爬取新闻列表

Posted 2020-10-11

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。

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。

3、获取所有新闻列表页的网址，调用上述函数。

4、完成所有校园新闻的爬取工作。

import requests
import re
from bs4 import BeautifulSoup
from datetime import datetime

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

def getclicks(current_urls):
    id = re.search("_(.*).html",current_urls).groups()[0].split(‘/‘)[1]
    click =int(requests.get(‘http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80‘.format(id)).text.split(‘.‘)[-1].lstrip("html(‘").rstrip("‘);"))
    return click
#每一页文章明细
def getfirstpages(url24):
    res=requests.get(url24)
    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#时间
        url1=news.select(‘a‘)[0][‘href‘]#url
        bumen=news.select(‘.news-list-info‘)[0].contents[1].text#院系
        description=news.select(‘.news-list-description‘)[0].text#明细（文章）

        resd=requests.get(url1)
        resd.encoding=‘utf-8‘
        soupd=BeautifulSoup(resd.text,‘html.parser‘)
        detail = soupd.select(‘.show-content‘)[0].text #内容
        count = getclicks(url1)#调用函数
        #re.match(‘http://news.gzcc.cn/html/2017/xiaoyuanxinwen_1001/(.*).html‘,url).groups()
        
        print(title,count)
        #print(detail)
        #break
n =int(soup.select(‘.a1‘)[0].text.rstrip(‘条‘))
number = n // 10 + 1
for i in range(2,number+1):
    url01=‘http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html‘.format(i)
    getfirstpages(url01)

import requests
from bs4 import BeautifulSoup
from datetime import datetime

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#时间
        url1=news.select(‘a‘)[0][‘href‘]#url
        bumen=news.select(‘.news-list-info‘)[0].contents[1].text
        description=news.select(‘.news-list-description‘)[0].text 

        resd=requests.get(url1)
        resd.encoding=‘utf-8‘
        soupd=BeautifulSoup(resd.text,‘html.parser‘)
        detail = soupd.select(‘.show-content‘)[0].text

        print(detail)
        break

import requests
from bs4 import BeautifulSoup
from datetime import datetime

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#时间
        url1=news.select(‘a‘)[0][‘href‘]#url
        bumen=news.select(‘.news-list-info‘)[0].contents[1].text
        description=news.select(‘.news-list-description‘)[0].text 

        resd=requests.get(url1)
        resd.encoding=‘utf-8‘
        soupd=BeautifulSoup(resd.text,‘html.parser‘)
        detail = soupd.select(‘.show-content‘)[0].text #内容

        click = requests.get(‘http://oa.gzcc.cn/api.php?op=count&id=8249&modelid=80‘).text.split(‘.‘)[-1].lstrip("html(‘").rstrip("‘);")
        
        print(click)
        print(detail)
        break