python ---- spider

使用python写基本爬虫

以http://news.sina.com.cn/china/

import requests

resp=requests.get('http://news.sina.com.cn/china/')

resp.encoding='uft-8'

from bs4 import BeautifulSoup

html_sample=resp.text

soup=BeautifulSoup(html_sample,'html.parser')

titles=soup.select(''title)

print(titles)

for meta in metas:

print(meta)

IDs=soup.select('#id')

print(IDs)

CLASSs=soup.select('.class')

print(CLASSs)

 

----------------------------------------------------------------------------------------------

Python 3.7.0 (v3.7.0:1bf9cc5093, Jun 27 2018, 04:59:51) [MSC v.1914 64 bit (AMD64)] on win32
Type "help", "copyright", "credits" or "license" for more information.
>>> import requests
>>> from bs4 import BeautifulSoup
>>> res=requests.get('http://news.sina.com.cn/china')
>>> res.encoding='utf-8'
>>> soup=BeautifulSoup(res.text,'html.parser')
>>> for news in soup.select('.news-item'):
...     if len(news.select('h2'))>0:
...             h2=news.select('h2')[0].text
...             time=news.select('.time')[0].text
...             a=news.select('a')[0]['href']
...             print(time,h2,a)
...
>>>
>>>

时间字符串转换

from datetime import datetime

字符串时间---strptime

dt=datetime.strptime(timesource,'%Y年%m月%d日%H:%M')

时间转字符串：strftime

dt.strftime('%Y-%m-%d')