Python学习第五天

简单的爬取一个网页的信息

1.需要做好访问用户的返回信息，防止被认出是爬虫
2.找好想要爬取的网站
3.找准想要爬取信息的位置

import requests

导入extree模块

from lxml import html
etree = html.etree

game_list_info = []
def spider_guaishou_top12():
    headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.80 Safari/537.36"}

    url = 'https://www.apk8.com/zt/zt_1604.html'
    #获取bytes类型响应（二进制）
    data = requests.get(url, headers=headers).content
    html = etree.HTML(data)
    yemian_list = html.xpath('//div[@id="zl"]/div[1]/div[@class="sli_item"]')

    for game in yemian_list:
        #游戏名
        game_name = game.xpath('./a[2]/text()')[0]
        print(game_name)
        #游戏类型
        game_type = game.xpath('./p[1]/a/text()')[0]
        print(game_type)
        #游戏大小
        game_size = game.xpath('./p[1]/text()')[1].strip()
        game_size = game_size.replace('/ ', '')
        print(game_size)
        #游戏下载链接
        game_interlinkage = game.xpath('./p[@class="sli_btn"]/a/@href')[0]
        print('游戏下载链接：{}'.format(game_interlinkage))
        #游戏图片地址
        game_picture = game.xpath('./a[1]/img/@src')[0]
        print('游戏图片地址：{}'.format(game_picture))

将爬取到的信息集合到一起

        game_list_info.append({
            'game_name':game_name,
            'game_type':game_type,
            'game_size':game_size,
            'game_interlinkage':game_interlinkage,
            'game_picture':game_picture
        })

将图片下载到本地的imgs文件夹下

    for game in game_list_info:
        url = game['game_picture']
        resp = requests.get(url)
        if resp.status_code == 200:
            img_name = '{}.jpg'.format(game['game_name'])
            with open('./imgs/{}'.format(img_name), 'wb') as f:
                f.write(resp.content)

spider_guaishou_top12()

这是爬取到的游戏的封面

image.png