豌豆荚

''''''
'''
一、请求url
https://www.wandoujia.com/category/6001
二、请求方式
三、请求头
'''
#爬虫三部曲
#1.发送请求
import requests
def get_page(url):
    reponse = requests.get(url)
    #print(reponse.text)
    return reponse
# 2.解析数据
'''

<a href="(.*?)" title="捕鱼大作战" class="name">(.*?)</a></h2><div class="meta">    <span class="install-count">(.*?)</span> .*?<span title="37.31MB">(.*?)</span>

</div><div class="app-desc"><h2 class="app-title-h2"><a  href="https://www.wandoujia.com/apps/com.tuyoo.fish.uc"  title="捕鱼大作战" class="name">捕鱼大作战</a></h2><div class="meta">    <span class="install-count">13.9万人安装</span>  <span class="dot">・</span> <span title="37.31MB">37.31MB</span></div><div class="comment">  捕鱼大作战，经典街机新体验  </div></div>   <a class="tag-link" href="https://www.wandoujia.com/category/6001?pos=w/cardtag/gamecategory_com.tuyoo.fish.uc">休闲益智</a>   
'''
import re
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">.*?MB</span>',html,re.S)
    return movie_list


# 3.保存数据
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}MB
                \n
                \n
            '''
    print(data)
    with open('wandoujia.txt','a',encoding='utf-8') as f:
        f.write(data)


if __name__ == '__main__':
    #拼接所有主页
        url=f'https://www.wandoujia.com/category/6001'
        #1.往每个主页发送请求
        index_res = get_page(url)
        #2.解析主页获取电影信息
        movie_list = parse_index(index_res.text)

        for movie in movie_list:
            #3.保存数据
            #print(movie_list)
            save_data(movie)