day04 爬取豌豆荚app数据的两种方法

今日内容:
方法一 bs4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)
def save_data(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)

 

方法二：requests请求库爬去豌豆荚游戏信息

import requests
import re
# 爬虫三部曲
# 1、发送请求
def get_page(url):
    response = requests.get(url)
    # print(response.text)
    return response
# 2、解析数据
def parse_index(html):
    #关键是写好正则规则
    game_list = re.findall(
        '<li data-pn=".*?" class="card" data-suffix="">.*?<a  href="(.*?)"  >'
        '.*?class="name">(.*?)</a>.*?<span class="install-count">(.*?)万人安装</span>'
        '.*?<span title=".*?">(.*?)MB',
        html,
        re.S)
    return game_list


# 3、保存数据
def save_data(game):

    url,name,download,size = game
    data = f'''
                ======== 欢迎 ========
                    
                        游戏网址:{url}
                        游戏名称:{name}
                        评价人数:{download}万人
                        游戏大小:{size}MB
                ========下次再来哟 ========
                \n
                \n
                '''
    print(data)

    with open('wandoujiagame.txt', 'a', encoding='utf-8') as f:
        f.write(data)

    print(f'游戏: {name} 写入成功...')


if __name__ == '__main__':
        url = f'https://www.wandoujia.com/category/6001'
        # print(url)
        # 1.往每个主页发送请求
        index_res = get_page(url)
        # print(index_res.text)
# 2.解析主页获取信息
        game_list = parse_index(index_res.text)
        print(game_list)
        #
        num=1
        for game in game_list:
            num+=1
            # print(game)
            # 3.保存数据
            save_data(game)

 

转载于:https://www.cnblogs.com/jiangbaoyabo/p/11130468.html