day03 爬豌豆荚

'''
主页:
    名称、下载次数、大小、详情页地址


https://www.wandoujia.com/wdjweb/api/category/more?catId=6001&subCatId=0&page=1&ctoken=FRsWKgWBqMBZLdxLaK4iem9B

https://www.wandoujia.com/wdjweb/api/category/more?catId=6001&subCatId=0&page=2&ctoken=FRsWKgWBqMBZLdxLaK4iem9B

https://www.wandoujia.com/wdjweb/api/category/more?catId=6001&subCatId=0&page=3&ctoken=FRsWKgWBqMBZLdxLaK4iem9B
'''

import requests
from bs4 import BeautifulSoup
# 1、发送请求
def get_page(url):
    response = requests.get(url)
    return response

# 解析主页
def parse_index(data):
    soup = BeautifulSoup(data, 'lxml')

    # 获取所有app的li标签
    app_list = soup.find_all(name='li', attrs={"class": "card"})
    for app in app_list:

        app_name = soup.find(name="a", attrs={"class": "name"}).text
        print(app_name)

        # 下载次数
        # 获取class为install-count的span标签中的文本
        down_num = app.find(name='span', attrs={"class": "install-count"}).text
        print(down_num)

        import re
        # 大小
        # 根据文本正则获取到文本中包含 数字 + MB（\d+代表数字）的span标签中的文本
        size = soup.find(name='span', text=re.compile("\d+MB")).text
        print(size)

        # 详情页地址
        detail_url = app.find(name='a').attrs['href']
        print(detail_url)


def main():
    for line in range(1, 33):
        url = f"https://www.wandoujia.com/wdjweb/api/category/more?catId=6001&subCatId=0&page={line}&ctoken=FRsWKgWBqMBZLdxLaK4iem9B"

        # 1、往app接口发送请求
        response = get_page(url)

        print('*' * 1000)
        # 反序列化为字典
        data = response.json()

        # 获取接口中app标签数据
        app_li = data['data']['content']
        # print(app_li)
        # 2、解析app标签数据
        parse_index(app_li)


if __name__ == '__main__':
    main()

标签：name,day03,app,find,url,print,page,豌豆荚
来源： https://www.cnblogs.com/cl007/p/11127872.html