爬取全部的校園新聞

作業要求來自于:https://edu.cnblogs.com/campus/gzcc/GZCC-16SE1/homework/3002

0.從新聞url擷取點選次數，并整理成函數

newsUrl
newsId(re.search())
clickUrl(str.format())
requests.get(clickUrl)
re.search()/.split()
str.lstrip(),str.rstrip()
int
整理成函數
擷取新聞釋出時間及類型轉換也整理成函數

1.從新聞url擷取新聞詳情：字典,anews

import pandas
import requests
from bs4 import BeautifulSoup
from datetime import datetime
import re

def click(url):
    id = re.findall('(\d{1,5})',url)[-1]#傳回所有比對的字元串的字元串清單的最後一個
    clickUrl = 'http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80'.format(id)
    resClick = requests.get(clickUrl)
    newsClick = int(resClick.text.split('.html')[-1].lstrip("('").rstrip("');"))
    return newsClick
#時間
def newsdt(showinfo):
    newsDate = showinfo.split()[0].split(':')[1]
    newsTime = showinfo.split()[1]
    newsDT = newsDate+' '+newsTime
    dt = datetime.strptime(newsDT,'%Y-%m-%d %H:%M:%S')#轉換成datetime類型
    return dt
#内容
def anews(url):
    newsDetail = {}
    res = requests.get(url)
    res.encoding = 'utf-8'
    soup = BeautifulSoup(res.text,'html.parser')
    newsDetail['newsTitle'] = soup.select('.show-title')[0].text#題目
    showinfo = soup.select('.show-info')[0].text
    newsDetail['newsDT'] = newsdt(showinfo)#時間
    newsDetail['newsClick'] = click(newsUrl)#點選次數
    return newsDetail
newsUrl = 'http://news.gzcc.cn/html/2019/xiaoyuanxinwen_0404/11155.html'
print(anews(newsUrl))

anews

2.從清單頁的url擷取新聞url：清單append(字典) alist

import pandas
import requests
from bs4 import BeautifulSoup
from datetime import datetime
import re

def click(url):
    id = re.findall('(\d{1,5})',url)[-1]#傳回所有比對的字元串的字元串清單的最後一個
    clickUrl = 'http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80'.format(id)
    resClick = requests.get(clickUrl)
    newsClick = int(resClick.text.split('.html')[-1].lstrip("('").rstrip("');"))
    return newsClick

def newsdt(showinfo):
    newsDate = showinfo.split()[0].split(':')[1]
    newsTime = showinfo.split()[1]
    newsDT = newsDate+' '+newsTime
    dt = datetime.strptime(newsDT,'%Y-%m-%d %H:%M:%S')#轉換成datetime類型
    return dt

def anews(url):
    newsDetail = {}
    res = requests.get(url)
    res.encoding = 'utf-8'
    soup = BeautifulSoup(res.text,'html.parser')
    newsDetail['newsTitle'] = soup.select('.show-title')[0].text#題目
    showinfo = soup.select('.show-info')[0].text
    newsDetail['newsDT'] = newsdt(showinfo)#時間
    newsDetail['newsClick'] = click(newsUrl)#點選次數
    return newsDetail

def alist(url):
    res = requests.get(listUrl)
    res.encoding = 'utf-8'
    soup = BeautifulSoup(res.text, 'html.parser')
    newsList = []
    for news in soup.select('li'):#擷取li元素
        if len(news.select('.news-list-title'))>0:#如果存在新聞題目
            newsUrl = news.select('a')[0]['href']#擷取新聞的連結
            newsDesc = news.select('.news-list-description')[0].text#擷取摘要文本
            newsDict = anews(newsUrl)#通過連結擷取題目時間點選數
            newsDict['description'] = newsDesc
            newsList.append(newsDict)#把每個新聞的資訊放進字典擴充到清單裡
    return newsList
listUrl = 'http://news.gzcc.cn/html/xiaoyuanxinwen/'
print(alist(listUrl))

alist

3.生成所頁清單頁的url并擷取全部新聞：清單extend(清單) allnews

*每個同學爬學号尾數開始的10個清單頁

def alist(url):
    res=requests.get(listUrl)
    res.encoding='utf-8'
    soup = BeautifulSoup(res.text,'html.parser')
    newsList=[]
    for news in soup.select('li'):
        if len(news.select('.news-list-title'))>0:
            newsUrl=news.select('a')[0]['href']
            newsDesc=news.select('.news-list-description')[0].text
            newsDict=anews(newsUrl)
            newsDict['description']=newsDesc
            newsList.append(newsDict)
    return newsList
listUrl='http://news.gzcc.cn/html/xiaoyuanxinwen/'
alist(listUrl)

allnews=[]
for i in range(40,50):
    listUrl='http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html'.format(i)
    allnews.extend(alist(listUrl))
len(allnews)

4.設定合理的爬取間隔

import time

import random

time.sleep(random.random()*3)

import time
import random
for i in range(5):
    print(i)
    time.sleep(random.random()*3)#沉睡随機數的3倍秒數
print(allnews)

5.用pandas做簡單的資料處理并儲存

儲存到csv或excel檔案

newsdf.to_csv(r'F:\duym\爬蟲\gzccnews.csv')

import pandas as pd
s2 = pd.Series(anews(newsUrl))#一維數組對象
print(s2)
newsdf = pd.DataFrame(allnews)#表格型的資料結構
print(newsdf)
print(newsdf.sort_values(by=['newsDT'],ascending=False))#按更新時間降序排列
print(newsdf.sort_index(by=['newsClick'],ascending=False))#按點選量降序排列

newsdf.to_csv(r'gzccnews.csv')
import sqlite3
with sqlite3.connect('gzccnewsdb.sqlite') as db:
    newsdf.to_sql('gzccnewsdb',db)
with sqlite3.connect('gzccnewsdb.sqlite') as db:
    df2 = pandas.read_sql_query('SELECT * FROM gzccnewsdb',con=db)
print(df2[df2['newsClick']>385])

newsdf.to_csv(r'F:\gzccnews.csv')