From 3117b3a18d09a706ac562c55bdf1f5dca77db767 Mon Sep 17 00:00:00 2001 From: lededev Date: Sun, 6 Mar 2022 17:36:22 +0800 Subject: [PATCH] madou.py:fix get title for MAD039 --- WebCrawler/madou.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/WebCrawler/madou.py b/WebCrawler/madou.py index be0f5b1..0c03cf7 100644 --- a/WebCrawler/madou.py +++ b/WebCrawler/madou.py @@ -17,8 +17,9 @@ def getActorPhoto(html): def getTitle(html, number): # 获取标题 # MD0140-2 / 家有性事EP2 爱在身边-麻豆社 + # MAD039 机灵可爱小叫花 强诱僧人迫犯色戒-麻豆社 browser_title = str(html.xpath("/html/head/title/text()")[0]) - browser_title = browser_title[browser_title.find('/ ') + 2:].strip() + browser_title = browser_title[browser_title.find(' '):].replace('/','').strip() return browser_title[:browser_title.find('-麻豆社')].strip() @@ -161,3 +162,4 @@ def main(number): if __name__ == '__main__': print(main('MD0222')) print(main('MD0140-2')) + print(main('MAD039'))