day03 爬取豌豆荚

时间:2021-03-23 20:12:28
from bs4 import BeautifulSoup
import requests
#请求url https://www.wandoujia.com/category/6001
#请求方式: get

def have_title(tag):
    if tag.name == 'span' and tag.has_attr("title"):
        return tag

#获取网页
def get_page(url):
    index_res = requests.get(url)
    return index_res
#解析网页
def parse_detail(html):
    soup = BeautifulSoup(html,'lxml')
    list = soup.find_all(name='li',class_='card')

    data = ""
    for i in list:
        app_name = i.a.img.attrs['alt']
        detail_url = i.a.attrs['href']
        download_num = i.find(name='div',class_='meta').find(class_='install-count').text
        app_size =  i.find(name='div',class_='meta').find(have_title).text
        data += f"""
              名称      : {app_name}
              详情页url : {detail_url}
              下载人数  : {download_num}
               app大小  : {app_size}
                
                """
    return data

#保存数据
def save_games(data):
    with open('games.txt','w',encoding='utf-8') as f:
        f.write(data)

if __name__ == '__main__':
    url = 'https://www.wandoujia.com/category/6001'
    index_res = requests.get(url)
    index_detail = index_res.text
    data = parse_detail(index_detail)
    save_games(data)