赞
踩
import requests
from fake_useragent import UserAgent
import base64
from lxml import etree
from requests import RequestException
# fake_useragent使用
ua = UserAgent()
def download_page(url):
headers = {
'User-Agent': ua.random,
'Sec - Fetch - Mode': 'no-cors',
'Referer': 'https://piaofang.maoyan.com/?ver=normal'
}
try:
response = requests.get(url=url, headers=headers)
if response.status_code == 200:
return response.content
else:
print(response.status_code)
return None
except RequestException:
print(RequestException.args)
return None
def get_contents(html):
print(html)
def main():
url = 'https://piaofang.maoyan.com/?ver=normal'
html = download_page(url)
get_contents(html)
if __name__ == '__main__':
main()
使用requests.get(url=url, headers=headers)爬取到的网页是美团登录验证的网页,请问怎样才能继续爬取数据
接触爬虫时间不久,所以很多知识不足,请各位大佬指教,提供具体思路就好
谢谢大家,祝大家生活开心
Copyright © 2003-2013 www.wpsshop.cn 版权所有,并保留所有权利。