Python爬取重庆交通大学官网

import requests
from urllib import request
from bs4 import BeautifulSoup
def main():
    url = "http://news.cqjtu.edu.cn/rss.htm"
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36'}
    page = request.Request(url, headers=headers)
    page_info = request.urlopen(page).read()
    soup = BeautifulSoup(page_info, 'html.parser')
    news_titles = soup.select("#ywDiv_0 a")
    news_titles.extend(soup.select("#JxDiv_0 a"))
    news_titles.extend(soup.select("#JDiv_0 a"))
    news_titles.extend(soup.select("#JKDiv_0 a"))
    print(type(news_titles))
    for news in news_titles:
        #print(news)
        title = news.get_text()
        link = news.get("href")
        data = {"title": title, "link": "http://news.cqjtu.edu.cn"+link}
        print(data)
main()