1. 將新聞的正文內容保存到文本文件。php
2. 將新聞數據結構化爲字典的列表:html
import requests from bs4 import BeautifulSoup from datetime import datetime import re import pandas import sqlite3 import pymysql from sqlalchemy import create_engine conn = create_engine('mysql+pymysql://root:root@localhost:3306/gzccnews?charset=utf8') pandas.io.sql.to_sql(df, 'gzccnews', con=conn, if_exists='replace') def writeNewsDetail(content): f = open('gzccNews.txt', 'a',encoding='utf-8') f.write(content) f.close() def getClickCount(newsUrl): #一篇新聞的點擊次數 newId = re.search('\_(.*).html', newsUrl).group(1).split('/')[1] clickUrl = "http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80".format(newId) return (int(requests.get(clickUrl).text.split('.html')[-1].lstrip("('").rstrip("');"))) def getNewsDetail(newsUrl): #一篇新聞的所有信息 resd = requests.get(newsUrl) resd.encoding = 'utf-8' soupd = BeautifulSoup(resd.text, 'html.parser') # 打開新聞詳情頁並解析 news ={} news['title'] = soupd.select('.show-title')[0].text info = soupd.select('.show-info')[0].text news['dt'] = datetime.strptime(info.lstrip('發佈時間:')[0:19], '%Y-%m-%d %H:%M:%S') if info.find('來源:') > 0: # 做者: 審覈: 來源: 攝影:同樣處理 news['source'] = info[info.find('來源:'):].split()[0].lstrip('來源:') else: news['source'] = 'none' news['content'] = soupd.select('.show-content')[0].text.strip() writeNewsDetail(news['content']) news['click'] = getClickCount(newsUrl) #print(dt,title,newsUrl,source,click) news['newsUrl'] = newsUrl return (news) def getListPage(pageUrl): #一個列表頁的所有新聞 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'] # 連接 newsList.append(getNewsDetail(newsUrl)) return(newsList) def getPageN(): # 新聞列表頁的總頁數 res = requests.get('http://news.gzcc.cn/html/xiaoyuanxinwen/') res.encoding = 'utf-8' soup = BeautifulSoup(res.text, 'html.parser') n = int(soup.select('.a1')[0].text.rstrip('條')) return (n // 10 + 1) newsTotal = [] firstPageUrl = 'http://news.gzcc.cn/html/xiaoyuanxinwen/' newsTotal.extend(getListPage(firstPageUrl)) n = getPageN() for i in range(n, n+1): listPageUrl = 'http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html'.format(i) newsTotal.extend(getListPage(listPageUrl)) print(newsTotal)
3. 安裝pandas,用pandas.DataFrame(newstotal),建立一個DataFrame對象df.mysql
4. 經過df將提取的數據保存到csv或excel 文件。sql
df=pandas.DataFrame(newsTotal)
df.to_excel('')
5. 用pandas提供的函數和方法進行數據分析:數據庫
# 安裝pandas,用pandas.DataFrame(newstotal),建立一個DataFrame對象df. df = pandas.DataFrame(newslist1) print(df) # 經過df將提取的數據保存到csv或excel 文件 df.to_csv("1.excel") # 提取包含點擊次數、標題、來源的前5行數據 print(df[['click', 'title', 'sources']].head(5)) # 提取‘學校綜合辦’發佈的,‘點擊次數’超過3000的新聞。 print(df[(df['click'] > 3000) & (df['sources'] == '學校綜合辦')]) # 提取'國際學院'和'學生工做處'發佈的新聞。 print(df[df['sources'].isin(['國際學院', '學生工做處'])])
#進取2018年3月的新聞
print(df['dt']=='2018.03')
6. 保存到sqlite3數據庫api
import sqlite3 with sqlite3.connect('gzccnewsdb.sqlite') as db: df3.to_sql('gzccnews05',con = db, if_exists='replace')數據結構
7. 從sqlite3讀數據app
with sqlite3.connect('gzccnewsdb.sqlite') as db: df2 = pandas.read_sql_query('SELECT * FROM gzccnews05',con=db) print(df2)函數
8. df保存到mysql數據庫spa
安裝SQLALchemy 安裝PyMySQL MySQL裏建立數據庫:create database gzccnews charset utf8;
import pymysql from sqlalchemy import create_engine conn = create_engine('mysql+pymysql://root:root@localhost:3306/gzccnews?charset=utf8') pandas.io.sql.to_sql(df, 'gzccnews', con=conn, if_exists='replace')
MySQL裏查看已保存了數據。(經過MySQL Client或Navicate。)