老套的爬图片实例，陆续写了几天，不容易，终于出来了。

难点有：分别为图片创建文件夹，爬取时不惧怕防盗链。

没有定义函数 比较难看，哈哈

from bs4 import BeautifulSoup
import requests
import urllib.request
import os
import re



website = "http://www.sucaibar.com/image/meinv/"
web_data = requests.get(website)
soup = BeautifulSoup(web_data.text,'lxml')
urls= soup.select('#pic-list > li > a')

url_list = []
for url in urls:
    url_list.append(url.get('href'))
print(url_list)

for url in url_list:


    web_data = requests.get(url)
    soup = BeautifulSoup(web_data.text,'lxml')
    links= soup.select('body > div.content > div.col-main > div > div.gbox.sucai-detail > div > div > div > a')
    folder_name = soup.title.string.replace('_美女图片_素材吧', '')
    print(links)


    folder_path = "C:/ChromeDL/Pics/" + str(folder_name) + "/"
    if not os.path.exists(folder_path):  # 路径不存在时创建一个
        os.makedirs(folder_path)
    print(folder_path)

    download_links = []
    for link in links:
        imageURL = link.get('href')
        download_links.append(link.get('href'))
    print(download_links)

    for item in download_links:
        opener = urllib.request.build_opener()
        opener.addheaders = [('User-agent', 'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/46.0.2490.76 Mobile Safari/537.36')]
        urllib.request.install_opener(opener)
        urllib.request.urlretrieve(item,folder_path + item.split('/')[-1])

运行结果如下：