爬取所有新闻列表

Posted 2020-10-10 素欣

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
import re

res = requests.get("http://news.gzcc.cn/html/xibusudi/")
res.encoding = ‘utf-8‘

soup = BeautifulSoup(res.text,‘html.parser‘)
li = soup.select(‘li‘)

def gethits(url_1):
li_id =re.search(‘_.*/(.*).html‘,url_1).groups(0)[0]
hits = requests.get(‘http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80‘.format(li_id)).text.split(‘.‘)[-1].rstrip(‘‘‘‘);‘‘‘).lstrip(‘‘‘‘html(‘‘‘)
return hits

def getpageinfo(label):
for title_list in label:
if len(title_list.select(‘.news-list-title‘))>0:
href = title_list.select(‘a‘)[0][‘href‘]
title = title_list.select(‘.news-list-title‘)[0].text
time = title_list.select(‘span‘)[0].text
info = title_list.select(‘span‘)[1].text

res_list = requests.get(href)
res_list.encoding = ‘utf-8‘
soup_list = BeautifulSoup(res_list.text,‘html.parser‘)
text_list = soup_list.select(‘.show-content‘)[0].text

hits_list = gethits(href)

print(‘时间：‘,time,
‘\n标题：‘,title,
‘\n链接：‘,href,
‘\n来源：‘,info,
‘\n点击次数：‘,hits_list,‘\n‘)

print(‘正文：‘,text_list)
break

getpag

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
import re
from bs4 import BeautifulSoup
from datetime import datetime

def getchick(url):
    t = re.match(‘http://news.gzcc.cn/html/2017/xiaoyuanxinwen_(.*).html‘,url).groups()
    id = t[0].split(‘/‘)[1]
    chickurl = ‘http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80‘.format(id)
    chick = int(requests.get(chickurl).text.split(‘.‘)[-1].lstrip("html(‘").rstrip("‘);"))
    return(chick)
def getonepage(url):
    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‘] 
            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 
        
            resd = requests.get(url)
            resd.encoding=‘utf-8‘
            soupd = BeautifulSoup(resd.text,‘html.parser‘)
            detail = soupd.select(‘.show-content‘)[0].text
            chick = getchick(url)
            print(title,chick,url,dt,source,detail)
gzccurl = ‘http://news.gzcc.cn/html/xiaoyuanxinwen/‘
res = requests.get(gzccurl)
res.encoding=‘utf-8‘
soup = BeautifulSoup(res.text,‘html.parser‘)

getonepage(‘http://news.gzcc.cn/html/xiaoyuanxinwen/index,html‘)

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
url_main="http://news.gzcc.cn/html/xiaoyuanxinwen/"
res = requests.get(url_main)
res.encoding = ‘utf-8‘
soup = BeautifulSoup(res.text,‘html.parser‘)
li = soup.select(‘li‘)
def gethits(url_1):
    li_id =re.search(‘_.*/(.*).html‘,url_1).groups(0)[0]
    hits = requests.get(‘http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80‘.format(li_id)).text.split(‘.‘)[-1].rstrip(‘‘‘‘);‘‘‘).lstrip(‘‘‘‘html(‘‘‘)
    return hits
def getpageinfo(label):
    for title_list in label:
        if len(title_list.select(‘.news-list-title‘))>0:
            href = title_list.select(‘a‘)[0][‘href‘]
            title = title_list.select(‘.news-list-title‘)[0].text
            time = title_list.select(‘span‘)[0].text
            info = title_list.select(‘span‘)[1].text
            res_list = requests.get(href)
            res_list.encoding = ‘utf-8‘
            soup_list = BeautifulSoup(res_list.text,‘html.parser‘)
            text_list = soup_list.select(‘.show-content‘)[0].text
            hits_list = gethits(href)
getpageinfo(li)
pages = int(soup.select(‘.a1‘)[0].text.rstrip(‘条‘))//10+1
for i in range(2,pages+1):
    url_page = "http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html".format(i) 
    res_page = requests.get(url_page)
    res_page.encoding = ‘utf-8‘
    soup_page = BeautifulSoup(res_page.text,‘html.parser‘)
    list_page = soup.select(‘li‘)
    getpageinfo(list_page)
    print(url_page)

4、完成所有校园新闻的爬取工作。

import requests
from bs4 import BeautifulSoup
import re

url_main="http://news.gzcc.cn/html/xiaoyuanxinwen/"
res = requests.get(url_main)
res.encoding = ‘utf-8‘

soup = BeautifulSoup(res.text,‘html.parser‘)
li = soup.select(‘li‘)

def gethits(url_1):
li_id =re.search(‘_.*/(.*).html‘,url_1).groups(0)[0]
hits = requests.get(‘http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80‘.format(li_id)).text.split(‘.‘)[-1].rstrip(‘‘‘‘);‘‘‘).lstrip(‘‘‘‘html(‘‘‘)
return hits

def getpageinfo(label):
for title_list in label:
if len(title_list.select(‘.news-list-title‘))>0:
href = title_list.select(‘a‘)[0][‘href‘]
title = title_list.select(‘.news-list-title‘)[0].text
time = title_list.select(‘span‘)[0].text
info = title_list.select(‘span‘)[1].text

res_list = requests.get(href)
res_list.encoding = ‘utf-8‘
soup_list = BeautifulSoup(res_list.text,‘html.parser‘)
text_list = soup_list.select(‘.show-content‘)[0].text

hits_list = gethits(href)

print(‘时间：‘,time,‘\n标题：‘,title,‘\n链接：‘,href,‘\n来源：‘,info,‘\n点击次数：‘,hits_list,‘\n‘)
print(‘正文：‘,text_list)


getpageinfo(li)

pages = int(soup.select(‘.a1‘)[0].text.rstrip(‘条‘))//10+1

for i in range(2,pages+1):
url_page = "http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html".format(i)

res_page = requests.get(url_page)
res_page.encoding = ‘utf-8‘

soup_page = BeautifulSoup(res_page.text,‘html.parser‘)
list_page = soup.select(‘li‘)

getpageinfo(list_page)