1.從新聞url擷取新聞詳情： 字典,anews
2.從清單頁的url擷取新聞url：清單append(字典) alist
3.生成所頁清單頁的url并擷取全部新聞 ：清單extend(清單) allnews
*每個同學爬學号尾數開始的10個清單頁
4.設定合理的爬取間隔
import time
import random
time.sleep(random.random()*3)
5.用pandas做簡單的資料處理并儲存
儲存到csv或excel檔案
newsdf.to_csv(r'F:\duym\爬蟲\gzccnews.csv')
儲存到資料庫
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 #從新聞url擷取新聞詳情： 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 #從清單頁的url擷取新聞url：清單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):#爬取學号尾數開始的10個清單頁
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)#設定爬取的時間間隔
90 print(newsdf)
91
92 newsdf.to_csv(r'F:\test1\gzcc.csv',encoding='utf_8_sig')#儲存成csv格式，編碼格式為utf_8_sig
93
94 with sqlite3.connect(r'F:\test1\gzccnewsdb.sqlite') as db:#儲存檔案為sql
95 newsdf.to_sql('gzccnewsdb',db) View Code