36:46 +00:00

[nova] Add extractor

This commit is contained in:
Sergey M․ 2015-06-02 00:53:04 +06:00
parent 866b296d0f
commit 923e79e2e4
2 changed files with 136 additions and 0 deletions

View file

@ -352,6 +352,7 @@ from .ninegag import NineGagIE
from .noco import NocoIE from .noco import NocoIE
from .normalboots import NormalbootsIE from .normalboots import NormalbootsIE
from .nosvideo import NosVideoIE from .nosvideo import NosVideoIE
from .nova import NovaIE
from .novamov import NovaMovIE from .novamov import NovaMovIE
from .nowness import NownessIE from .nowness import NownessIE
from .nowtv import NowTVIE from .nowtv import NowTVIE

View file

@ -0,0 +1,135 @@
# encoding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
class NovaIE(InfoExtractor):
IE_DESC = 'TN.cz, Prásk.tv, Nova.cz, Novaplus.cz, FANDA.tv, Krásná.cz and Doma.cz'
_VALID_URL = 'http://(?:[^.]+\.)?(?P<site>tv(?:noviny)?|tn|novaplus|vymena|fanda|krasna|doma|prask)\.nova\.cz/(?:[^/]+/)+(?P<id>[^/]+)(?:\.html|/?)'
_TESTS = [{
'url': 'http://tvnoviny.nova.cz/clanek/novinky/co-na-sebe-sportaci-praskli-vime-jestli-pujde-hrdlicka-na-materskou.html',
'info_dict': {
'id': '1608920',
'display_id': 'co-na-sebe-sportaci-praskli-vime-jestli-pujde-hrdlicka-na-materskou',
'ext': 'flv',
'title': 'Duel: Michal Hrdlička a Petr Suchoň',
'description': 'md5:d0cc509858eee1b1374111c588c6f5d5',
'thumbnail': 're:^https?://.*\.(?:jpg)',
},
'params': {
# rtmp download
'skip_download': True,
}
}, {
'url': 'http://tn.nova.cz/clanek/tajemstvi-ukryte-v-podzemi-specialni-nemocnice-v-prazske-krci.html',
'md5': '1dd7b9d5ea27bc361f110cd855a19bd3',
'info_dict': {
'id': '1757139',
'display_id': 'tajemstvi-ukryte-v-podzemi-specialni-nemocnice-v-prazske-krci',
'ext': 'mp4',
'title': 'Podzemní nemocnice v pražské Krči',
'description': 'md5:f0a42dd239c26f61c28f19e62d20ef53',
'thumbnail': 're:^https?://.*\.(?:jpg)',
}
}, {
'url': 'http://novaplus.nova.cz/porad/policie-modrava/video/5591-policie-modrava-15-dil-blondynka-na-hrbitove/',
'info_dict': {
'id': '1756825',
'display_id': '5591-policie-modrava-15-dil-blondynka-na-hrbitove',
'ext': 'flv',
'title': 'Policie Modrava - 15. díl - Blondýnka na hřbitově',
'description': 'md5:d804ba6b30bc7da2705b1fea961bddfe',
'thumbnail': 're:^https?://.*\.(?:jpg)',
},
'params': {
# rtmp download
'skip_download': True,
}
}, {
'url': 'http://sport.tn.nova.cz/clanek/sport/hokej/nhl/zivot-jde-dal-hodnotil-po-vyrazeni-z-playoff-jiri-sekac.html',
'only_matching': True,
}, {
'url': 'http://fanda.nova.cz/clanek/fun-and-games/krvavy-epos-zaklinac-3-divoky-hon-vychazi-vyhrajte-ho-pro-sebe.html',
'only_matching': True,
}, {
'url': 'http://doma.nova.cz/clanek/zdravi/prijdte-se-zapsat-do-registru-kostni-drene-jiz-ve-stredu-3-cervna.html',
'only_matching': True,
}, {
'url': 'http://prask.nova.cz/clanek/novinky/co-si-na-sobe-nase-hvezdy-nechaly-pojistit.html',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
display_id = mobj.group('id')
site = mobj.group('site')
webpage = self._download_webpage(url, display_id)
video_id = self._search_regex(
[r"(?:media|video_id)\s*:\s*'(\d+)'",
r'media=(\d+)',
r'id="article_video_(\d+)"',
r'id="player_(\d+)"'],
webpage, 'video id')
config_url = self._search_regex(
r'src="(http://tn\.nova\.cz/bin/player/videojs/config\.php\?[^"]+)"',
webpage, 'config url', default=None)
if not config_url:
DEFAULT_SITE_ID = '23000'
SITES = {
'tvnoviny': DEFAULT_SITE_ID,
'novaplus': DEFAULT_SITE_ID,
'vymena': DEFAULT_SITE_ID,
'krasna': DEFAULT_SITE_ID,
'fanda': '30',
'tn': '30',
'doma': '30',
}
site_id = self._search_regex(
r'site=(\d+)', webpage, 'site id', default=None) or SITES.get(site, DEFAULT_SITE_ID)
config_url = ('http://tn.nova.cz/bin/player/videojs/config.php?site=%s&media=%s&jsVar=vjsconfig'
% (site_id, video_id))
config = self._download_json(
config_url, display_id,
'Downloading config JSON',
transform_source=lambda s: re.sub(r'var\s+[\da-zA-Z_]+\s*=\s*({.+?});', r'\1', s))
mediafile = config['mediafile']
video_url = mediafile['src']
m = re.search(r'^(?P<url>rtmpe?://[^/]+/(?P<app>[^/]+?))/&*(?P<playpath>.+)$', video_url)
if m:
formats = [{
'url': m.group('url'),
'app': m.group('app'),
'play_path': m.group('playpath'),
'player_path': 'http://tvnoviny.nova.cz/static/shared/app/videojs/video-js.swf',
'ext': 'flv',
}]
else:
formats = [{
'url': video_url,
}]
self._sort_formats(formats)
title = mediafile.get('meta', {}).get('title') or self._og_search_title(webpage)
description = self._og_search_description(webpage)
thumbnail = config.get('poster')
return {
'id': video_id,
'display_id': display_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'formats': formats,
}