From 9335b446f955e3d783d3665fec666f0ac67a9369 Mon Sep 17 00:00:00 2001 From: Feng4 Date: Sat, 26 Dec 2020 23:39:57 +0800 Subject: [PATCH] Update airav.py --- WebCrawler/airav.py | 100 ++++++++++++++++++++++++-------------------- 1 file changed, 55 insertions(+), 45 deletions(-) diff --git a/WebCrawler/airav.py b/WebCrawler/airav.py index 9a13cec..58263a2 100644 --- a/WebCrawler/airav.py +++ b/WebCrawler/airav.py @@ -110,56 +110,65 @@ def getTag(htmlcode): # 获取标签 tag.append(i.get_text()) return tag +def getExtrafanart(htmlcode): # 获取剧照 + html_pather = re.compile(r'
[\s\S]*?
') + html = html_pather.search(htmlcode) + if html: + html = html.group() + extrafanart_pather = re.compile(r'