1. 将新闻的正文内容保存到文本文件。
2. 将新闻数据结构化为字典的列表:
3. 安装pandas，用pandas.DataFrame(newstotal)，创建一个DataFrame对象df.
4. 通过df将提取的数据保存到csv或excel 文件。
5. 用pandas提供的函数和方法进行数据分析：
6. 保存到sqlite3数据库
import sqlite3
with sqlite3.connect(‘gzccnewsdb.sqlite‘) as db:
df3.to_sql(‘gzccnews05‘,con = db, if_exists=‘replace‘)
7. 从sqlite3读数据
with sqlite3.connect(‘gzccnewsdb.sqlite‘) as db:
df2 = pandas.read_sql_query(‘SELECT * FROM gzccnews05‘,con=db)
print(df2)
8. df保存到mysql数据库
安装SQLALchemy
安装PyMySQL
MySQL里创建数据库：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里查看已保存了数据。（通过MySQL Client或Navicate。）
1.def writeNewsDetail(content):
f = open(‘gzccnews.txt‘, ‘a‘, encoding=‘utf-8‘)
f.write(content)
f.close()
2.def getNewsDetail(url):
resd = requests.get(url)
resd.encoding = ‘utf-8‘
soupd = BeautifulSoup(resd.text,‘html.parser‘)
# print(resd.text)
news = {}
# 标题
news[‘title‘] = soupd.select(‘.show-title‘)[0].text
# 时间
info = soupd.select(‘.show-info‘)[0].text
# print(info)
news[‘time‘] = datetime.strptime(info.lstrip(‘发布时间:‘)[0:19],‘%Y-%m-%d %H:%M:%S‘)
# print(news[‘time‘])
# 来源
if info.find(‘来源：‘)>0:
news[‘source‘] = info[info.find(‘来源：‘):].split()[0].lstrip(‘来源：‘)
else:
news[‘source‘] = ‘none‘
# 点击次数
news[‘clickCount‘] = int(getClickCount(url))
news[‘newsUrl‘] = url
# print(clickCount)
# print(‘标题：‘ + ti + ‘ 时间：‘ + tim + ‘ 来源：‘ + source + ‘ 点击次数：‘ + clickCount + ‘ 链接: ‘ + url)
# 正文
# print(‘正文:‘)
news[‘content‘] = soupd.select(‘.show-content‘)[0].text.strip()
# cl = tuple(content)
# df = cl.__str__()
# print(news[‘content‘])
writeNewsDetail(news[‘content‘])
return(news)
# for c in content:
# print(c)
3.import pandas
newstotal = [{}]
df = pandas.DataFrame(newstotal)
4.import openpyxl
# 导入excel文件
df.to_excel(‘gzccnews.xlsx‘)
5.print(df[[‘title‘,‘clickCount‘,‘source‘]][:6])
print(df[(df[‘clickCount‘]>3000)&(df[‘source‘]==‘学校综合办‘)])
sou = [‘国际学院‘,‘学生工作处‘]
print(df[df[‘source‘].isin(sou)])
dftime = df.set_index(‘time‘)
print(dftime[‘2018-03‘])
6.import sqlite3
with sqlite3.connect("gzccdb.sqlite") as db:
df1.to_sql(‘gzccdb01‘,con=db,if_exists=‘replace‘)
with sqlite3.connect("gzccdb.sqlite") as db:
df2 = pandas.read_sql_query("select *from gzccdb01",con=db)
print("df2: \n",df2)
7.import pymysql
from sqlalchemy import create_engine
coon = create_engine(‘mysql+pymysql://root:root@localhost:3306/gzccnews?charset=utf8‘)
pandas.io.sql.to_sql(df3,"gzccnews",con=coon,if_exists=‘replace‘)
原文：https://www.cnblogs.com/xiaozheng303/p/8877277.html