用requests库和BeautifulSoup4库爬取新闻列表

Posted 2020-10-08 胡思琪

1.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

gzccurl = \'http://news.gzcc.cn/html/xiaoyuanxinwen/\'
res = requests.get(gzccurl)
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#标题
        url = news.select(\'a\')[0][\'href\']#链接
        time = news.select(\'.news-list-info\')[0].contents[0].text
        source = news.select(\'.news-list-info\')[0].contents[1].text
        
        #详情
        #resd = requests.get(url)
        #res.encoding=\'utf-8\'
        #soupd = BeautifulSoup(res.text,\'html.parser\')
        #detail = soupd.select(\'.show-content\')

        print(time,\'\\n\',title,\'\\n\',url,\'\\n\',source,\'\\n\')
        

结果：

2.将其中的时间str转换成datetime类型。

import requests
from bs4 import BeautifulSoup
from datetime import datetime

gzccurl = \'http://news.gzcc.cn/html/xiaoyuanxinwen/\'
res = requests.get(gzccurl)
res.encoding=\'utf-8\'
soup = BeautifulSoup(res.text,\'html.parser\')

#def getdetail(url):
    #resd = requests.get(url)
    #resd.encoding=\'utf-8\'
    #soupd = BeautifulSoup(res.text,\'html.parser\')
    #return (soupd.select(\'.show-content\')[0].text)

for news in soup.select(\'li\'):
    if len(news.select(\'.news-list-title\'))>0:
        title = news.select(\'.news-list-title\')[0].text#标题
        url = news.select(\'a\')[0][\'href\']#链接
        time = news.select(\'.news-list-info\')[0].contents[0].text
        dt = datetime.strptime(time,\'%Y-%m-%d\')
        source = news.select(\'.news-list-info\')[0].contents[1].text#来源
        #detail = getdetail(url)#详情


        print(dt,\'\\n\',title,\'\\n\',url,\'\\n\',source,\'\\n\')
        
        

结果

3.将取得详细内容的代码包装成函数。

import requests
from bs4 import BeautifulSoup
from datetime import datetime

gzccurl = \'http://news.gzcc.cn/html/xiaoyuanxinwen/\'
res = requests.get(gzccurl)
res.encoding=\'utf-8\'
soup = BeautifulSoup(res.text,\'html.parser\')

def getdetail(url):
    resd = requests.get(url)
    resd.encoding=\'utf-8\'
    soupd = BeautifulSoup(res.text,\'html.parser\')
    return (soupd.select(\'.show-content\')[0].text)

for news in soup.select(\'li\'):
    if len(news.select(\'.news-list-title\'))>0:
        title = news.select(\'.news-list-title\')[0].text#标题
        url = news.select(\'a\')[0][\'href\']#链接
        time = news.select(\'.news-list-info\')[0].contents[0].text
        dt = datetime.strptime(time,\'%Y-%m-%d\')
        source = news.select(\'.news-list-info\')[0].contents[1].text#来源
        detail = getdetail(url)#详情


        print(dt,\'\\n\',title,\'\\n\',url,\'\\n\',source,\'\\n\')
        break
        

结果

4.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
jq=\'http://www.lbldy.com/tag/gqdy/\'
res = requests.get(jq)
res.encoding=\'utf-8\'
soup = BeautifulSoup(res.text,\'html.parser\')
 
for news in soup.select(\'li\'):
    if len(news.select(\'a\'))>0:
        title=news.select(\'a\')[0].text
        url=news.select(\'a\')[0][\'href\']
        #time=news.select(\'span\')[0].contents[0].text
        #print(time,title,url)
        print(title,url)

结果：