知识点

爬虫的步骤
requests
parsel
xpath数据解析

爬虫四个步骤:

1.获取网页地址 (目标地址)
2.发送请求
3.数据解析
4.保存本地

分析网站

目标网址：https://hdqwalls.com/

网站是静态数据，那么只要找到它的规律，以及url地址就行

代码实现

导入模块

import requests
import parsel

请求数据

url =f'https://hdqwalls.com/latest-wallpapers/page/1'
# url = 'https://hdqwalls.com'
# 请求头  伪装  爬虫:伪装成客户端向服务器发送数据请求
headers = {
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.81 Safari/537.36'
}

requ = requests.get(url=url, headers=headers).text

数据解析

sel = parsel.Selector(requ)  # <Selector xpath=None data='<html lang="en">\n<head>\n<script src="...'>
pic_html = sel.xpath('//body/div/div[3]/div/a[1]/@href').getall()
for html in pic_html:
    pic_html = 'https://hdqwalls.com' + html
    requ2 = requests.get(url=pic_html, headers=headers).text
    sel2 = parsel.Selector(requ2)
    title = sel2.xpath('//body/header/div/div/h1/text()').get().strip()
    href = sel2.xpath('//body/div/div[2]/div/div/div/a/@href').get()
    # 二进制请求
    requ3 = requests.get(url=href, headers=headers).content

保存数据

with open('壁纸\\' + title + '.jpg', mode='wb')as fp:
    fp.write(requ3)
    print(title, '下载完成')

添加翻页后的完整代码

import requests
import parsel


for page in range(1,6):   # 包头不包尾
    url =f'https://hdqwalls.com/latest-wallpapers/page/{page}'
    # url = 'https://hdqwalls.com'
    # 请求头  伪装  爬虫:伪装成客户端向服务器发送数据请求
    headers = {
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.81 Safari/537.36'
    }

    requ = requests.get(url=url, headers=headers).text  # <Response [200]> 数据请求成功
    sel = parsel.Selector(requ)  # <Selector xpath=None data='<html lang="en">\n<head>\n<script src="...'>
    pic_html = sel.xpath('//body/div/div[3]/div/a[1]/@href').getall()
    for html in pic_html:
        pic_html = 'https://hdqwalls.com' + html
        requ2 = requests.get(url=pic_html, headers=headers).text
        sel2 = parsel.Selector(requ2)
        title = sel2.xpath('//body/header/div/div/h1/text()').get().strip()
        href = sel2.xpath('//body/div/div[2]/div/div/div/a/@href').get()
        # 二进制请求
        requ3 = requests.get(url=href, headers=headers).content
        with open('壁纸\\' + title + '.jpg', mode='wb')as fp:
            fp.write(requ3)
            print(title, '下载完成')
    print(f'----------------------第{page}页下载完成----------------------')