用requests库和BeautifulSoup4库爬取新闻列表

用requests库和BeautifulSoup4库，爬取校园新闻列表的时间、标题、链接、来源。

import requests
from bs4 import BeautifulSoup

url='http://news.gzcc.cn/html/xiaoyuanxinwen/'
res=requests.get(url)
res.encoding='utf-8'
soup=BeautifulSoup(res.text,'html.parser')
for news in soup.select('li'):
    if len(news.select('.news-list-title'))>0:
        title=news.select('.news-list-title')[0].text
        time=news.select('.news-list-info')[0].contents[0].text
        tag=news.select('.news-list-description')[0].text
        url=news.select('a')[0]['href']
        thumb=news.select('.news-list-thumb')[0].contents[0]
        print(time,title,url,tag,thumb)

选一个自己感兴趣的主题，做类似的操作，为“爬取网络数据并进行文本分析”做准备。

import requests
from bs4 import BeautifulSoup

url='http://gz.58.com/ershouche/?utm_source=market&spm=b-31580022738699-pe-f-829.hao360_101&PGTID=0d100000-0000-3ada-ba49-dc2ff301240a&ClickID=1'
res=requests.get(url)
res.encoding='utf-8'
soup=BeautifulSoup(res.text,'html.parser')
for esc in soup.select('dd'):
    if len(esc.select('a'))>0:
        url=esc.select('a')[0]['href']
        title=esc.select('a')[0].text
        print(title,url)