获取全部的校园新闻

1.从新闻url获取新闻详情： 字典,anews

2.从列表页的url获取新闻url：列表append(字典) alist

3.生成所页列表页的url并获取全部新闻 ：列表extend(列表) allnews

*每个同学爬学号尾数开始的10个列表页

4.设置合理的爬取间隔

import time

import random

time.sleep(random.random()*3)

5.用pandas做简单的数据处理并保存

保存到csv或excel文件 

newsdf.to_csv(r'F:\duym\爬虫\gzccnews.csv')

保存到数据库

import sqlite3
with sqlite3.connect('gzccnewsdb.sqlite') as db:
    newsdf.to_sql('gzccnewsdb',db)

 

 1 import requests
 2 from bs4 import BeautifulSoup
 3 from datetime import datetime
 4 import re
 5 import pandas as pd
 6 import time
 7 import random
 8 import sqlite3
 9 if __name__ == '__main__':
10  newsUrl = 'http://news.gzcc.cn/html/2005/xiaoyuanxinwen_0710/4.html'
11 listUrl = 'http://news.gzcc.cn/html/xiaoyuanxinwen/'
12 
13 
14 def click(url):
15     id = re.findall('(\d{1,5})', url)[-1]
16     clickUrl = 'http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80'.format(id)
17     resClick = requests.get(clickUrl)
18     newsClick = int(resClick.text.split('.html')[-1].lstrip("('").rstrip("');"))
19     return newsClick
20 
21 
22 def newsdt(showinfo):
23     newsDate = showinfo.split()[0].split(':')[1]
24     newsTime = showinfo.split()[1]
25     newsDT = newsDate + ' ' + newsTime
26     dt = datetime.strptime(newsDT, '%Y-%m-%d %H:%M:%S')
27     return dt
28 
29 #从新闻url获取新闻详情： 字典,anews
30 def anews(url):
31     newsDetail = {}
32     res = requests.get(url)
33     res.encoding = 'utf-8'
34     soup = BeautifulSoup(res.text, 'html.parser')
35     newsDetail['newsTitle'] = soup.select('.show-title')[0].text
36     showinfo = soup.select('.show-info')[0].text
37     newsDetail['newsDT'] = newsdt(showinfo)
38     newsDetail['newsClick'] = click(newsUrl)
39     return newsDetail
40 
41 #从列表页的url获取新闻url：列表append(字典) alist
42 def alist(url):
43     res = requests.get(listUrl)
44     res.encoding = 'utf-8'
45     soup = BeautifulSoup(res.text, 'html.parser')
46     newsList = []
47     for news in soup.select('li'):
48         if len(news.select('.news-list-title')) > 0:
49             newsUrl = news.select('a')[0]['href']
50             newsDesc = news.select('.news-list-description')[0].text
51             newsDict = anews(newsUrl)
52             newsDict['description'] = newsDesc
53             newsList.append(newsDict)
54     return newsList
55 
56 
57 
58 res = requests.get('http://news.gzcc.cn/html/xiaoyuanxinwen/')
59 res.encoding = 'utf-8'
60 soup = BeautifulSoup(res.text, 'html.parser')
61 
62 for news in soup.select('li'):
63     if len(news.select('.news-list-title')) > 0:
64         newsUrl = news.select('a')[0]['href']
65         print(anews(newsUrl))
66 
67 allnews = []
68 for i in range(15, 25):#爬取学号尾数开始的10个列表页
69     listUrl = 'http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html'.format(i)
70     allnews.extend(alist(listUrl))
71 
72 print("allnewsLength={}".format(len(allnews)))
73 print(allnews)
74 
75 res = requests.get('http://news.gzcc.cn/html/xiaoyuanxinwen/')
76 res.encoding = 'utf-8'
77 soup = BeautifulSoup(res.text, 'html.parser')
78 for news in soup.select('li'):
79     if len(news.select('.news-list-title')) > 0:
80         newsUrl = news.select('a')[0]['href']
81         print(anews(newsUrl))
82 
83 s1 = pd.Series([100, 23, 'bugingcode'])
84 print(s1)
85 pd.Series(anews)
86 newsdf = pd.DataFrame(allnews)
87 for i in range(5):
88     print(i)
89     time.sleep(random.random() * 3)#设置爬取的时间间隔
90     print(newsdf)
91 
92 newsdf.to_csv(r'F:\test1\gzcc.csv',encoding='utf_8_sig')#保存成csv格式，编码格式为utf_8_sig
93 
94 with sqlite3.connect(r'F:\test1\gzccnewsdb.sqlite') as db:#保存文件为sql
95     newsdf.to_sql('gzccnewsdb',db)
View Code

posted @ 2019-04-12 17:11  FreyjaFs  阅读(210)  评论(0)  编辑  收藏  举报