mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-12-23 10:37:18 -05:00
[douyutv] Improve extraction and update tests
The JSON API sometimes return HTML pages with errors
This commit is contained in:
parent
51762e1a31
commit
aa9dc24f5a
@ -18,7 +18,7 @@ class DouyuTVIE(InfoExtractor):
|
|||||||
'display_id': 'iseven',
|
'display_id': 'iseven',
|
||||||
'ext': 'flv',
|
'ext': 'flv',
|
||||||
'title': 're:^清晨醒脑!T-ara根本停不下来! [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
|
'title': 're:^清晨醒脑!T-ara根本停不下来! [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
|
||||||
'description': 'md5:f34981259a03e980a3c6404190a3ed61',
|
'description': 're:.*m7show@163\.com.*',
|
||||||
'thumbnail': 're:^https?://.*\.jpg$',
|
'thumbnail': 're:^https?://.*\.jpg$',
|
||||||
'uploader': '7师傅',
|
'uploader': '7师傅',
|
||||||
'uploader_id': '431925',
|
'uploader_id': '431925',
|
||||||
@ -43,7 +43,7 @@ class DouyuTVIE(InfoExtractor):
|
|||||||
'params': {
|
'params': {
|
||||||
'skip_download': True,
|
'skip_download': True,
|
||||||
},
|
},
|
||||||
'skip': 'Romm not found',
|
'skip': 'Room not found',
|
||||||
}, {
|
}, {
|
||||||
'url': 'http://www.douyutv.com/17732',
|
'url': 'http://www.douyutv.com/17732',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
@ -51,7 +51,7 @@ class DouyuTVIE(InfoExtractor):
|
|||||||
'display_id': '17732',
|
'display_id': '17732',
|
||||||
'ext': 'flv',
|
'ext': 'flv',
|
||||||
'title': 're:^清晨醒脑!T-ara根本停不下来! [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
|
'title': 're:^清晨醒脑!T-ara根本停不下来! [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
|
||||||
'description': 'md5:f34981259a03e980a3c6404190a3ed61',
|
'description': 're:.*m7show@163\.com.*',
|
||||||
'thumbnail': 're:^https?://.*\.jpg$',
|
'thumbnail': 're:^https?://.*\.jpg$',
|
||||||
'uploader': '7师傅',
|
'uploader': '7师傅',
|
||||||
'uploader_id': '431925',
|
'uploader_id': '431925',
|
||||||
@ -75,13 +75,28 @@ class DouyuTVIE(InfoExtractor):
|
|||||||
room_id = self._html_search_regex(
|
room_id = self._html_search_regex(
|
||||||
r'"room_id"\s*:\s*(\d+),', page, 'room id')
|
r'"room_id"\s*:\s*(\d+),', page, 'room id')
|
||||||
|
|
||||||
prefix = 'room/%s?aid=android&client_sys=android&time=%d' % (
|
config = None
|
||||||
room_id, int(time.time()))
|
# Douyu API sometimes returns error "Unable to load the requested class: eticket_redis_cache"
|
||||||
|
# Retry with different parameters - same parameters cause same errors
|
||||||
|
for i in range(5):
|
||||||
|
prefix = 'room/%s?aid=android&client_sys=android&time=%d' % (
|
||||||
|
room_id, int(time.time()))
|
||||||
|
auth = hashlib.md5((prefix + '1231').encode('ascii')).hexdigest()
|
||||||
|
|
||||||
auth = hashlib.md5((prefix + '1231').encode('ascii')).hexdigest()
|
config_page = self._download_webpage(
|
||||||
config = self._download_json(
|
'http://www.douyutv.com/api/v1/%s&auth=%s' % (prefix, auth),
|
||||||
'http://www.douyutv.com/api/v1/%s&auth=%s' % (prefix, auth),
|
video_id)
|
||||||
video_id)
|
try:
|
||||||
|
config = self._parse_json(config_page, video_id, fatal=False)
|
||||||
|
except ExtractorError:
|
||||||
|
# Wait some time before retrying to get a different time() value
|
||||||
|
self._sleep(1, video_id, msg_template='%(video_id)s: Error occurs. '
|
||||||
|
'Waiting for %(timeout)s seconds before retrying')
|
||||||
|
continue
|
||||||
|
else:
|
||||||
|
break
|
||||||
|
if config is None:
|
||||||
|
raise ExtractorError('Unable to fetch API result')
|
||||||
|
|
||||||
data = config['data']
|
data = config['data']
|
||||||
|
|
||||||
|
Loading…
Reference in New Issue
Block a user