爬取豌豆荚

'''
爬取豌豆荚APP数据
    url：https://www.wandoujia.com/category/6001
    data：
        名称、详情页、下载人数、APP大小
        app_name
        detail_url
        download_num
        app_size
        <a href="" title="" class="">(.*?)</a>.*?<span class="">(.*?)</span>.*?<span title="">(.*?)</span><div class="comment"> (.*?)</div>
'''
import requests
import re


# 1.发送请求
def get_page(url):
    response=requests.get(url)
    return response


def parse_index(html):
    movie_list=re.findall('<h2 class="app-title-h2"><a  href="(.*?)"  title="(.*?)" class="name">.*?</a>.*?<span class="install-count">(.*?)万人安装</span>  <span class="dot">・</span> <span title="(.*?)">.*?MB</span>',
                          html,
                          re.S)
    return movie_list

# 保持数据
def save_data(movie):
    detail_url,app_name,download_num,app_size=movie
    data=f'''
        游戏名称:{app_name}
        详情页url:{detail_url}
        下载人数:{download_num}万人
        APP大小:{app_size}
        \n
        \n
    '''
    print(data)
    with open('wandoujia.text','a',encoding='utf-8')as f:
        f.write(data)

    # print("写入成功！")

if __name__ == '__main__':
        url=f'https://www.wandoujia.com/category/6001'
        print(url)

        index_res=get_page(url)

        movie_list=parse_index(index_res.text)

        for movie in movie_list:
            save_data(movie)

转载于:https://www.cnblogs.com/2328322824chx/p/11129387.html