import requests
from urllib.request import urlopen, Request
from bs4 import BeautifulSoup
import re
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4183.102 Safari/537.36'
}#爬虫[Requests设置请求头Headers],伪造浏览器
url = "http://www.cfbond.com/cfkx/index.html"
ret = Request(url, headers=headers)
html = urlopen(ret)
bs = BeautifulSoup(html, "html.parser")
div = bs.find("div", {"class": "wrapper"})
ul = div.find("ul")
links = ul.find_all("a")
link_list = []
for link in links:
link = link.get('href')
link_list.append(link)
website = Request(link, headers=headers)
web = urlopen(website)
bs2 = BeautifulSoup(web, "html.parser")
div2 = bs2.find("div", {"class": "s_xlLCont"})
title = div2.find("h1", {"class": "marginBot10"})
body = div2.find("p")
titles = title.get_text(strip=True)
bodies = body.get_text(strip=True)
#print(titles,bodies)
list = "{0:<40}\t{1:<40}".format(titles, bodies, chr(12288))
print(list)
Python爬虫学习之爬取财富快讯
最新推荐文章于 2023-05-22 14:25:36 发布