使用beautifulsoup与requests爬取数据

sudo service mongod start
sudo service mongod stop
sudo service mongod restart

# network interfaces
net:
  port: 27017
#  bindIp: 127.0.0.1

import requests
from bs4 import BeautifulSoup
import time
import pymongo
import random
from multiprocessing import Pool
# 导入多个对象或者函数用逗号分开
# from test_parsing import get_items,url_list

# mongodb客户端
client = pymongo.MongoClient(‘192.168.1.101‘,27017)
# 数据库
test = client[‘testdata‘]
# 各种表
tb = test[‘testtable‘]
mb= test[‘itemtable‘]
detail= test[‘detailtable‘]

headers  = {
User-Agent:
    ‘User-Agent‘:‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36‘,
    ‘Connection‘:‘keep-alive‘
}


proxy_list = [
    ‘http://118.79.27.123:8081‘,
    ‘http://113.108.253.195:9797‘,
    ]

# 随机获取代理ip
proxy_ip = random.choice(proxy_list) 
proxies = {‘http‘: proxy_ip}

# 简单用例
def get_pages_within(pagenums):
    for page_num in range(1,pagenums+1):
        # 请求
        wb_data = requests.get(‘http://urldata/test/pn{}/‘.format(page_num))
        # 包装一个对象
        soup = BeautifulSoup(wb_data.text,‘lxml‘)
        # 使用select方法，参数为样式选择器，div.price_li > span 标识逐层级关系，div.price_li span 只是简单的包含关系        
        numbers = soup.select(‘div.number‘)
        prices = soup.select(‘span.price‘)
        
        links = soup.select(‘a.t‘)

        for number, price, link in zip(numbers,prices,links):             
            if int(price.get_text()) > 500:
                print(number,price)
            data = {
                ‘title‘:number.get_text(),
                ‘price‘:price.get_text(),
                ‘link‘ :link.get(‘href‘)
            }
            tb.insert_one(data)
        print(‘finished‘)

# 复杂点的
def get_links_from(source, pages, flag=‘c‘):
    list_view = ‘{}{}{}/‘.format(source, str(flag), str(pages))
    # 带参数
    wb_data = requests.get(list_view,headers=headers,proxies=proxies)
    soup = BeautifulSoup(wb_data.text, ‘lxml‘)
    if soup.find(‘ul‘, ‘pageLink‘):
        for link in soup.select(‘.fenlei dt a‘):
            item_link = link.get(‘href‘)
            mb.insert_one({‘url‘: item_link})
            print(item_link)
            
    else:
        pass


def get_detail_from(url,data=None):
    wb_data = requests.get(url,headers=headers)
    time.sleep(1)
    # flag = ‘flagnumber‘ in soup.find(‘script‘, type="text/javascript").get(‘src‘).split(‘/‘)
    # if flag: 
    if wb_data.status_code == 404:    
        pass
    else:
        soup = BeautifulSoup(wb_data.text, ‘lxml‘)
        data = {
            ‘title‘:soup.title.text.strip(),
            ‘price‘:soup.select(‘div.price_li > span > i‘)[0].text.strip(),
            ‘time‘:soup.select(‘.pubtime‘)[0].text.strip().split(‘/‘)[0],
            ‘area‘:list(map(lambda x:x.text,soup.select(‘ul.area-infor > li > a‘))),
            ‘cates‘:list(soup.select(‘div.cates > span > i‘)[0].stripped_strings),
            ‘url‘:url
        }       
        detail.insert_one(data)

source_list = ‘‘‘
http://test.com/books/
http://test.com/pictures/
‘‘‘

# 读取数据
# $lt/$lte/$gt/$gte/$ne，依次等价于</<=/>/>=/!=。（l表示less g表示greater e表示equal n表示not  ）
for item in detail.find({‘price‘: {‘$lt‘: 100}}):
    print(item)
    
for i in detail.find():
    if i[‘price‘] >= 500:
        print(i)

if __name__ == ‘__main__‘:
    # 使用多进程
    pool = Pool()
    # pool = Pool(processes=2)
    if source_list is not None:
        pool.map(get_links_from,source_list.split())
    
    pool.close()
    pool.join()