python --简单的网页图片爬取

import requests
import re
from bs4 import BeautifulSoup
import pymssql  
import time
import threading

conn=pymssql.connect(host='192.168.1.167\Test',user='sa',password='123',database='db',timeout=30,login_timeout=5)
cur=conn.cursor()

class myThread (threading.Thread):
    def __init__(self,id):
        threading.Thread.__init__(self)
        self.id=id
    def run(self):
             getimagesList(id)


def getimagesList(id):
     try:
         res = requests.get("www.xxxx.html")
         res.encoding = 'gbk'
         soup = BeautifulSoup(res.text,"html.parser")
         imagesList=soup.find_all('img',style="width: auto;")
         for image in imagesList:
             name = image.get('alt')
             url = image.get('src').replace("//", "")
             if "!/fw/264/quality/91/unsharp/true/compress/true/canvas/264x458a0a0/watermark/url/bG9nby53YXRlci52MTAucG5n/repeat/true/align/center" not in url:
                 return             
             url = url.replace("!/fw/264/quality/91/unsharp/true/compress/true/canvas/264x458a0a0/watermark/url/bG9nby53YXRlci52MTAucG5n/repeat/true/align/center", "")
             #print("insert INTO  wotu (id,title,url) values("+str(id)+",'"+str(name)+"','"+str(url)+"')")
             cur.execute("insert INTO  pic (id,title,url) values("+str(id)+",'"+str(name)+"','"+str(url)+"')")
             conn.commit()
             print("成功了")
     except Exception as ex:
          print("失败了"+time.strftime('%Y-%m-%d %H:%M:%s',time.localtime(time.time())))


 

相关文章

功能概要:(目前已实现功能)公共展示部分:1.网站首页展示...
大体上把Python中的数据类型分为如下几类: Number(数字) ...
开发之前第一步,就是构造整个的项目结构。这就好比作一幅画...
源码编译方式安装Apache首先下载Apache源码压缩包,地址为ht...
前面说完了此项目的创建及数据模型设计的过程。如果未看过,...
python中常用的写爬虫的库有urllib2、requests,对于大多数比...