数据结构化和保存

def writeNewsDetails(contents):
    f = open('gzccnews.txt', 'a', encoding='utf-8')
    f.write(contents)
    f.close()

  

2. 将新闻数据结构化为字典的列表:

  • 单条新闻的详情-->字典news
  • 一个列表页所有单条新闻汇总-->列表newsls.append(news)
  • 所有列表页的所有新闻汇总列表newstotal.extend(newsls)
import requests
from bs4 import BeautifulSoup
from datetime import datetime
import re
import pandas
import openpyxl
import sqlite3

url = "http://news.gzcc.cn/html/xiaoyuanxinwen/"
res = requests.get(url);
res.encoding = "utf-8"
soup = BeautifulSoup(res.text,"html.parser");

def writeNewsDetails(contents):
    f = open('gzccnews.txt',"a",encoding="utf-8")
    f.write(contents)
    f.close()


def getClickCount(newUrl):
    newsId = re.findall("\_(.*).html",newUrl)[0].split("/")[-1];
    res = requests.get("http://oa.gzcc.cn/api.php?op=count&id= {}&modelid=80".format(newsId))
    return int(res.text.split(".html")[-1].lstrip("('").rsplit("');")[0])


#获取新闻详情
def getNewDetails(newsDetailUrl):
    detail_res = requests.get(newsDetailUrl)
    detail_res.encoding = "utf-8"
    detail_soup = BeautifulSoup(detail_res.text, "html.parser")

    news={}
    news['title'] = detail_soup.select(".show-title")[0].text
    info = detail_soup.select(".show-info")[0].text
    news['date_time'] = datetime.strptime(info.lstrip('发布时间:')[: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'] = detail_soup.select("#content")[0].text
    writeDetailNews(news['content'])
    news['click'] = getClickCount(newsDetailUrl)
    return news
    # print(news)

# 获取总页数
def getPageN(url):
    res = requests.get(url)
    res.encoding = 'utf-8'
    soup = BeautifulSoup(res.text, 'html.parser')
    return int(soup.select(".a1")[0].text.rstrip("条"))//10+1

# 获取新闻一页的所有信息
def getListPage(url):
   newsList = []
   for news in soup.select("li"):
        if len(news.select(".news-list-title"))>0:  #排除为空的li
            # time = news.select(".news-list-info")[0].contents[0].text
            # title = news.select(".news-list-title")[0].text
            # description = news.select(".news-list-description")[0].text
            detail_url = news.select('a')[0].attrs['href']
            newsList.append(getNewDetails(detail_url))
            return newsList

newsTotal = []
totalPageNum = getPageN(url)
firstPageUrl = "http://news.gzcc.cn/html/xiaoyuanxinwen/"
newsTotal.extend(getListPage(firstPageUrl))

for num in range(totalPageNum,totalPageNum+1):
        listpageurl="http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html".format(num)
        getListPage(listpageurl)

print(newsTotal)

  

3. 安装pandas,用pandas.DataFrame(newstotal),创建一个DataFrame对象df.

df = pandas.DataFrame(newsTotal)
print(df)

  

4. 通过df将提取的数据保存到csv或excel 文件。

df.to_excel('gzcss.xlsx')

 

5. 用pandas提供的函数和方法进行数据分析:

  • 提取包含点击次数、标题、来源的前6行数据
  • 提取‘学校综合办’发布的,‘点击次数’超过3000的新闻。
  • 提取'国际学院'和'学生工作处'发布的新闻。
  • 进取2018年3月的新闻
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)])

# 进取2018年3月的新闻
df1 = df.set_index('time')
print(df1['2018-03'])

  

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。)

posted @ 2018-04-17 21:55  247李嘉嘉  阅读(194)  评论(0编辑  收藏  举报