爬虫入门-爬取华为应用商店app的评论

最新推荐文章于 2025-02-08 12:47:03 发布

一只干测试的兔子

最新推荐文章于 2025-02-08 12:47:03 发布

阅读量978

点赞数 6

文章标签：爬虫

本文链接：https://blog.csdn.net/norma_chai/article/details/144109888

版权

直接上代码
import csv
import random
import requests

#appid可以替换成你要爬取的app的appid
url='https://web-drcn.hispace.dbankcloud.com/edge/uowap/index?method=internal.user.commenList3&serviceType=20&reqPageNum=%s&maxResults=25&appid=C10219077&version=10.0.0&zone=&locale=zh'


def get_agent():
    agents= ['Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0;',
    'Mozilla/5.0 (Macintosh; Intel Mac os x 10.6; rv,2.0.1) Gecko/20100101 Firefox/4.0.1',
    'Opera/9.80 (Macintosh; Intel Mac os x 10.6.8; U; en) Presto/2.8.131 Version/11.11',
    'Mozilla/5.0(Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11(KHTML,like Gecko)Chrome/17.0.963.56Safari/535.11',
    'Mozilla/4.0 (compatible; MsIE 7.0; Windows NT 5.1; 360SE)']
    fakeheader = {}
    a=random.randint(0,len (agents)-1)
    fakeheader['user-agent'] = agents[a]
    return fakeheader


csv_file = '../csv/华为应用商店评论.csv'
for i in range(5,10):
    with open(csv_file, mode='a', newline='', encoding='utf-8') as file:
        writer = csv.writer(file)
        response = requests.get(url%i,timeout=30,headers=get_agent())
        # 检查请求是否成功
        if response.status_code == 200:
            # 解析HTML内容
            comment_list=response.json()["list"]
            if comment_list ==[]:
                break
            for comment in comment_list:
                aa=comment["commentInfo"]
                #爬取到的评论写入csv文件
                writer.writerow(["智能证件照",aa])
        else:
            break