import re import time import requests from lxml import etree #爬某豆瓣读书 Top 250 #浏览器的代理 #在网址上输入about://version 浏览器的代理 cz={'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/104.0.5112.102 Safari/537.36 Edg/104.0.1293.70'} io=0 def zxc(): #遍历网页 # zxc_lp='https://book.douban.com/top250?start='+str(io) asd=requests.get('https://book.douban.com/top250?start=225',headers=cz).text qwe=etree.HTML(asd) c='//*[@valign="top"]/p/text()' #书名 lp11='//*[@class="star clearfix"]/span[2]/text()' #作者,出版社,日期, lp111='//*[@class="star clearfix"]/span[3]/text()'#多少人评价 lp1111='//*[@class="inq"]/text()'#名句 lp11111='//*[@class="nbg"]/img/@src'##图片 asd1=qwe.xpath('//*[@class="pl2"]/a/@title') lp=qwe.xpath(c) lp1=qwe.xpath(lp11) lp12=qwe.xpath(lp111) lp13=qwe.xpath(lp1111) lp14=qwe.xpath(lp11111) # 去除空格和换行 zxc33=[str(i1).strip() for i1 in lp if str(i1).strip()!=''] qwe=[str(i2).strip() for i2 in asd1 if str(i2).strip()!=''] qwe11=[str(i4).replace(' ','').split('\n') for i4 in lp12] #['(', # '66963人评价' # , ')'] '替换空格 位 空 在删除换行之后' # ['(', '66963人评价', ')'] for a1,a2,a3,a4,a5,a6 in zip(qwe,zxc33,lp1,qwe11,lp13,lp14): print(f'作者:{a1},作者,出版社,日期:{a2},评分:{a3} ,评价{a4},名句:{a5} 图片地址:'+str(a6)) zxc()
标签:xpath,text,qwe,爬虫,某豆,str,排行,import,class From: https://www.cnblogs.com/xxh12/p/16641774.html