利用Python爬去囧网福利(多线程、urllib、request)

import os;
import urllib.request;
import re;
import threading;# 多线程
from urllib.error import URLError#接收异常‘s 模块


#获取网站的源码
class QsSpider:
    #init 初始化构造函数 .self本身
    def __init__(self):
      self.user_agent=‘Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.84 Safari/537.36‘
      self.header = {‘User-Agent‘:self.user_agent}
      self.url = ‘http://www.qiubaichengren.net/%s.html‘
      self.save_dir = ‘./img‘
      self.page_num = 20  #page num
#获取网站源代码
    def load_html(self,page):
        try:
            web_path = self.url % page
            request = urllib.request.Request(web_path,headers=self.header)
            with urllib.request.urlopen(request) as f:
                html_content = f.read().decode(‘gbk‘)
                #print(html_content)
                self.pick_pic(html_content)
        except URLError as e :
            print(e.reason) #异常原因
    #download
    def sava_pic(self,img):
        save_path = self.save_dir + "/" +img.replace(‘:‘,‘@‘).replace(‘/‘,‘_‘)
        if not os.path.exists(self.save_dir):
            os.makedirs(self.save_dir)
        print(save_path)
        urllib.request.urlretrieve(img,save_path)
    #filter
    def pick_pic(self,html_content):
        patren = re.compile(r‘src="http://www.soscw.com/(http:.*?\.(?:jpg|png|gif))‘)
        pic_path_list = patren.findall(html_content)
        for i in pic_path_list:
           #print(i)
           self.sava_pic(str(i))


    #mamy threading
    def start(self):
        for i in range(1,self.page_num):
            thread = threading.Thread(target=self.load_html,args=str(i))
            thread.start()

# main void
spider = QsSpider()
spider.start()