Python——大众点评评论爬虫代码

评论链接

 

  放入excel(negkey)中的内容  1 # -*- coding: utf-8 -*-

 2 """
 3 Created on Thu Aug 16 14:52:09 2019  4 需要爬虫服务可以联系Q：2960389193 
 6 """
 7 #好评链接：http://www.dianping.com/shop/2044996/review_all/p2?queryType=reviewGrade&queryVal=good
 8 #差评链接：http://www.dianping.com/shop/2044996/review_all/p2?queryType=reviewGrade&queryVal=bad
9 
10 
11 import requests 12 from lxml import etree 13 import xlrd 14 import random 15 import time 16 
17 data = [] 18 def Comments(url): 19     
20     headers = {‘Accept‘: ‘text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8‘, 21                ‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.75 Safari/537.36‘, 22                ‘Cookie‘: ‘浏览器获取的cookie‘
23  } 24     #url = ‘http://www.dianping.com/shop/19110508/review_all?queryType=reviewGrade&queryVal=bad‘
25     resp = requests.get(url,headers=headers) 26 
27     #print (resp.content.decode(‘utf-8‘))#查看爬取网页代码，代码中文内容用二进制表示，故print时要decode
28 
29     comments = etree.HTML(resp.text,parser=etree.HTMLParser(encoding=‘utf-8‘)) 30     commentlong = comments.xpath(‘//div[@class="review-words Hide"]‘)#长评
31     commentshort = comments.xpath(‘//div[@class="review-words"]‘)#短评
32     for l in commentlong: 33         data.append(l.xpath(‘string(.)‘).replace("\t","").replace("\n","").replace(" ","").replace("收起评论","").encode(‘gbk‘,‘ignore‘).decode(‘gbk‘)) 34     #把不需要的字符清除，可以用split()去掉\xa0，\t，\n，但是句子会被拆分成一个列表，不方便后续使用
35     for s in commentshort: 36         data.append(s.xpath(‘string(.)‘).replace("\t","").replace("\n","").replace(" ","").encode(‘gbk‘,‘ignore‘).decode(‘gbk‘)) 37 
38 def getComments(): 39     path = ‘D:/anaconda/shirleylearn/dazhongdianping/negkey.xlsx‘#抓取关键字
40     excelfile = xlrd.open_workbook(path) 41     keys = excelfile.sheet_by_name(‘Sheet1‘) 42     n = keys.nrows 43     for i in range(0,n): 44         key = int(keys.row(i)[0].value) 45         for page in range(1,int(keys.row(i)[1].value)+1): 46             url = ‘http://www.dianping.com/shop/%d/review_all/p%d?queryType=reviewGrade&queryVal=bad‘%(key,page)#拼链接，修改bad,good即为差评和好评
47             #print(url)
48  Comments(url) 49  time.sleep(random.random()) 50 
51 if __name__ == "__main__": 52  getComments() 53     print (len(data)) 54     with open(‘neg.txt‘,‘w‘) as f:#把评论放入txt,好评改为pos.txt
55         for k in data: 56             f.write(k)

抓取结果展示   爬一次IP就被封了 o(╥﹏╥)o