码迷,mamicode.com
首页 > 其他好文 > 详细

爬取所有校园新闻

时间:2017-10-12 22:52:03      阅读:132      评论:0      收藏:0      [点我收藏+]

标签:sky   label   info   nbsp   hit   time   bre   ref   lis   

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
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)

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)
#break

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)
#break

5.完成自己所选其他主题相应数据的爬取工作。

import requests
from bs4 import BeautifulSoup
import re

url_main="http://www.12306.cn/mormhweb/"
res = requests.get(url_main)
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)
for i in range(2,pages+1):
url_page = "http://www.gamersky.com/{}.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)

 

爬取所有校园新闻

标签:sky   label   info   nbsp   hit   time   bre   ref   lis   

原文地址:http://www.cnblogs.com/elewen/p/7658401.html

(0)
(0)
   
举报
评论 一句话评论(0
登录后才能评论!
© 2014 mamicode.com 版权所有  联系我们:gaon5@hotmail.com
迷上了代码!