Python爬虫实践1，博主博客文章爬取

 

'''
爬取博客文章，静态页面
'''

import urllib.request
import http.cookiejar
import requests
from bs4 import BeautifulSoup

def clean_file():  #初始清除文档内容
    with open('article.txt','w',encoding='utf-8') as f:
        f.truncate()

def write_to_file(content): #增量写入
    with open('article.txt', 'a', encoding='utf-8') as f:
        f.write(content)

def get_page(url): #获取response
    try:
        response = requests.get(url,timeout=20)
        return response.text
    except:
        return "error"

def get_blog_info():
    headers={'User-Agent':  #chrome申请头信息
             'Mozilla/5.0 (Windows NT 6.1; WOW64)'
             'AppleWebKit/537.36 (KHTML, like Gecko)'
             'Chrome/77.0.3865.90'
             'Safari/537.36'}
    html=get_page(blog_url)
    soup=BeautifulSoup(html,'lxml&