No.5 爬虫学习——MongoDB爬虫实践：虎扑论坛(唐松编《Python网络爬虫从入门到实践》P116-123)

题目：获取虎扑步行街论坛上所有帖子的数据，内容包括帖子名称、帖子链接、作者、作者链接、创建时间、回复数、浏览数、最后回复用户和最后回复时间，网络地址为：https://bbs.hupu.com/bxj

使用mysql作为数据存储器，完整代码如下：

import requests
from bs4 import BeautifulSoup
import pymysql
import time


headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.149 Safari/537.36'
}

data_list = []

def get_info(url):
    html = requests.get(url,headers=headers)
    soup = BeautifulSoup(html.text,'lxml')
    names = soup.select('div > div.post-title > a')
    authors = soup.select('div > div.post-auth > a')
    times = soup.select('div > div.post-time')
    replys = soup.select('div > div.post-datum')
    for name,author,posttime,reply in zip(names,authors,times,replys):
        data = {
            'nameik':'https://bbs.hupu.com'+name['href'],
            'name':name.get_text().strip(),
            'author':author.get_text().strip(),
            'authorik':author['href'],
            'posttime':posttime.get_text().strip(),
            'reply':reply.get_text().strip().split('/')[0],
            'reading':reply.get_text().strip().split('/')[1]
        }
        print(data)
        data_list.append(data)
        
'''
建表语句
CREATE TABLE `hupuss` (
  `nameik` varchar(200) DEFAULT NULL,
  `name` varchar(200) DEFAULT NULL,
  `author` varchar(200) DEFAULT NULL,
  `authorik` varchar(200) DEFAULT NULL,
  `posttime` varchar(200) DEFAULT NULL,
  `reply` varchar(200) DEFAULT NULL,
  `reading` varchar(200) DEFAULT NULL
) ENGINE=InnoDB DEFAULT CHARSET=utf8

'''
        

def get_sql(data_list):
    data = data_list[0]  
    cols = ", ".join('`{}`'.format(k) for k in data.keys())  
    val_cols = ', '.join('%({})s'.format(k) for k in data.keys())  
    sql = """
    INSERT INTO hupu(%s) VALUES(%s)
    """ % (cols, val_cols)
    return sql

def get_mysql():
    conn = pymysql.connect(host='localhost', user='root', passwd='123456', db='mydb', port=3306, charset='utf8')
    cursor = conn.cursor()
    sql = get_sql(data_list)
    cursor.executemany(sql,data_list)
    conn.commit()
    
if __name__ == '__main__':
    urls = ['https://bbs.hupu.com/bxj-{}'.format(str(i)) for i in range(0,11)]
    for url in urls:
        get_info(url)
        time.sleep(2)
    get_mysql()
    

使用mongoDB存储数据代码如下：

import requests
from bs4 import BeautifulSoup
import pymongo
import time

client = pymongo.MongoClient('localhost', 27017)
mydb = client['mydb']
hupustreet = mydb['hupu']

headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.149 Safari/537.36'
}

def get_info(url):
    html = requests.get(url,headers=headers)
    soup = BeautifulSoup(html.text,'lxml')
    names = soup.select('div > div.post-title > a')
    authors = soup.select('div > div.post-auth > a')#名称、链接
    times = soup.select('div > div.post-time')
    replys = soup.select('div > div.post-datum')
    for name,author,posttime,reply in zip(names,authors,times,replys):
        data = {
            '帖子链接':'https://bbs.hupu.com'+name['href'],
            '帖子名称':name.get_text().strip(),
            '作者':author.get_text().strip(),
            '作者链接':author['href'],
            '创建时间':posttime.get_text().strip(),
            '回复数':reply.get_text().strip().split('/')[0],
            '浏览数':reply.get_text().strip().split('/')[1]
        }
        print(data)
        hupustreet.insert_one(data)

if __name__ == '__main__':
    urls = ['https://bbs.hupu.com/bxj-{}'.format(str(i)) for i in range(0,11)]
    for url in urls:
        get_info(url)
        time.sleep(2)