Python爬虫 requests使用post请求分析并登录Chinaunix

import requests
from lxml import etree

# 使用代理
proxy = {
    'http': '219.149.59.250:9797'
}
# 创建一个会话
s = requests.Session()
# 定制头信息
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.108 Safari/537.36',
}
url = 'http://bbs.chinaunix.net/member.php?mod=logging&action=login&logsubmit=yes'
# 发送get请求
r = s.get(url=url, headers=headers, proxies=proxy)
# 查找formhash值的xpath
formhash_xpath = '//div[@class="form"]//input[@name="formhash"]/@value'
# 创建xpath tree对象
html_tree = etree.HTML(r.text)
# 查找得到formhash值
formhash = html_tree.xpath(formhash_xpath)

# print(formhash)
# 发送post请求进行登录

post_url = 'http://bbs.chinaunix.net/member.php?mod=logging&action=login&loginsubmit=yes&loginhash=LFpXy'
# 抓包分析得到的参数
data = {
    'formhash': formhash,
    'referer': 'http://bbs.chinaunix.net/',
    'username': '17312345678', # 账号
    'password': '123456', # 密码
    'loginsubmit': 'true',
    'return_type': ''
}
headers_post = {
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
    'Accept-Language': 'zh-CN,zh;q=0.9',
    'Connection': 'keep-alive',
    'Content-Type': 'application/x-www-form-urlencoded',
    'Host': 'bbs.chinaunix.net',
    'Origin': 'http://bbs.chinaunix.net',
    'Referer': 'http://bbs.chinaunix.net/member.php?mod=logging&action=login&logsubmit=yes',
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.108 Safari/537.36',
}

r = s.post(url=post_url, data=data, headers=headers_post, proxies=proxy)
r.encoding = 'gbk'
with open('chinaunix.html', 'w') as fp:
    fp.write(r.text)

注意：代码是否执行成功具有时效性