Python爬虫从入门到入狱

最近刚学了爬虫，迫不及待找了个测试网站练练

为了效果更好，我加入了:

• python多线程的老模块_thread
• 简易的UA代理池fake_useragent (需自己下载)

自己电脑配置也高一点，否则带不动。

爬虫代码

# -*- coding:utf-8 -*-
from urllib import request
from fake_useragent import UserAgent
import _thread

class my_spider(object):	#爬虫类
	def __init__(self):		#构造函数
		self.tick_cnt = 1 #tick计数
		try:
			self.Ua_Pattern = UserAgent()	#构造代理池
			Ua = self.Ua_Pattern.firefox 	#获取UA
			self.url = "https://www.mianshiya.com/"  # 嘿嘿嘿，测试网站
			headers = {"User-Agent": Ua}  #写入UA
			Requests = request.Request(url=self.url, headers=headers)
			Response = request.urlopen(Requests)    #爬虫!
			first_html = Response.read().decode('utf-8')  #第一次爬的信息
			print("first_html get message : ")
			print(first_html)
		except Exception as error_message:    #问题?
			print("Catch Error: " + error_message)

	def run(self):			#RURNRURNRUN
		#消化一下……无法描述
		while True:
			try:
				Ua = self.Ua_Pattern.firefox
				headers = {"User-Agent" : Ua}
				Requests = request.Request(url=self.url,headers=headers)
				Response = request.urlopen(Requests)
				if(Response.read().decode('utf-8') == None):
					print("Device our request!")
					print("Exit!")
					exit(0)
				print("Tick["+self.tick_cnt+"] ", end=" ")
				tick_cnt += 1
				Ua = self.Ua_Pattern.ie
				headers = {"User-Agent" : Ua}
				Requests = request.Request(url=self.url,headers=headers)
				Response = request.urlopen(Requests)
				if(Response.read().decode('utf-8') == None):
					print("Device our request!")
					print("Exit!")
					exit(0)
				print("Tick["+self.tick_cnt+"] ", end=" ")
				tick_cnt += 1
				Ua = self.Ua_Pattern.safari
				headers = {"User-Agent" : Ua}
				Requests = request.Request(url=self.url,headers=headers)
				Response = request.urlopen(Requests)
				if(Response.read().decode('utf-8') == None):
					print("Device our request!")
					print("Exit!")
					exit(0)
				print("Tick["+self.tick_cnt+"] ",end=" ")
				tick_cnt += 1
				Ua = self.Ua_Pattern.edge
				headers = {"User-Agent" : Ua}
				Requests = request.Request(url=self.url,headers=headers)
				Response = request.urlopen(Requests)
				if(Response.read().decode('utf-8') == None):
					print("Device our request!")
					print("Exit!")
					exit(0)
				print("Tick["+self.tick_cnt+"] ", end=" ")
				tick_cnt != 1
			except Exception as error_message:
				print("Take Error As: ")
				print(error_message)
	

def run_sub_request():		#创建进程的函数
	s = my_spider()
	s.run()			
		
def main():		#主函数
	try:
		while True:
			_thread.start_new_thread(run_sub_request,())   #进程!
	except:
		print("Error: Can't init thread")

if __name__ == '__main__':		#INIT
	main()

不要随意尝试，否则真的是从入门到入狱，试一次够了