数据结构化与保存

Posted 2020-10-31 Polvem

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)])
df1 = df.set_index(‘time‘)
print(df1[‘2018-03‘])