python3爬虫模拟登录_python3爬虫——模拟登录丁香园并提取信息

上一篇：模拟登录QQ邮箱

ps:在进行模拟登录时，输入账号密码后，会弹出验证码，目前还没有解决模拟验证，所以本教程需要进行人工验证。

代码：

from selenium import webdriver

import time

from lxml import etree

#模拟登陆丁香园网站

browser = webdriver.Firefox()

browser.get('https://auth.dxy.cn/accounts/login?service=http://www.dxy.cn/bbs/thread/626626')

time.sleep(1)

browser.find_element_by_xpath('//*[@paneid="j_loginTab2"]').click()

time.sleep(5)

browser.find_element_by_name('username').send_keys('丁香园网站账号')

time.sleep(6)

browser.find_element_by_name('password').send_keys('丁香园网站密码')

time.sleep(3)

browser.find_element_by_xpath('//button[@class= "button"]').click()

time.sleep(18)

#得到所需得到的信息

url = browser.current_url #得到当前网址

browser.get(url)

html = browser.page_source #得到页面的html

tree = etree.HTML(html)

xpath_auth="//div[@class= 'auth']/a/text()"

xpath_level ="//div[@class='user-level-area']"

xpath_score_vote_dingdang="//div[@class='num']/a/text()"

xpath_contect="//td[@class= 'postbody']"

re_auth = tree.xpath(xpath_auth)

re_content = tree.xpath(xpath_contect)

re_three =tree.xpath(xpath_score_vote_dingdang)

re_level=tree.xpath(xpath_level)

#将提取到的信息打印出来

i =1

for auth,content,level in zip(re_auth,re_content,re_level):

print('作者:'+auth,' 级别：'+level.xpath('string(.)'),' 内容：'+content.xpath('string(.)').strip(),end=' ')

print('积分：'+re_three[i],' 得票：'+re_three[i+1],' 丁当：'+re_three[i+2]+'\n')

i = i+1```