还望有能力的高手完善下在发布,比如代理,随机ua,优化下。Windows7跟乌班图测试通过。树莓派跑不起来,不知道为什么。

python3.5环境

  • #! /usr/bin/python3
  • # -- coding:utf-8 --
  • - import requests
  • import re
  • from bs4 import BeautifulSoup
  • import time
  • class Mymm():
  • def __init__(self, url):
  • self.url = url
  • header = {'User-Agent':'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50',
  • 'Referer':'http://www.souutu.com/mnmm/ ',
  • 'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,/;q=0.8',
  • 'Accept-Encoding':'gzip, deflate, sdch',
  • 'Connection':'keep-alive',
  • 'Cache-Control':'max-age=0',
  • 'Host':'www.souutu.com',
  • 'Upgrade-Insecure-Requests':'1'}
  • - index = requests.get(self.url, headers=header) # 获取网页源码
  • time.sleep(4)
  • bs = BeautifulSoup(index.content, 'html5lib')
  • load_img = bs.find(attrs={'class':'sumlist'})
  • g_num = load_img.find_all('a')
  • num = re.search(r'\d{3}', g_num[-1].text).group() # 得到一共有多少个页面
  • - for page in range(1, int(num) + 1):
  • if page == 1:
  • load_img = bs.find(id='load-img')
  • ul_img = load_img.find_all(attrs={'class':'timg'})
  • # 将得到的连接跟图片的张数
  • for link in ul_img:
  • href = link.find('a').get('href')
  • url = re.findall(r'(http://www.souutu.com/mnmm/.+)', href)
  • img_num = re.findall(r'([1-9])', link.find('span').text)
  • print(url, img_num)
  • self.get_link(''.join(url), ''.join(img_num))
  • else:
  • page_url = r'http://www.souutu.com/mnmm/index_' + str(page) + '.html' # 根据页数生成页面URL
  • page_index = requests.get(page_url, headers=header)
  • bs = BeautifulSoup(page_index.content, 'html5lib')
  • load_img = bs.find(id=r'load-img')
  • ul_img = load_img.find_all(attrs={'class':'timg'})
  • url = []
  • img_num = []
  • for link in ul_img:
  • href = link.find('a').get('href')
  • url = re.findall(r'(http://www.souutu.com/mnmm/.+)', href)
  • img_num = re.findall(r'([1-9])', link.find('span').text)
  • self.get_link(''.join(url), ''.join(img_num)) # 将url跟图片的张数转换成str,方便传入dict
  • def get_link(self, url, img_num):
  • self.url = url
  • self.img_num = img_num
  • dict = {self.url:self.img_num} # 将url跟图片张数一一对应
  • page = 0
  • for k, v in dict.items():
  • content = requests.get(k).content
  • time.sleep(4)
  • bs = BeautifulSoup(content, 'html5lib')
  • getimg_all = bs.find(attrs={'class':'cl gallery'})
  • get_imgurl = re.findall(r'()(. )(d{17}.jpg)', str(getimg_all))
  • for g in get_imgurl:
  • gg = g[0] + g[2]
  • print(gg)
  • self.save_img(gg)
  • def save_img(self, get_imgurl):
  • self.get_imgurl = get_imgurl
  • save = open('mm.txt', 'a')
  • for w in self.get_imgurl:
  • save.write(w)
  • save.write('\n')
  • save.close()
  • - mm = Mymm(r'http://www.souutu.com/mnmm/')复制代码