至美化爬虫

就先上代码吧。

# 手机壁纸

# 单页版本


import os
import requests
from bs4 import BeautifulSoup


all_in_url = 'https://zhutix.com/mobile/page/1/'

res = BeautifulSoup((requests.get(all_in_url)).text, 'lxml')

all_li = res.findAll('a', class_="imglist-char shu")

all_a = res.findAll('a', class_="imglist-char shu", target="_blank")

print('这一页共有' + str(len(all_li))+'个合集')

name_link = {}
for i in range(len(all_a)):
    aa = all_a[i].getText()
    a = all_li[i]['href']
    cont = name_link[aa] = a

the_num = 0

# 这个页面的所有合集
for value in name_link.values():

    all_imgs = []

    res = BeautifulSoup((requests.get(value)).text, 'lxml')

    img = res.findAll('div', class_="thumbCont")
    all_img = img[0]('img')
    for i in range(len(all_img)):
        all_imgs.append(all_img[i]['url'])

    # 创建文件夹合集对应的 与 适当的提示

    k_key = list(name_link.keys())[list(name_link.values()).index(str(value))]

    the_num += 1

    print('第‖ {} ‖合集『{}』正在解析'.format(the_num, k_key))

    dd = "C:/Users/Administrator/PycharmProjects/2021合集/爬虫/至美化爬虫/手机壁纸/"

    dir = dd + 'imgs/' + str(k_key)
    try:
        if os.path.exists(dir):
            print('Yes')
        else:
            os.mkdir(dir)
    except:
        os.mkdir(dir)

    # 下载图片
    num = 0

    for lin in all_imgs:

        num = num + 1

        name = str(num) + '.jpg'

        name = dir + '/' + name

        r = requests.get(lin)

        try:
            with open(name, "wb") as f:
                f.write(r.content)
                print('{}合集的第{}张下载成功'.format(k_key, num))
        except:
            print("============文件名有误============")
# ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
# 多页版本

import os
import requests
from bs4 import BeautifulSoup

url = 'https://zhutix.com/mobile/'

res = requests.get(url)

bres = BeautifulSoup(res.text, 'lxml')

num = bres.findAll('div', class_="pagination shu")

t_num = len(num[0]('li'))-3

print('共有' + str(t_num) + '页')


for i in range(t_num):



    all_in_url = 'https://zhutix.com/mobile/page/{}/'.format(str(i+1))

    res = BeautifulSoup((requests.get(all_in_url)).text, 'lxml')

    all_li = res.findAll('a', class_="imglist-char shu")

    all_a = res.findAll('a', class_="imglist-char shu", target="_blank")

    print('这一页共有' + str(len(all_li))+'个合集')

    name_link = {}
    for i in range(len(all_a)):
        aa = all_a[i].getText()
        a = all_li[i]['href']
        cont = name_link[aa] = a

    the_num = 0

    # 这个页面的所有合集
    for value in name_link.values():

        all_imgs = []

        res = BeautifulSoup((requests.get(value)).text, 'lxml')

        img = res.findAll('div', class_="thumbCont")
        all_img = img[0]('img')
        for i in range(len(all_img)):
            all_imgs.append(all_img[i]['url'])

        # 创建文件夹合集对应的 与 适当的提示

        k_key = list(name_link.keys())[list(name_link.values()).index(str(value))]

        the_num += 1

        print('第‖ {} ‖合集『{}』正在解析'.format(the_num, k_key))

        dd = "C:/Users/Administrator/PycharmProjects/2021合集/爬虫/至美化爬虫/手机壁纸/"

        dir = dd + 'imgs/' + str(k_key)
        try:
            if os.path.exists(dir):
                print('Yes')
            else:
                os.mkdir(dir)
        except:
            os.mkdir(dir)

        # 下载图片
        num = 0

        for lin in all_imgs:

            num = num + 1

            name = str(num) + '.jpg'

            name = dir + '/' + name

            r = requests.get(lin)

            try:
                with open(name, "wb") as f:
                    f.write(r.content)
                    print('{}合集的第{}张下载成功'.format(k_key, num))
            except:
                print("============文件名有误============")

# ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
# 电脑壁纸

# 直接在手机壁纸多页版本上进行设计

import os
import requests
from bs4 import BeautifulSoup

url = 'https://zhutix.com/wallpaper/'

res = requests.get(url)

bres = BeautifulSoup(res.text, 'lxml')

num = bres.findAll('div', class_="pagination shu")

t_num = len(num[0]('li'))-3

print('共有' + str(t_num) + '页')


for i in range(t_num):

    all_in_url = 'https://zhutix.com/wallpaper/page/{}/'.format(str(i+1))

    res = BeautifulSoup((requests.get(all_in_url)).text, 'lxml')

    all_li = res.findAll('a', class_="imglist-char shu")

    all_a = res.findAll('a', class_="imglist-char shu", target="_blank")

    print('这一页共有' + str(len(all_li))+'个合集')

    name_link = {}
    for i in range(len(all_a)):
        aa = all_a[i].getText()
        a = all_li[i]['href']
        cont = name_link[aa] = a

    the_num = 0

    # 这个页面的所有合集
    for value in name_link.values():

        all_imgs = []

        res = BeautifulSoup((requests.get(value)).text, 'lxml')

        img = res.findAll('div', class_="thumbCont")
        all_img = img[0]('img')
        for i in range(len(all_img)):
            all_imgs.append(all_img[i]['url'])

        # 创建文件夹合集对应的 与 适当的提示

        k_key = list(name_link.keys())[list(name_link.values()).index(str(value))]

        the_num += 1

        print('第‖ {} ‖合集『{}』正在解析'.format(the_num, k_key))

        dd = "C:/Users/Administrator/PycharmProjects/2021合集/爬虫/至美化爬虫/电脑壁纸/"

        dir = dd + 'imgs/' + str(k_key)
        try:
            if os.path.exists(dir):
                print('Yes')
            else:
                os.mkdir(dir)
        except:
            os.mkdir(dir)

        # 下载图片
        num = 0

        for lin in all_imgs:

            num = num + 1

            name = str(num) + '.jpg'

            name = dir + '/' + name

            r = requests.get(lin)

            try:
                with open(name, "wb") as f:
                    f.write(r.content)
                    print('{}合集的第{}张下载成功'.format(k_key, num))
            except:
                print("============文件名有误============")
```
`

目前就这些了。