爬虫小程序--0001

第1题：爬取捧腹网上笑话段子。

# -*- coding: utf-8 -*-
import sys
import urllib.request as request
from bs4 import BeautifulSoup

def get_jokes(nums):
    cnt = 0
    page = 1
    while cnt < nums:
        url = 'http://www.pengfu.com/xiaohua_%d.html' % page
        headers = {'User-Agent':'User-Agent:Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.115 Safari/537.36'}
        req = request.Request(url, headers=headers)
        soup = BeautifulSoup(request.urlopen(req).read(),'lxml')
        #print(soup)
        #for joke in get_pengfu_results(url):
        for joke in soup.find_all(class_="content-img clearfix pt10 relative"):
            content = joke.string
            try:
                if cnt < nums:
                    text = content.lstrip()
                    cnt += 1
                    print("%s. "%cnt + text + "\n")
                else:
                    return
            except:
                continue
        page += 1

if __name__ == '__main__':
    nums = input("Please enter number of jokes:")
    get_jokes(int(nums))

输出如下：