diff --git a/src/you_get/extractors/douyutv.py b/src/you_get/extractors/douyutv.py index 0292c94e..1dde4141 100644 --- a/src/you_get/extractors/douyutv.py +++ b/src/you_get/extractors/douyutv.py @@ -8,11 +8,11 @@ import json def douyutv_download(url, output_dir = '.', merge = True, info_only = False): html = get_html(url) - room_id_patt = '"room_id":(\d{1,99}),' - title_patt = '([^<]{0,1000})' + room_id_patt = r'"room_id":(\d{1,99}),' + title_patt = r'
\s*

([^<]{1,9999})

\s*
' roomid = re.findall(room_id_patt,html)[0] - title = re.findall(title_patt,html)[0] + title = unescape_html(re.findall(title_patt,html)[0]) conf = get_html("http://www.douyutv.com/api/client/room/"+roomid) metadata = json.loads(conf)