红亚华宇杯爬虫

1、导入第三方库

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

2、获取网页内容

def fetchURL(url):
    headers = {
        'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.212 Safari/537.36',
    }
    
    try:
        r = requests.get(url,headers=headers)
        r.raise_for_status()
        return r.text
    except requests.HTTPError as e:
        print(e)
        print("HTTPError")
    except requests.RequestException as e:
        print(e)
    except:
        print("Unknown Error !")

3、解析网页内容

def parserHtml(html):
    soup = BeautifulSoup(html,"html.parser")
    tbodys = soup.find_all('tbody')
    data = []
 
    for i in range(1,len(tbodys)):
        comment = tbodys[i]
        try:
            ci = comment.cite.a['href']
            uid = re.findall(r"(\d+)",ci)[0]
        except:
            uid = None
        tmp = comment.find(onclick="atarget(this)")
        title = tmp.string
        tid = re.findall(r"(\d+)",tmp['href'])[0]
        co = {
            'tid':tid,
            'title':title,
            'uid':uid
        }
        data.append(co)
    return pd.DataFrame(data)

4、存储爬取信息

def save_file(data_df):
    data_df.to_csv('/root/discuz_result.txt', mode='a',encoding='utf_8_sig',header = False,index=False) 
    print("successed")

5、主函数

if __name__ == '__main__':
    for i in range(1,20):
        url = 'https://www.discuz.net/forum-developer-{}.html'.format(i)
        html = fetchURL(url)
        data = parserHtml(html)
        save_file(data)
        time.sleep(random.randint(1,3))        
    print("All successed ")

7、将数据存入数据库

create database hive_db;
use hive_db;
create table crawl_discuz(tid int,title string,uid int)row format delimited fields terminated by ',';

load data local inpath '/root/discuz_result.txt' into table crawl_discuz;