E02 - 带验证码的登录爬取

注意：由于网站升级等原因，各关卡的访问链接会有所变化，请注意修改代码中的url变量。

                # coding=utf-8

import requests
from lxml import etree

url = 'http://spiderbuf.cn/e02/list'

myheaders = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.164 Safari/537.36',
             'Cookie':'admin=d9d5ebe4783beff1f824fd8a7911db57'}

payload = {'username':'admin','password':'123456'}

html = requests.post(url, headers=myheaders, data=payload).text
print(html)

f = open('./data/e02/e02.html', 'w', encoding='utf-8')
f.write(html)
f.close()

root = etree.HTML(html)
trs = root.xpath('//tr')

f = open('./data/e02/data_e02.txt', 'w', encoding='utf-8')
for tr in trs:
    tds = tr.xpath('./td')
    s = ''
    for td in tds:
        # print(td.text)
        s = s + str(td.text) + '|'
    print(s)
    if s != '':
        f.write(s + '\n')

f.close()