import re
import requests
url = "https://www.xbiquge.la/"
def getbook(url):
dic = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.101 Safari/537.36 Edg/91.0.864.48"
}
get_url =requests.get(url,headers=dic)
get_url.encoding='utf-8'
page_content = get_url.text
obj =re.compile(
r'<div class="item">.*?<span>(?P<name>.*?)</span>'
r'<a href="(?P<href>.*?)">'
r'(?P<shuming>.*?)</a></dt>.*?'
r'<dd>(?P<jieshao>.*?)</dd>',re.S)
result =obj.findall(page_content)
for it in result:
print(it)
print(it.group("name"))#这里用不了group
getbook(url)