一个简单的Python爬虫+写入文本

import os
import requests
from bs4 import BeautifulSoup

# 获取HTML文档
def get_html(url):
 response = requests.get(url)
 response.encoding = 'uft-8'
 return response.text

# 获取笑话
def get_joke(html):
 soup = BeautifulSoup(html,'lxml')

 abc = ''
 num = 0
 for link in soup.find_all("div", class_="content"):
# for i in range(10):
 # joke_content = soup.select('div.content')[i].get_text()
 num = num + 1
 abc += "--------" + str(num) + link.get_text()
return abc

# 将笑话写入txt
# ls = os.linesep

def writeJoke(joke):
while True:
 filename = input('文件名：')
if os.path.exists(filename):
print("错误:'%s' 该文件已存在" % filename) # 是否存在

 else:
break

 fobj = open(filename, 'w') #写入文本

 fobj.write(joke)
# fobj.writelines(['%s%s' % (x, ls) for x in all]) #每一个字符后面都会换行
 fobj.close()
print('写入成功！')

url_joke = "https://www.qiushibaike.com"
html = get_html(url_joke)
joke = get_joke(html)
writeJoke(joke)
# print(joke)

转载于:https://www.cnblogs.com/lbx6935/p/9508084.html