qiushuidongshi的博客

import requests r=requests.get('https://book.douban.com/') content=r.text 需要解析的主要HTMl # <div class="info"> #               <div class="title"> #                 <a class="" href="htt.

import requests,re,json from requests.exceptions import RequestException from multiprocessing import Pool def get_page_source(url):     headers={ "User-Agent": "Mozilla/5.0 (X11; Linux x86_64) App...

from lxml import etree import requests #获取页面地址 def getUrl():     for i in range(10):      url = 'https://music.douban.com/top250?start={}'.format(i*25)      scrapyPage(url) #爬取每页数据 def scrapyPage(u...