37,719
社区成员
发帖
与我相关
我的任务
分享
#!/usr/bin/python
# -*- coding: UTF-8 -*-
import requests
import codecs
from bs4 import BeautifulSoup
url = 'http://www.ifanr.com/feed'
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.82 Safari/537.36'}
page = requests.get(url, headers=headers)
page.encoding = 'utf-8'
page_content = page.text
soup = BeautifulSoup(page_content, 'lxml-xml')
items = soup.select('rss > channel > item')
f = codecs.open('d:/ifanr.txt', 'w', 'utf-8')
for i in range(len(items)):
f.write(u'标题:' + items[i].title.text + '\r\n')
f.write(u'内容:' + items[i].description.text + '\r\n')
f.write(u'链接:' + items[i].link.text + '\r\n\r\n')
f.close()