爬虫_获取壁纸

#https://www.4kbizhi.com/

import requests
from bs4 import BeautifulSoup
import re
import time

‘‘‘
获取源网页
‘‘‘
header = {‘user-agent‘:"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36",}
url = ‘‘

for i in range(1,20):
    print(‘开始第%d页‘%i)
    if i == 1:
        source_page = requests.get(url + ‘index.html‘, headers=header)
    else:
        source_page = requests.get(url + ‘index_‘ + str(i) + ‘.html‘, headers=header)
    source_page = source_page.text.encode(‘iso-8859-1‘).decode(‘gbk‘)

    ‘‘‘
    解析源网页，获取地址
    ‘‘‘
    soup = BeautifulSoup(source_page)
    a = 0
    pattern = re.compile(‘s[a-z]+.+jpg‘)
    pattern_follow = re.compile(‘[0-9]{6}[a-zA-Z0-9]{5}‘)
    print(time.time())
    for item in soup.find_all(‘a‘):
        link = re.findall(pattern,str(item))
        title = item.get_text()
        link_follow = re.findall(pattern_follow,str(item))
        a += 1
        if link:
            #对获取的地址拆分和拼接
            link_str = link[0]
            adder = link_str.split(‘"‘)
            adder = adder[1].split(‘small‘)
            pic = (url + adder[0] + link_follow[0] + ‘.jpg‘)
            #获取图片地址
            img = requests.get(pic)
            ‘‘‘
            将图片写入指定的目录D:\壁纸\imgs\
            ‘‘‘
            with open(r"D:\壁纸\imgs\\" + title + str(a) + ‘_‘ + str(i) + ".jpg",‘wb‘) as f:
                f.write(img.content)
                print(title + str(a) + ‘...200‘)
            f.close()
    print(‘第%d页结束‘%i)
    print(time.time())

爬虫_获取壁纸

原文：https://www.cnblogs.com/jion/p/14807634.html