- 爬取搜狐主页标题和对应网址
import re
import requests
resp = requests.get(
url='https://www.sohu.com/',
headers={'User-Agent': 'Mozilla/5.0 (Windows '
'NT 10.0; Win64; x64) '
'AppleWebKit/537.36 (KHTML, like Gecko)'
' Chrome/88.0.4324.150 Safari/537.36'
}
)
# print(resp.text)
re_str = re.compile(r'\<a.+?href="\/?\/?(.+?)".+?title=[\'\"](.+?)[\'\"]\>')
result = re_str.findall(resp.text)
for x in result:
print(x[1])
print(x[0])