python基础05

通过生成器不断爬取网页(非闭包)

---

#!/bin/python3
# -*- coding:utf-8 -*-
from urllib.request import urlopen
def get():
	print("start crawing...")
	while True: #进入循环不断获取url
		url = yield #将传入参数赋值给url
		temp_content = urlopen(url) #爬取传入的url
		print(temp_content.read()) #输出爬取到的内容
def main():
	g = get() #生成迭代器
	next(g) #进入函数内的第一次循环开始
	while True:
		url = input("url:") #输入url
		g.send(url) #传入url
#main program
if __name__ == '__main__':
	main()

闭包实现

---

#!/bin/python3
# -*- coding:utf-8 -*-
from urllib.request import urlopen
def get(url):
	def index():
		temp_url = url
		while True:
			html_data = urlopen(temp_url).read()
			temp_url = yield html_data
	return index
def main():
	url = input("url:")
	g = get(url)
	e = g()
	print(next(e))
	while True:
		url = input("url:")
		if url != 'q':
			print(e.send(url))
		else:
			break
#main program
if __name__ == '__main__':
	main()