資料結構化與儲存

2022-05-27 18:36:06 字數 4013 閱讀 8229

作業是**同學的，因為沒有對新聞資訊做提取，所有無法新增新聞資訊到字典。已練習pandas庫的相關使用方法，匯出excel檔案。ps：自己的**會盡快修改！

import


requests


from bs4 import


beautifulsoup


from datetime import


datetime


import


re, pandas


#獲取新聞點選次數


defgetnewsid(url):


newsid = re.findall(r'


\_(.*).html


', url)[0][-4:]


clickurl = '


'.format(newsid)


clickres =requests.get(clickurl)


#利用正規表示式獲取新聞點選次數


clickcount = int(re.search("


hits'\).html\('(.*)'\);


", clickres.text).group(1))


return


clickcount


#將新聞正文寫進檔案,不會被覆蓋


defwritenewscontenttofile(content):


f=open('


gzccnews.txt


','a


',encoding='


utf-8')


f.write(content)


f.close()


#獲取新聞細節


defgetnewsdetail(newsurl):


contentlist={}


resd =requests.get(newsurl)


resd.encoding = '


utf-8


'soupd = beautifulsoup(resd.text, '


html.parser')


newsdict ={}


content = soupd.select('


#content


')[0].text


writenewscontenttofile(content)


info = soupd.select('


.show-info


')[0].text


newsdict[


'title


'] = soupd.select('


.show-title


')[0].text


#識別時間格式


date = re.search('


(\d.\d.\d\s\d.\d.\d)


', info).group(1)


#識別乙個至三個資料


if(info.find('


')>0):


newsdict[


'author


'] = re.search('


', info).group(1)


else


:        newsdict[


'author


'] = '


none


'if(info.find('


')>0):


newsdict[


'check


'] = re.search('


', info).group(1)


else


:        newsdict[


'check


'] = '


none


'if(info.find('


')>0):


newsdict[


'sources


'] = re.search('


', info).group(1)


else


:        newsdict[


'sources


'] = '


none


'if (info.find('


攝影：') >0):


newsdict[


'photo


'] = re.search('


攝影：(.*)\s*點


', info).group(1)


else


:        newsdict[


'photo


'] = '


none'#


用datetime將時間字串轉換為datetime型別


newsdict['


datetime


'] = datetime.strptime(date, '


%y-%m-%d %h:%m:%s')


#呼叫getnewsid()獲取點選次數


newsdict['


click


'] =getnewsid(newsurl)


return


newsdict


defgetlistpage(listurl):


res =requests.get(listurl)


res.encoding = '


utf-8


'soup = beautifulsoup(res.text, '


html.parser')


for new in soup.select('li'


):        


if len(new.select('


.news-list-title


')) >0:


title = new.select('


.news-list-title


')[0].text


description = new.select('


.news-list-description


')[0].text


newsurl = new.select('


a')[0]['


href']


list =


print('


'.format(title, description, newsurl))


#呼叫getnewsdetail()獲取新聞詳情


dict =getnewsdetail(newsurl)


total.extend(list)


total =


listurl = '


'getlistpage(listurl)


res =requests.get(listurl)


res.encoding = '


utf-8


'soup = beautifulsoup(res.text, '


html.parser')


listcount = int(soup.select('


.a1')[0].text.rstrip('


條'))//10+1df =pandas.dataframe(total)


df.to_excel(


'newsresult.xlsx')


print(df[['


click


','author


','datetime


','sources


']][(df['


click


']>3000)&(df['


sources


'] == u'


學生處'


)])print(df[(df['


click


'] > 3000) & (df['


sources


'] == '


學校綜合辦


')])


print(df[['


click


', '


author


', '


sources


']].head(6))


news_info = ['


國際學院


', '


學生工作處']


print(df[df['


sources


'].isin(news_info)])

資料結構化與儲存

1.將新聞的正文內容儲存到文字檔案。soup beautifulsoup res.text,html.parser content soup.select show content 0 text f open news.txt w encoding utf 8 f.write content f.c...

資料結構化與儲存

1.將新聞的正文內容儲存到文字檔案。newscontent soup.select show content 0 text f open news.txt w f.write newscontent f open news.txt r print f.read 3.安裝pandas，用pandas....

資料結構化與儲存

1.將新聞的正文內容儲存到文字檔案。f open content.txt a encoding utf 8 f.write content f.close 2.將新聞資料結構化為字典的列表 獲取新聞詳情 defgetnewdetail url resd requests.get url resd.e...