python爬虫下载壁纸图片

有疑问可以回复我，共同交流学习。

 

#!/usr/bin/env python
# -*- coding:utf-8 -*- 
#Author: ss

from bs4 import BeautifulSoup
import requests
import time
import random
import os

my_headers = [
    "Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/35.0.1916.153 Safari/537.36",
    "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:30.0) Gecko/20100101 Firefox/30.0"
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_2) AppleWebKit/537.75.14 (KHTML, like Gecko) Version/7.0.3 Safari/537.75.14",
    "Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.2; Win64; x64; Trident/6.0)"

    ]


headers = {
    'User-Agent':random.choice(my_headers)
}


def Downloads(url,abc,title1):
    data = requests.get(url,headers=headers)
    time.sleep(1)
    with open('.\\壁纸\\' + title1 + '\\' + str(abc) + '.jpg','wb+') as f:
        f.write(data.content)


def get_image(url,abc,title1):
    #url = 'http://desk.zol.com.cn/showpic/1366x768_89338_102.html'
    data = requests.get(url, headers=headers)
    soup = BeautifulSoup(data.text, 'lxml')
    url = soup.select('img')[0].get('src')
    print('正在下载{}第{}张'.format(title1, abc))
    Downloads(url,abc,title1)


def get_image_url(url,abc):
    #url = 'http://desk.zol.com.cn/bizhi/7254_89744_2.html'
    data = requests.get(url,headers=headers)
    soup = BeautifulSoup(data.text,'lxml')
    time.sleep(2)
    url = 'http://desk.zol.com.cn' + soup.select('dd#tagfbl > a#1366x768')[0].get('href')
    title1 = soup.select('a#titleName')[0].text
    if not os.path.exists('.\\壁纸\\' + title1):
        os.mkdir('.\\壁纸\\' + title1)
    get_image(url,abc,title1)


def get_one_urls(url):
    #url = 'http://desk.zol.com.cn/bizhi/7211_89338_2.html'
    data = requests.get(url,headers=headers)
    soup = BeautifulSoup(data.text,'lxml')
    urlss = soup.select('div.photo-list-box > ul.clearfix')
    title1 = soup.select('a#titleName')[0].text
    print('正在下载{}'.format(title1))
    abc = 0
    for urls in urlss:
        urls = urls.select('li > a')
        for url in urls:
            try:
                url = 'http://desk.zol.com.cn' + url.get('href')
                time.sleep(1)
                abc += 1
                get_image_url(url,abc)
            except:
                continue



def get_urls(url):
    #url = 'http://desk.zol.com.cn/fengjing/1366x768/'
    data = requests.get(url,headers=headers)
    soup = BeautifulSoup(data.text.encode('ISO-8859-1').decode('GB18030'),'lxml')
    urls = soup.select('li.photo-list-padding > a')
#titles = soup.select('li.photo-list-padding > a.pic > span > em')
#urls = soup.select('body > div.wrapper.top-main.clearfix > div.main > ul > li > a')[0].get('href')
    for url in urls:
        try:
            time.sleep(1)
            url = 'http://desk.zol.com.cn' + url.get('href')
            get_one_urls(url)
        except:
            continue


def urls():
    for i in range(10):
        try:
            url = 'http://desk.zol.com.cn/fengjing/1366x768/' + str(i) + '.html'
            time.sleep(1)
            get_urls(url)
        except:
            continue


urls()