初识Python爬妹子图片

 

1、地址

http://www.jder.net/meizi/

 

代码：

 

#!/usr/bin/python3.6  
# -*- coding: utf-8 -*- 

import requests
from bs4 import BeautifulSoup
import codecs
import time
import os.path

# 伪装成浏览器进行登录

headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:61.0) Gecko/20100101 Firefox/61.0"}
def download_page(url):
   r = requests.get(url, headers=headers)  # 增加headers, 模拟浏览器
   return  r.text

def download_pic(imgUrl):
  r = requests.get(imgUrl,headers=headers)
  return r.content

def getFilePath(title,link):
  pic =  './/pic'
  if not os.path.exists(pic):
    os.makedirs(pic)
    pass
  return pic + '/{}.{}'.format(title,link.split('.')[-1])

def get_content(html):
   soup = BeautifulSoup(html, 'html.parser')
   main_ll = soup.find_all('div',class_='picture-box')
   for ll in main_ll:
    a_tag = ll.find(class_='picture-img').find('a')
    img = a_tag.find('img')

    link = img.get('src')
    start = link.find('=') + 1
    end = link.find('&')
    realLink = link[start:end]

    title = img.get('alt')
    r = download_pic(realLink)

    filepath = getFilePath(title,realLink)

    with open(filepath,'wb') as f:
      f.write(r)
      time.sleep(1)


def main():
       url = 'http://www.jder.net/meizi/'
       html = download_page(url)
       get_content(html)


if __name__ == '__main__':
   main()

 

附：

BeautifulSoup 使用文档：

https://www.crummy.com/software/BeautifulSoup/bs4/doc.zh/#