快上车，老司机带你使用Python爬虫抓取知乎网小姐姐美照并保存到本地

2019独角兽企业重金招聘Python工程师标准>>>

# coding=utf-8

import urllib2
from bs4 import BeautifulSoup
import os
import re
import datetime
nowTime=datetime.datetime.now().strftime('%Y%m%d%H%M%S')#现在为了防止图片重名被覆盖，给图片加上时间戳
url = "https://www.zhihu.com/question/268538892"  # 指定的URL


def download(_url, name):  # 下载函数
    if (_url == None):  # 地址若为None则跳过
        pass
    result = urllib2.urlopen(_url)  # 打开链接
    # print result.getcode()
    if (result.getcode() != 200):  # 如果链接不正常，则跳过这个链接
        pass
    else:
        data = result.read()  # 否则开始下载到本地
        with open(name, "wb") as code:
            code.write(data)
            code.close()


res = urllib2.urlopen(url)  # 打开目标地址
respond = res.read()  # 获取网页地址源代码

count =0  # 计数君
soup = BeautifulSoup(respond,"html.parser")  # 实例化一个BeautifulSoup对象
lst = []  # 创建list对象

for link in soup.find_all("img"):  # 获取标签为img的内容
    address = link.get('data-original')  # 获取标签属性为data-original的内容，即图片地址
    lst.append(address)  # 添加到list中

s = set(lst)  # 去重
for address in s:
    if (address != None):
        pathName = "/Users/zhoupeng/Downloads/" + str(count+1) +nowTime+ ".jpg"  # 设置路径和文件名
        download(address, pathName)  # 下载
        count = count + 1  # 计数君+1
        print "正在下载第：", count, "张图片，请耐心等待啊！"
print "------全部图片已经下载完毕--------"

 

转载于:https://my.oschina.net/babyanzichen/blog/1827840