mirror/yt-dlc
1
0
Fork 0
mirror of https://github.com/blackjack4494/yt-dlc.git synced 2024-12-21 23:33:10 +00:00
Code Issues Releases Wiki Activity

[cloudy] Retry extraction on 410 status code (#3743 #3744)

Browse source
This commit is contained in:
Sergey M․ 2014-09-14 19:04:16 +07:00
parent 3b11e86eeb
commit eb3bd7ba8d
1 changed files with 40 additions and 16 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

56
youtube_dl/extractor/cloudy.py
View file

@ -9,6 +9,8 @@ from ..utils import (
compat_parse_qs, compat_parse_qs,
compat_urllib_parse, compat_urllib_parse,
remove_end, remove_end,
HEADRequest,
compat_HTTPError,
) )
@ -21,6 +23,7 @@ class CloudyIE(InfoExtractor):
''' '''
_EMBED_URL = 'http://www.%s/embed.php?id=%s' _EMBED_URL = 'http://www.%s/embed.php?id=%s'
_API_URL = 'http://www.%s/api/player.api.php?%s' _API_URL = 'http://www.%s/api/player.api.php?%s'
_MAX_TRIES = 2
_TESTS = [ _TESTS = [
{ {
'url': 'https://www.cloudy.ec/v/af511e2527aac', 'url': 'https://www.cloudy.ec/v/af511e2527aac',
@ -42,24 +45,30 @@ class CloudyIE(InfoExtractor):
} }
] ]
def _real_extract(self, url): def _extract_video(self, video_host, video_id, file_key, error_url=None, try_num=0):
mobj = re.match(self._VALID_URL, url)
video_host = mobj.group('host')
video_id = mobj.group('id')
url = self._EMBED_URL % (video_host, video_id) if try_num > self._MAX_TRIES - 1:
webpage = self._download_webpage(url, video_id) raise ExtractorError('Unable to extract video URL', expected=True)
file_key = self._search_regex( form = {
r'filekey\s*=\s*"([^"]+)"', webpage, 'file_key')
data_url = self._API_URL % (video_host, compat_urllib_parse.urlencode({
'file': video_id, 'file': video_id,
'key': file_key, 'key': file_key,
})) }
if error_url:
form.update({
'numOfErrors': try_num,
'errorCode': '404',
'errorUrl': error_url,
})
data_url = self._API_URL % (video_host, compat_urllib_parse.urlencode(form))
player_data = self._download_webpage( player_data = self._download_webpage(
data_url, video_id, 'Downloading player data') data_url, video_id, 'Downloading player data')
data = compat_parse_qs(player_data) data = compat_parse_qs(player_data)
try_num += 1
if 'error' in data: if 'error' in data:
raise ExtractorError( raise ExtractorError(
'%s error: %s' % (self.IE_NAME, ' '.join(data['error_msg'])), '%s error: %s' % (self.IE_NAME, ' '.join(data['error_msg'])),
@ -69,16 +78,31 @@ class CloudyIE(InfoExtractor):
if title: if title:
title = remove_end(title, '&asdasdas').strip() title = remove_end(title, '&asdasdas').strip()
formats = []
video_url = data.get('url', [None])[0] video_url = data.get('url', [None])[0]
if video_url: if video_url:
formats.append({ try:
'format_id': 'sd', self._request_webpage(HEADRequest(video_url), video_id, 'Checking video URL')
'url': video_url, except ExtractorError as e:
}) if isinstance(e.cause, compat_HTTPError) and e.cause.code in [404, 410]:
self.report_warning('Invalid video URL, requesting another', video_id)
return self._extract_video(video_host, video_id, file_key, video_url, try_num)
return { return {
'id': video_id, 'id': video_id,
'url': video_url,
'title': title, 'title': title,
'formats': formats,
} }
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_host = mobj.group('host')
video_id = mobj.group('id')
url = self._EMBED_URL % (video_host, video_id)
webpage = self._download_webpage(url, video_id)
file_key = self._search_regex(
r'filekey\s*=\s*"([^"]+)"', webpage, 'file_key')
return self._extract_video(video_host, video_id, file_key)