Day04 爬取豌豆荚

今日内容:

    一 爬取豌豆荚







爬取豌豆荚:
    1.访问游戏主页
        https://www.wandoujia.com/category/6001
    2.点击查看更多，观察network内的请求
        - 请求url
            page2:
                https://www.wandoujia.com/wdjweb/api/category/more?
                catId=6001&subCatId=0&page=2&ctoken=vbw9lj1sRQsRddx0hD-XqCNF
            page3:
                https://www.wandoujia.com/wdjweb/api/category/more?
                catId=6001&subCatId=0&page=3&ctoken=vbw9lj1sRQsRddx0hD-XqCNF
            page4:
                https://www.wandoujia.com/wdjweb/api/category/more?
                catId=6001&subCatId=0&page=4&ctoken=vbw9lj1sRQsRddx0hD-XqCNF

    3.循环拼接30个接口

    4.解析返回的数据，获取每一个app数据

''''''

'''
爬取豌豆荚app数据
- 请求url
page2:
https://www.wandoujia.com/wdjweb/api/category/more?catId=6001&subCatId=0&page=2&ctoken=vbw9lj1sRQsRddx0hD-XqCNF
'''
import requests
from bs4 import BeautifulSoup
import re
'''
爬虫三部曲
'''
# 1.发送请求
def get_page(url):
    response = requests.get(url)
    return response

# 2.解析数据
def parse_data(text):
    soup = BeautifulSoup(text, 'lxml')
    # print(soup)
    li_list = soup.find_all(name='li', class_="card")
    # print(li_list)
    for li in li_list:
        # print(li)
        # print('tank' * 100)
        app_name = li.find(name='a', class_="name").text
        # print(app_name)

        app_url = li.find(name='a', class_="name").attrs.get('href')
        # print(app_url)

        download_num = li.find(name='span', class_="install-count").text
        # print(download_num)

        app_size = li.find(name='span', attrs={"title": re.compile('\d+MB')}).text
        # print(app_size)


        app_data = f'''
        游戏名称: {app_name}
        游戏地址: {app_url}
        下载人数: {download_num}
        游戏大小: {app_size}
        \n
        '''
        print(app_data)
        with open('wandoujia.txt', 'a', encoding='utf-8') as f:
            f.write(app_data)
            f.flush()

if __name__ == '__main__':
    for line in range(1, 2):
        url = f'https://www.wandoujia.com/wdjweb/api/category/more?catId=6001&subCatId=0&page={line}&ctoken=vbw9lj1sRQsRddx0hD-XqCNF'
        print(url)
        # 1.发送请求
        # 往接口发送请求获取响应数据
        response = get_page(url)
        # print(response.text)
        # import json
        # json.loads(response.text)
        # print(type(response.json()))
        # print('tank ' * 1000)

        # 把json数据格式转换成python的字典
        data = response.json()

        # print(data['state'])

        # 通过字典取值获取到li文本
        text = data.get('data').get('content')

        # 2.解析数据
        parse_data(text)