一个简单的爬虫

import urllib.request
import re
import os
import time
import sched

# 写入错误日志方法
def write_error_log(error_str):
    try:
        fh=open(data_path + "/error_log.txt", "a")
        fh.write(time.strftime("-" * 30 + "%Y-%m-%d %H:%M:%S",time.localtime(time.time())) + "-" * 30 + "\n")
        fh.write(str(error_str) + "\n")
        fh.close()
    except Exception as e:
        print(e)
        
url="http://blog.csdn.net/"
data_path="d:/CSDN"
data=urllib.request.urlopen(url,timeout=60).read().decode("UTF-8","ignore")
pat = "

alllink=re.compile(pat,re.S).findall(data)

def get_link(wait_time):
    if not os.path.exists(data_path):
        os.makedirs(data_path)
    for link in alllink:
        print(link)
        try:
            urllib.request.urlretrieve(link, data_path + "/" + str(int(round(time.time() * 1000))) + ".html")
        except urllib.error.URLError as e:
            if hasattr(e, "code"):
                write_error_log(e.code)
            if hasattr(e, "reason"):
                write_error_log(e.reason)
    schedule.enter(wait_time, 0, get_link, (wait_time,))

schedule = sched.scheduler( time.time, time.sleep )

#程序入口
if __name__ == "__main__":
    wait_time = 5
    schedule.enter(0, 0, get_link, (wait_time,))
    schedule.run()