python3爬虫例子02（获取个人博客园的文章信息）

#!/usr/bin/env python
# -*- coding:UTF-8 -*-

import requests
from bs4 import BeautifulSoup

res=requests.get("https://www.cnblogs.com/NiceTime/")
# c=res.content
c=res.text
# print(c)

#获取文章日期
soup=BeautifulSoup(c,"html.parser")

postday=soup.find_all(class_="dayTitle")
# for i in postday:
#     pday=i
#     print(pday.a.string)

#获取文章标题
posttitle=soup.find_all(class_="postTitle")
# for i in posttitle:
#     ptitle=i
#     print(ptitle.a.string)

#获取文章摘要
postcorn=soup.find_all(class_="c_b_p_desc")
# for i in postcorn:
#     ptitle=i
#     print(pcorn.contents[0])

for day,title,corn in zip(postday,posttitle,postcorn):
    # pcorn=i
    print(day.a.string)
    print(title.a.string)
    print(corn.contents[0].string)
    print("")

转载于:https://www.cnblogs.com/NiceTime/p/10070177.html