作业——08 爬虫综合大作业

作业的要求来自于：https://edu.cnblogs.com/campus/gzcc/GZCC-16SE2/homework/3075

一.把爬取的内容保存取MySQL数据库

import pandas as pd
import pymysql
from sqlalchemy import create_engine
conInfo = "mysql+pymysql://user:passwd@host:port/gzccnews?charset=utf8"
engine = create_engine(conInfo,encoding='utf-8')
df = pd.DataFrame(allnews)
df.to_sql(name = ‘news', con = engine, if_exists = 'append', index = False）

import pandas as pd
import requests
from bs4 import BeautifulSoup
from datetime import datetime
import re
import time
import random
import sqlite3 

import pymysql
from sqlalchemy import create_engine
coninfo='mysql+pymysql://root:lyh0523@localhost:3306/gzccnews?charset=utf8'
engine = create_engine(coninfo,encoding='utf-8')

def click(url):
    id = re.findall('(\d{1,5})',url)[-1]#返回所有匹配的字符串的字符串列表的最后一个
    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
#时间
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')#转换成datetime类型
    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#题目
    showinfo = soup.select('.show-info')[0].text
    newsDetail['newsDT'] = newsdt(showinfo)#时间
    newsDetail['newsClick'] = click(url)#点击次数
    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'):#获取li元素
        if len(news.select('.news-list-title'))>0:#如果存在新闻题目
            newsUrl = news.select('a')[0]['href']#获取新闻的链接
            newsDesc = news.select('.news-list-description')[0].text#获取摘要文本
            newsDict = anews(newsUrl)#通过链接获取题目时间点击数
            newsDict['description'] = newsDesc
            newsList.append(newsDict)#把每个新闻的信息放进字典扩展到列表里
    return newsList

allnews = []
for i in range(59,69):
    listUrl = 'http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html'.format(i)
    allnews.extend(alist(listUrl))

pd.Series(anews)
newsdf=pd.DataFrame(allnews)
for i in range(5):
    print(i)
    time.sleep(random.random()*3)        
    print(newsdf)
    
        
newsdf.to_csv('123.csv')   #在本地项目下生成一个表格存储爬取新闻内容

newsdf.to_sql(name='news',con=engine,if_exists='append',index=False)
conn=pymysql.connect(host='localhost',port=3306,user='root',passwd='lyh0523',db='gzccnews',charset='utf8')

with sqlite3.connect('gzccnewsdb.sqlite') as db:
     newsdf.to_sql('gzccnewsdb',db)    #在本地项目下生成一个数据库存储爬取新闻内容

完整代码