爬取新闻列表

Posted 2020-10-10 06刘玲苑

1、获取单条新闻的#标题#链接#时间#来源#内容 #点击次数，并包装成一个函数。

import requests
from bs4 import BeautifulSoup

mt="http://news.gzcc.cn/html/xiaoyuanxinwen/"
res=requests.get(mt)
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)
        url=news.select(\'a\')[0][\'href\']
        day=(news.select(\'.news-list-info\')[0].contents[0].text)
        sorce=(news.select(\'.news-list-info\')[0].contents[1].text)
    
   
        resd=requests.get(url)
        resd.encoding=\'utf-8\'
        soupd=BeautifulSoup(resd.text,"html.parser")
        textd=(soupd.select(\'.show-content\')[0].text)

        diji=requests.get(\'http://oa.gzcc.cn/api.php?op=count&id=8301&modelid=80\').text.split(\'.\')[-1].lstrip("html(\'").rstrip("html\');")
        print(diji)
        break

 

2、获取一个新闻列表页的所有新闻的上述详情，并包装成一个函数。

 

import requests
from bs4 import BeautifulSoup

mt="http://news.gzcc.cn/html/xiaoyuanxinwen/"
res=requests.get(mt)
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)
        url=news.select(\'a\')[0][\'href\']
        day=(news.select(\'.news-list-info\')[0].contents[0].text)
        sorce=(news.select(\'.news-list-info\')[0].contents[1].text)
    
   
        resd=requests.get(url)
        resd.encoding=\'utf-8\'
        soupd=BeautifulSoup(resd.text,"html.parser")
        textd=(soupd.select(\'.show-content\')[0].text)

        
        print(textd)
        break

 

3、获取所有新闻列表页的网址，调用上述函数。

import requests
from bs4 import BeautifulSoup
import re


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

n=int(soup.select(\'.a1\')[0].text.rstrip(\'条\'))
page=n//10+1
for i in range(page+1):
    pageurl=\'http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html\'.format(i)
    print(pageurl)

4、完成所有校园新闻的爬取工作。

 

import requests
from bs4 import BeautifulSoup
import re

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

def getdiji(newurl):
    id=re.search(\'_(.*).html\',newurl).group(1).split(\'/\')[1]
    dijiurl=\'http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80\'.format(id)
    diji=requests.get(\'http://oa.gzcc.cn/api.php?op=count&id=8301&modelid=80\').text.split(\'.\')[-1].lstrip("html(\'").rstrip("html\');")
    return diji


def genonepage(listurl):
    res=requests.get(listurl)
    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\']       #网址
        day=(news.select(\'.news-list-info\')[0].contents[0].text) #日期
        sorce=(news.select(\'.news-list-info\')[0].contents[1].text) #来源
    
   
        resd=requests.get(url)
        resd.encoding=\'utf-8\'
        soupd=BeautifulSoup(resd.text,"html.parser")
        textd=(soupd.select(\'.show-content\')[0].text)#点击次数

        diji=getdiji(url)
        print(day,title,sorce,diji)
        
gzccurl=\'http://news.gzcc.cn/html/xiaoyuanxinwen/\'
res=requests.get(gzccurl)
res.encoding=\'utf-8\'
soup=BeautifulSoup(res.text,"html.parser")

n=int(soup.select(\'.a1\')[0].text.rstrip(\'条\'))
page=n//10+1
for i in range(2,7):
    pageurl=\'http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html\'.format(i)
    print(pageurl)