爬取彼岸壁纸

import requests

import os

import re

import time

 

url_base = 'http://www.netbian.com'

headers = {

    'User-Agent:':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/112.0.0.0 Safari/537.36',

}

 

# 分析网页结构

# 第1页：http://www.netbian.com/index.htm

# 第3页：http://www.netbian.com/index_3.htm

# 第8页：http://www.netbian.com/index_8.htm

# 第i页：

# f'http://www.netbian.com/index_{i}.htm'

# <p><a href="/desk/30948-1920x1080.htm" target="_blank"><img src="http://img.netbian.com/file/2023/0427/112808gmtzD.jpg" alt="王者荣耀 妲己九尾狐皮肤超清无水印电脑壁纸" title="王者荣耀 妲己九尾狐皮肤超清无水印电脑壁纸"></a></p>

# <p><a href="/desk/30935-1920x1080.htm" target="_blank"><img src="http://img.netbian.com/file/2023/0426/203306JXA7z.jpg" alt="海边 橙色兰博基尼跑车高清电脑壁纸" title="海边 橙色兰博基尼跑车高清电脑壁纸"></a></p>

# <p><a href="/desk/.*?-1920x1080.htm" target="_blank"><img src="(.*?)" alt=".*?" title=".*?"></a></p>


 

# 给爬取到的图片编号命名

num = 1

os.makedirs('./img_bian',exist_ok=True)

# 第1页列表页提取规则

# <li><a href="/desk/30922.htm"title="大海 棕榈树 海滩沙滩 帆船 岛 插图风景 动漫壁纸"

# <li><a href="/desk/30909.htm"title="灌篮高手人物大全图片高清壁纸"

# <li><a href="/desk/30910.htm"title="美女刘亦菲2023年5月日历高清桌面壁纸"

# <li><a href="(.*?)"title=".*?"

# 第2页列表页提取规则

# <li><a href="/desk/30909.htm"title="灌篮高手人物大全图片高清壁纸"

# <li><a href="/desk/30915.htm" title="雪境之森 可爱女孩 白夜极光壁纸 更新时间：2023-04-25"

# 第7页列表页提取规则

# <li><a href="/desk/30674.htm" title="跑车动态壁纸电脑桌面 更新时间：2023-04-04"

# 结论：从第2页开始，列表页提取规则相比第一页,title属性前多了一个空格

 

# 用来实现多页爬取

# 测试用

# for i in range(1,2):

# 正式版

for i in range(1,21):

    if i == 1:

        url_page = 'http://www.netbian.com/index.htm'

        response = requests.get(url_page,headers)

        # print(response.encoding)

        response.encoding = 'gbk'

        # print(response.encoding)

        # 下面调试代码，正式程序中屏蔽

        # with open('./img_bian/彼岸第一页.txt','w',encoding='utf-8') as f:

        #     f.write(response.text)

        pattern = '<li><a href="(.*?)"title=".*?"'

        res_list = re.findall(pattern,response.text)

        # 调试代码，正式版屏蔽

        # print(len(res_list))

        # print(res_list)

        # 爬取22张壁纸图片的详情页响应

        # 测试版

        # for j in range(1):

        # 正式版

        for j in range(len(res_list)):

            url_detail = url_base + res_list[j]

            # print(url_detail)

            response_detail = requests.get(url_detail,headers)

            # 防止乱码，更改编码方式

            response_detail.encoding = 'gbk'

            # 测试用代码，正式版屏蔽

            # with open('./img_bian/第一幅图片网页源代码.txt','w',encoding='utf-8') as f:

            #     f.write(response_detail.text)

            time.sleep(1)

            pattern_detail = '<p><a href="/desk/.*?-1920x1080.htm" target="_blank"><img src="(.*?)" alt=".*?" title=".*?"></a></p>'

            img_url = re.findall(pattern_detail,response_detail.text)[0]

            # print(img_url)

            # 请求图片数据并保存图片

            image_data = requests.get(img_url,headers).content

            print(f'正在下载第{i}页第{num}张图片......')

            time.sleep(1)

            with open(f'./img_bian/{num}.jpg','wb') as file:

                file.write(image_data)

            num = num + 1

    else:

        url_page = f'http://www.netbian.com/index_{i}.htm'

        response = requests.get(url_page,headers)

        # print(response.encoding)

        response.encoding = 'gbk'

        # print(response.encoding)

        # 下面调试代码，正式程序中屏蔽

        # with open('./img_bian/彼岸第2页.txt','w',encoding='utf-8') as f:

        #     f.write(response.text)

        # 不同于第一页有22张图片,从第2页开始每一页只有19张图片,检查其提取规则也有小差别

        pattern = '<li><a href="(.*?)" title=".*?" target="_blank"><img src="'

        res_list = re.findall(pattern,response.text)

        # 调试代码，正式版屏蔽

        # print(len(res_list))

        # print(res_list)

        # 爬取19张壁纸图片的详情页响应

        # 测试版

        # for j in range(1):

        # 正式版

        for j in range(len(res_list)):

            url_detail = url_base + res_list[j]

            # print(url_detail)

            response_detail = requests.get(url_detail,headers)

            # 防止乱码，更改编码方式

            response_detail.encoding = 'gbk'

            # 测试用代码，正式版屏蔽

            # with open('./img_bian/第一幅图片网页源代码.txt','w',encoding='utf-8') as f:

            #     f.write(response_detail.text)

            time.sleep(1)

            pattern_detail = '<p><a href="/desk/.*?-1920x1080.htm" target="_blank"><img src="(.*?)" alt=".*?" title=".*?"></a></p>'

            img_url = re.findall(pattern_detail,response_detail.text)[0]

            # print(img_url)

            # 请求图片数据并保存图片

            image_data = requests.get(img_url,headers).content

            print(f'正在下载第{i}页第{num}张图片......')

            time.sleep(1)

            with open(f'./img_bian/{num}.jpg','wb') as file:

                file.write(image_data)

            num = num + 1