爬取大众点评的评论

爬取大众点评的评论

介绍

这个项目是爬取大众点评中，爬取武汉轮渡武汉关码头评论用户的男女和评论时间的代码，代码只能做一个参考，因为我的账号已经被ban了（具体原因可能是我没设置延迟，下面代码中也没有，如果你不会设置，请不要使用），cookie需要自己填写，代理可以找免费的代理，输出格式是csv文件，可以在exsel中另存为xlsx文件

代码

#  -*-coding:utf8 -*-
import requests,re,time,csv

re1 = re.compile(r'href="/member/(?P<href>.*?)".*?data-click-name=.*?data-click-title=.*?>.*?</a>.*?data-click-title="文字".*?>(?P<name>.*?)</a>.*?<div class="misc-info clearfix">.*?<span class="time">(?P<time1>.*?)</span>',re.S)
re2 = re.compile(r'<span class="user-groun"><i class="(?P<sex>.*?)"></i>.*?</span>',re.S)
proxies = {
        "https": "117.69.233.236:8089"
}
headers = {
    "Cookie": "",
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/104.0.0.0 Safari/537.36",
    "Referer": "https://www.dianping.com/shop/l9AxHePS7bRtisgd/review_all/p3",
    "Host": "www.dianping.com"
}
f = open("daz.csv" , mode="w" , encoding='utf-8')
csvwriter = csv.writer(f)
for a in range(110):
    url = f"https://www.dianping.com/shop/l9AxHePS7bRtisgd/review_all/p{a}"
    requests1 = requests.get(url,headers = headers,proxies = proxies)
    # csvwriter.writerow([requests1.text])
    list1 = re1.finditer(requests1.text)
    requests1.close()
    for it in list1:
        href = it.group("href")
        name = it.group("name").strip()
        time1 = it.group("time1").strip()
        url2 = f"https://www.dianping.com/member/{href}"
        requests2 = requests.get(url2,headers = headers,proxies = proxies)
        list2 = re2.finditer(requests2.text)
        for i in list2:
            sex = i.group("sex")
            csvwriter.writerow([ href , name , time1 , sex])
        print(name)
        requests2.close()