爬虫综合大作业

可以用pandas读出之前保存的数据：

newsdf = pd.read_csv(r'F:\duym\gzccnews.csv')

 

一.把爬取的内容保存到数据库sqlite3

import sqlite3
with sqlite3.connect('gzccnewsdb.sqlite') as db:
newsdf.to_sql('gzccnews',con = db)

with sqlite3.connect('gzccnewsdb.sqlite') as db:
df2 = pd.read_sql_query('SELECT * FROM gzccnews',con=db)

 

保存到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）

 作为一名爱运动的男生，我选择爬取的是季后赛nba新闻

这是生成爬虫的代码

def creat_bs(url):
    result = requests.get(url)
    e=chardet.detect(result.content)['encoding']
    #set the code of request object to the webpage's code
    result.encoding=e
    c = result.content
    soup =BeautifulSoup(c,'lxml')
    return soup

　　构建要获取网页的集合函数

def build_urls(prefix,suffix):
    urls=[]
    for item in suffix:
        url=prefix+item
        urls.append(url)
    return urls

　　爬取函数

def find_title_link(soup):
    titles=[]
    links=[]
    try:
        contanier=soup.find('div',{'class':'container_padd'})
        ajaxtable=contanier.find('form',{'id':'ajaxtable'})
        page_list=ajaxtable.find_all('li')
        for page in page_list:
            titlelink=page.find('a',{'class':'truetit'})
            if titlelink.text==None:
                title=titlelink.find('b').text
            else:
                title=titlelink.text
            if np.random.uniform(0,1)>0.90:
                link=titlelink.get('href')
                titles.append(title)
                links.append(link)
    except:
        print('have no value')
    return titles,links

　　保存数据

wordlist=str()
for title in title_group:
    wordlist+=title

for reply in reply_group:
    wordlist+=reply

def savetxt(wordlist):
    f=open('wordlist.txt','wb')
    f.write(wordlist.encode('utf8'))
    f.close()
savetxt(wordlist)

　　生成的词云