数据结构化与保存

import requests
import re
from bs4 import BeautifulSoup


def uslHtml(url):
    res = requests.get(url)
    res.encoding = "utf-8"
    soup = BeautifulSoup(res.text, "html.parser")
    return soup
def page(url):
   soup = uslHtml(url)
   newsList = soup.select(".news-list")[0].select("li")
   for aList in newsList:
      a = aList.select("a")[0].attrs["href"]
      number = re.search("_(\d+)/(\d+)",a).group(0)
      ress = requests.get(a)
      ress.encoding="utf-8"
      soup1 = BeautifulSoup(ress.text,"html.parser")
      content = soup1.select("#content")[0].text
      f.write(content)
      print(content)
so = uslHtml("http://news.gzcc.cn/html/xiaoyuanxinwen/")
n = int(so.select("#pages")[0].select(".a1")[0].text.strip("条"))
n=int(n/10)+1
f = open("SchoolNews.txt","a+",encoding='utf-8')
page("http://news.gzcc.cn/html/xiaoyuanxinwen/")
for i in range(2,3):
    url1 = "http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html".format(i);
    page(url1)
f.close()

　　

2.

def Url(newsUrl):
  re = requests.get(newsUrl)
  re.encoding="utf-8"
  soup = BeautifulSoup(re.text,"html.parser")
  return soup

newsArr= []

def pageNumber():
    soup = Url("http://news.gzcc.cn/html/xiaoyuanxinwen/")
    newsPage = int(soup.select("#pages")[0].select(".a1")[0].text.rstrip("条"))
    newsPage = int((newsPage/10)+1)
    return newsPage

def site():
    newsPage = pageNumber()
    for i in (newsPage,newsPage+1):
        othersUrl = "http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html".format(i)
        soup = Url(othersUrl)
        News(soup)

def News(soup):
    newsList = soup.select(".news-list-text")
    for i in range(len(newsList)):
       dict = {}
       news = newsList[i]
       newsTitle = news.select(".news-list-title")[0].text
       dict["title"] = newsTitle
       newsDescription = news.select(".news-list-description")[0].text
       dict["description"] = newsDescription
       newsArr.insert(len(newsArr),dict)
    print(newsArr)
site()

 

3.

df = pandas.DataFrame(newsArr)
df.to_excel("title.xlsx")

 

 print(df[['click', 'title', 'sources']].head(6))

  print(df[(df['click'] > 3000) & (df['sources'] == '学校综合办')])

  sou = ['国际学院', '学生工作处']
  print(df[df['sources'].isin(sou)])