Python爬虫实践代码示例

对于刚入门爬虫的小伙伴来说，累积经验多练习代码是非常有必要的，下面就是有关爬虫的一些小案例，欢迎大家指正。

import requests
from bs4 import BeautifulSoup
# import pandas

def GetBlogByPage(pageNum):
  headers={
  "User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36"
  }
  targetUrl="目标网站"
  response=requests.get(targetUrl.format(pageNum),headers=headers)
  response.encoding='utf-8'
  contentText=response.text
  soup=BeautifulSoup(contentText,"html.parser")

  getTargetInfo=[]
  articles=soup.select('.article-item-box')
  for article in articles:
  info={}
  info["title"]=article.a.text.strip()
  info["source"]=article.a['href'].strip()
  info["sendTime"]=article.div.p.span.text.strip()
  info["ReadNum"]=article.div.select('span')[1].text
  info["writeNum"]=article.div.select('span')[3].text
  getTargetInfo.append(info)
  with open("blog.txt",'w') as f:
  for info in getTargetInfo:
    print(info)
    f.write(str(info))
  # df=pandas.DataFrame(getTargetInfo)
  # df.head()
  # df.to_excel('blog.xlsx')


for i in range(1,9):       #按页爬取
  GetBlogByPage(i)