Python3 抓取糗事百科最新文本笑话
07/21
from bs4 import BeautifulSoup
import requests
#糗事百科 首页最新笑话抓取
class Downxh(object):
def __init__(self):
self.domain = 'https://www.qiushibaike.com'
self.target = self.domain + '/text/'
self.urls = []
# 根据首页获取列表url
def getHtml(self):
info = requests.get(self.target)
html = info.text
htmlObj = BeautifulSoup(html,'html.parser')
cHtml = htmlObj.find('div',id = 'content-left')
html2Obj = BeautifulSoup(str(cHtml),'html.parser')
lists = html2Obj.find_all('a',class_ = 'contentHerf')
for item in lists:
self.urls.append( self.domain + item.get('href') )
# 遍历urls保存到txt文件
def saveContent(self):
print('--正在下载最新' + str(len(self.urls)) + '条笑话--')
f = open('最新笑话.txt', 'w', encoding='utf-8')
i = 1
for url in self.urls:
print('正在下载第：' + str(i) + '条')
info = requests.get(url)
html = info.text
htmlObj = BeautifulSoup(html, 'html.parser')
contents = htmlObj.find_all('div', class_='content')
content = contents[0].text
f.write(content + '\n\n')
i = i+1
f.close()
# 执行抓取
def run(self):
self.getHtml()
self.saveContent()
print('下载完成')
pass
downObj = Downxh()
# 运行
downObj.run()如果没有：BeautifulSoup 和 requests 插件的请先用pip安装一下
pip install beautifulsoup4 pip install requests
下面是运行结果
版权属于：
Dcr163的博客
本文链接：
http://dcr163.cn/214.html（转载时请注明本文出处及文章链接）
哟呵，上班还有空更新，还写那么多，是不是工作量不饱和
