mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2025-10-31 14:45:14 +00:00
5c2266df4b
compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
95 lines
3.5 KiB
Python
95 lines
3.5 KiB
Python
from __future__ import unicode_literals
|
|
|
|
import re
|
|
|
|
from .common import InfoExtractor
|
|
from ..compat import compat_urlparse
|
|
from ..utils import (
|
|
ExtractorError,
|
|
NO_DEFAULT,
|
|
encode_dict,
|
|
sanitized_Request,
|
|
urlencode_postdata,
|
|
)
|
|
|
|
|
|
class NovaMovIE(InfoExtractor):
|
|
IE_NAME = 'novamov'
|
|
IE_DESC = 'NovaMov'
|
|
|
|
_VALID_URL_TEMPLATE = r'http://(?:(?:www\.)?%(host)s/(?:file|video)/|(?:(?:embed|www)\.)%(host)s/embed\.php\?(?:.*?&)?v=)(?P<id>[a-z\d]{13})'
|
|
_VALID_URL = _VALID_URL_TEMPLATE % {'host': 'novamov\.com'}
|
|
|
|
_HOST = 'www.novamov.com'
|
|
|
|
_FILE_DELETED_REGEX = r'This file no longer exists on our servers!</h2>'
|
|
_FILEKEY_REGEX = r'flashvars\.filekey="(?P<filekey>[^"]+)";'
|
|
_TITLE_REGEX = r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>([^<]+)</h3>'
|
|
_DESCRIPTION_REGEX = r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>[^<]+</h3><p>([^<]+)</p>'
|
|
|
|
_TEST = {
|
|
'url': 'http://www.novamov.com/video/4rurhn9x446jj',
|
|
'md5': '7205f346a52bbeba427603ba10d4b935',
|
|
'info_dict': {
|
|
'id': '4rurhn9x446jj',
|
|
'ext': 'flv',
|
|
'title': 'search engine optimization',
|
|
'description': 'search engine optimization is used to rank the web page in the google search engine'
|
|
},
|
|
'skip': '"Invalid token" errors abound (in web interface as well as youtube-dl, there is nothing we can do about it.)'
|
|
}
|
|
|
|
def _real_extract(self, url):
|
|
video_id = self._match_id(url)
|
|
|
|
url = 'http://%s/video/%s' % (self._HOST, video_id)
|
|
|
|
webpage = self._download_webpage(
|
|
url, video_id, 'Downloading video page')
|
|
|
|
if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
|
|
raise ExtractorError('Video %s does not exist' % video_id, expected=True)
|
|
|
|
def extract_filekey(default=NO_DEFAULT):
|
|
return self._search_regex(
|
|
self._FILEKEY_REGEX, webpage, 'filekey', default=default)
|
|
|
|
filekey = extract_filekey(default=None)
|
|
|
|
if not filekey:
|
|
fields = self._hidden_inputs(webpage)
|
|
post_url = self._search_regex(
|
|
r'<form[^>]+action=(["\'])(?P<url>.+?)\1', webpage,
|
|
'post url', default=url, group='url')
|
|
if not post_url.startswith('http'):
|
|
post_url = compat_urlparse.urljoin(url, post_url)
|
|
request = sanitized_Request(
|
|
post_url, urlencode_postdata(encode_dict(fields)))
|
|
request.add_header('Content-Type', 'application/x-www-form-urlencoded')
|
|
request.add_header('Referer', post_url)
|
|
webpage = self._download_webpage(
|
|
request, video_id, 'Downloading continue to the video page')
|
|
|
|
filekey = extract_filekey()
|
|
|
|
title = self._html_search_regex(self._TITLE_REGEX, webpage, 'title', fatal=False)
|
|
description = self._html_search_regex(self._DESCRIPTION_REGEX, webpage, 'description', default='', fatal=False)
|
|
|
|
api_response = self._download_webpage(
|
|
'http://%s/api/player.api.php?key=%s&file=%s' % (self._HOST, filekey, video_id), video_id,
|
|
'Downloading video api response')
|
|
|
|
response = compat_urlparse.parse_qs(api_response)
|
|
|
|
if 'error_msg' in response:
|
|
raise ExtractorError('%s returned error: %s' % (self.IE_NAME, response['error_msg'][0]), expected=True)
|
|
|
|
video_url = response['url'][0]
|
|
|
|
return {
|
|
'id': video_id,
|
|
'url': video_url,
|
|
'title': title,
|
|
'description': description
|
|
}
|