import re import requests from bs4 import BeautifulSoup from datetime import datetime def getClickCount(r): s = re.findall('\_(.*).html', r)[0].split('/')[-1] res = requests.get('http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80'.format(s)) return int(res.text.split('.html')[-1].lstrip("('").rstrip("');")) def getNewsDetail(newsUrl): #一篇新闻的全部内容 resd = requests.get(newsUrl) resd.encoding = 'utf-8' soupd = BeautifulSoup(resd.text, 'html.parser') #打开新闻详情并解析 news = {} news['title']=soupd.select('.show-title')[0].text info=soupd.select('.show-info')[0].text news['dt']=datetime.strptime(info.lstrip('发布时间:')[0:19], '%Y-%m-%d %H:%M:%S') if info.find('来源:')>0: news['source']=info[info.find('来源:'):].split()[0].lstrip('来源:') else: news['source']='none' news['content'] = soupd.select('.show-content')[0].text.strip() news['click']=getClickCount(newsUrl) news['newsUrl'] = newsUrl return(news) def getListPage(pageUrl): #9. 取出一个新闻列表页的全部新闻 包装成函数def getListPage(pageUrl) res = requests.get(pageUrl) res.encoding = 'utf-8' soup = BeautifulSoup(res.text, 'html.parser') newslist = [] for news in soup.select('li'): if len(news.select('.news-list-title')) > 0: newsUrl = news.select('a')[0].attrs['href'] newslist.append(getNewsDetail(newsUrl)) return(newslist) def getPageN(): res = requests.get('http://news.gzcc.cn/html/xiaoyuanxinwen/') res.encoding = 'utf-8' soup = BeautifulSoup(res.text, 'html.parser') pagenumber=int(soup.select('.a1')[0].text.rstrip('条')) page = pagenumber//10+1 return page newstotal = [] firstPageUrl='http://news.gzcc.cn/html/xiaoyuanxinwen/' newstotal.extend(getListPage(firstPageUrl)) n=getPageN() # f = open('gzccnews.txt','a',encoding='utf-8') for i in range(n,n+1): listPageUrl='http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html'.format(i) newstotal.extend(getListPage(listPageUrl)) for news in newstotal: print(news) import pandas df = pandas.DataFrame(newstotal) df.to_excel('gzccnews.xlsx')
# print(df.tail(3))
# print(df[2:5])
# print(df['title'])
# print(df[(df['click']>2000)&(df['click']<5000)])
# sou = ['国际学院','学生工作处']
# print(df[df['source'].isin(sou)])
# print(df.index)
# df[df['dt']>'2018-04-12 14:01:24']
# df.index
# print(df[1:5])
# df1 = df.set_index('dt')
# print(df1.index)
#
# print(df1['2018-04-12 17:27:50':'2018-04-04 09:35:00'])
# print(df1['2018-04'])
import sqlite3
with sqlite3.connect('gzccnewsdb.sqlite') as db:
df.to_sql('gzccnews',con= db,if_exists='replace')
with sqlite3.connect('gzccnewsdb.sqlite') as db:
df2 = pandas.read_sql_query('SELECT * FROM gzccnews',con=db)
print(df2)
import pymysql
from sqlalchemy import create_engine
conn = create_engine('mysql+pymysql://root:@localhost:3306/gz?charset=utf8')
pandas.io.sql.to_sql(df2,'news1',con=conn,if_exists='replace')
# f.close()