学习笔记(08):150讲轻松搞定Python网络爬虫-urllib库-urllib库爬虫作业

立即学习:https://edu.csdn.net/course/play/24756/280660?utm_source=blogtoedu

#HTTPS://www.biedoul.com

from urllib import request
for i in range(31095,31099):
    i=str(i)
    z="laugh" + i + ".html"
    url = "https://www.biedoul.com/index/"+i
    resp = request.urlopen(url)
    print(resp.read().decode('utf-8'))
    request.urlretrieve(url,z)
# 爬取别逗了笑话的最后三个网页。

#思考，如果要爬range(1,31099)如何用 yield 代替 range 

#-----------------------------------------------

#爬取www.biedoul.com
from urllib import request
import time     #引用时间函数
import random   #引用随机数#思路就是爬完一个html随机休息一段时间再爬以免对服务器造成负担,但是自己爬的特慢
def foo(num):

    while num<31099:
        num = num+1
        yield num

for i in foo(1):
    i=str(i)
    z="laugh" + i + ".html"
    url = "https://www.biedoul.com/index/"+i
    resp = request.urlopen(url)
    print(resp.read().decode('utf-8'))
    request.urlretrieve(url,z)
    time.sleep(random.random() * 3)
# 爬取别逗了笑话