xlwt在爬虫中的实战（爬取豆瓣图书）

爬虫相关知识请阅读我的其他文章

import re
import xlwt
import requests
from bs4 import BeautifulSoupdef getHtml(url):# 构造请求头headers &＃61; {&＃39;User-Agent&＃39;: &＃39;Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:56.0) Gecko/20100101 Firefox/56.0&＃39;}page &＃61; requests.get(url, headers&＃61;headers)html &＃61;page.textreturn htmlif __name__&＃61;&＃61;&＃39;__main__&＃39;:# 创建workbookWorkbook &＃61; xlwt.Workbook()# 创建worksheetsheet &＃61; Workbook.add_sheet(&＃39;豆瓣图书Top250&＃39;, cell_overwrite_ok&＃61;True)sheet.write(0,0,&＃39;书名&＃39;)sheet.write(0,1,&＃39;作者&＃39;)sheet.write(0,2,&＃39;译者&＃39;)sheet.write(0,3,&＃39;出版单位&＃39;)sheet.write(0,4,&＃39;出版时间&＃39;)sheet.write(0,5,&＃39;定价&＃39;)sheet.write(0,6,&＃39;豆瓣评分&＃39;)sheet.write(0,7,&＃39;评价人数&＃39;)sheet.write(0,8,&＃39;一句话&＃39;)i &＃61; 1j &＃61; 1k &＃61; 1m &＃61; 1# 循环翻页for page in range(0,250,25):url &＃61; &＃39;https://book.douban.com/top250?start&＃61;{0}&＃39;.format(page)html &＃61; getHtml(url)# beautiful对象Soup &＃61; BeautifulSoup(html,&＃39;html.parser&＃39;)names &＃61; Soup.find_all(&＃39;div&＃39;,class_ &＃61; &＃39;pl2&＃39;)for name in names:book &＃61; name.find(&＃39;a&＃39;)book &＃61; book.text.strip()book &＃61; book.replace(&＃39; &＃39;,&＃39;&＃39;)sheet.write(i,0,book)i &＃43;&＃61; 1Infos &＃61; Soup.find_all(&＃39;p&＃39;,class_ &＃61; &＃39;pl&＃39;)for Info in Infos:r &＃61; 1authorinfo &＃61; Info.textauthors &＃61; authorinfo.split(&＃39;/&＃39;)if len(authors) < 4:sheet.write(j,1,authors[0])sheet.write(j,2,authors[1])sheet.write(j,3,authors[2])j &＃43;&＃61; 1continuesheet.write(j,1,authors[0])if authorinfo.count(&＃39;/&＃39;) &＃61;&＃61; 4:sheet.write(j,2,authors[r])r &＃43;&＃61; 1sheet.write(j,3,authors[r])sheet.write(j,4,authors[r&＃43;1])sheet.write(j,5,authors[r&＃43;2])j &＃43;&＃61; 1rating_nums &＃61; Soup.find_all(&＃39;div&＃39;,class_ &＃61; &＃39;star clearfix&＃39;)for rating in rating_nums:star &＃61; rating.find_all(&＃39;span&＃39;)sheet.write(k,6,star[1].text)reg &＃61; r&＃39;\d&＃43;&＃39;vote &＃61; re.findall(reg,star[2].text)sheet.write(k,7,vote)k &＃43;&＃61; 1quotes &＃61; Soup.find_all(&＃39;p&＃39;,class_ &＃61; &＃39;quote&＃39;)for quote in quotes:sheet.write(m,8,quote.text)m &＃43;&＃61; 1Workbook.save(&＃39;豆瓣图书Top250.xls&＃39;)