Python学习笔记（五十）爬虫的自我修养（三）爬取漂亮妹纸图

Python学习笔记（五十）爬虫的自我修养（三）爬取漂亮妹纸图

import random
import urllib
from urllib import request
import os

#########################################################
# 参数设置
wsp = 'DouziOOXX'

# 打开连接
def url_open(url):
    req = urllib.request.Request(url)
    req.add_header('User-Agent',
                   'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.78 Safari/537.36')
    response = urllib.request.urlopen(req)
    html = response.read()

    # print(url)
    return html

def get_page(url):
    # 打开链接
    html = url_open(url).decode('utf-8')
    # 查找 current-comment-page
    a = html.find('current-comment-page') + 23
    b = html.find(']', a)   # 从a开始，找到第一个 ], 返回索引
    return html[a:b]


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

    a = html.find('img src=')
    while a != -1:
        b = html.find('.jpg', a, a + 255)
        if b != -1:   # 找到一个 jpg
            img_addrs.append(html[a+9 : b+4])  # 加入列表
        else:         # 到不到, 移动b的位置
            b = a + 9
        a = html.find('img src=', b)  # 在b之后开始，再找img src

    # for each in img_addrs:
    #     print(each)
    return img_addrs

def save_imgs(folder, img_addrs):
    for each in img_addrs:
        filename = each.split('/')[-1]
        # print('http:' + each)
        with open(filename, 'wb') as f:
            img = url_open('http:' + each)
            f.write(img)

def download_mm(folder = wsp, pages = 10):
    os.mkdir(folder)
    # 切换到工作目录
    os.chdir(folder)

    url = "http://jandan.net/ooxx/"
    # 获得页面的地址
    page_num = int(get_page(url))
    for i in range(pages):
        page_num -= i
        # 打开这个地址
        page_url = url + "page-" + str(page_num)
        # 获取图片地址, 保存为一个列表
        img_addrs = find_imgs(page_url)
        # 保存到图片到指定文件夹
        save_imgs(folder, img_addrs)

if __name__=='__main__':
    download_mm()

 

 

 

 

   

 

posted @ 2017-09-23 19:21 douzujun 阅读( ...) 评论( ...) 编辑 收藏