From 88cef56870cd3f30aa69c9b49e5a5c9a4b59791d Mon Sep 17 00:00:00 2001 From: yoshiko2 Date: Fri, 4 Jun 2021 01:27:02 +0800 Subject: [PATCH] Fix source avsox --- WebCrawler/avsox.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/WebCrawler/avsox.py b/WebCrawler/avsox.py index 9230ecf..254f3e8 100644 --- a/WebCrawler/avsox.py +++ b/WebCrawler/avsox.py @@ -96,7 +96,7 @@ def main(number): a = get_html(site + '/cn/search/' + number.replace('_', '')) html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() result1 = str(html.xpath('//*[@id="waterfall"]/div/a/@href')).strip(" ['']") - web = get_html(result1) + web = get_html("https:" + result1) soup = BeautifulSoup(web, 'lxml') info = str(soup.find(attrs={'class': 'row movie'})) try: @@ -116,7 +116,7 @@ def main(number): 'label': getLabel(info), 'year': getYear(getRelease(info)), # str(re.search('\d{4}',getRelease(a)).group()), 'actor_photo': getActorPhoto(web), - 'website': result1, + 'website': "https:" + result1, 'source': 'avsox.py', 'series': getSeries(info), }