python爬虫爬取煎蛋网妹子图片

import urllib.request
import os

def url_open(url):
    req = urllib.request.Request(url)
    req.add_header("User-Agent","Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:54.0) Gecko/20100101 Firefox/54.0")
    response = urllib.request.urlopen(url)
    html = response.read()
    return html

def get_page(url):
    html = url_open(url).decode("utf-8")

    a = html.find("current-comment-page") + 23
    b = html.find(']',a)
    return html[a:b]

def find_imgs(page_url):
    html = url_open(page_url).decode("utf-8")
    img_addrs = []

    a = html.find("img src=")

    while a!=-1:
        b = html.find(".jpg",a,a+255)
        if b!=-1:
            img_addrs.append(html[a+9:b+4])
        else:
            b = a+9
        a = html.find("img src",b)
    return img_addrs
def save_imgs(folder,img_addrs):
    for each in img_addrs:
        filename = each.split('/')[-1]
        with open(filename,'wb') as f:
            each = "http:"+each
            img = url_open(each)
            f.write(img)

def download_mm(folder="mm",pages=10):
    os.mkdir(folder)
    os.chdir(folder)

    url = "http://jandan.net/ooxx/"
    page_num = int(get_page(url))

    for i in range(pages):
        page_num -= i
        page_url = url + 'page-' + str(page_num) + "#comments"
        img_addrs = find_imgs(page_url)
        save_imgs(folder,img_addrs)
download_mm()

将url_open函数修改，使用代理会出错：

def url_open(url):
    req = urllib.request.Request(url)
    req.add_header("User-Agent","Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:54.0) Gecko/20100101 Firefox/54.0")

    proxies = ['221.237.122.22:8118','171.37.192.220:8123','110.73.0.59:8123','171.39.4.208:8123']
    proxy = random.choice(proxies)

    proxy_support = urllib.request.ProxyHandler({'http':proxy})
    opener = urllib.request.build_opener(proxy_support)
    urllib.request.install_opener(opener)

    response = urllib.request.urlopen(url)
    html = response.read()
    return html