#这个爬虫非常的好,加入你有一个自考的心态,这个代码可以帮助你爬取学习资料,大大的加快了你的浏览速率,代码还有待提升,
def zikao():
# 爬取湖北省自考考生服务平台的东西---这个可以无限量的爬取
import requests, re
from bs4 import BeautifulSoup
for i in range(0, 2):
link = 'https://www.hbzkw.com/test.aspx?MessageType=&page=' + str(i)
headers = {
'user-agent': 'Mzilla/5.0'
}
r = requests.get(link, headers=headers)
r.encoding = ('utf-8')
soup = BeautifulSoup(r.text, "html.parser")
'''html=etree.HTML(soup.text)
title_list=html.xpath('//ul[@class="tg_list time_list clearfix"]//text()')
print(title_list)'''
# print(soup.a.['href'])
first_title = soup.find_all("ul", class_='tg_list time_list clearfix')
print(