python爬取大众点评并写入mongodb数据库和redis数据库
抓取大众点评首页左侧信息,如图:
我们要实现把中文名字都存到mongodb,而每个链接存入redis数据库。
因为将数据存到mongodb时每一个信息都会有一个对应的id,那样就方便我们存入redis可以不出错。
# -*- coding: utf-8 -*- import re from urllib.request import urlopen from urllib.request import Request from bs4 import BeautifulSoup from lxml import etree import pymongo client = pymongo.MongoClient(host="127.0.0.1") db = client.dianping #库名dianping collection = db.classification #表名classification import redis #导入redis数据库 r = redis.Redis(host='127.0.0.1', port=6379, db=0) # client = pymongo.MongoClient(host="192.168.60.112") # myip = client['myip'] # 给数据库命名 def secClassFind(selector, classid): secItems = selector.xpath('//div[@class="sec-items"]/a') for secItem in secItems: url = secItem.get('href') #得到url title = secItem.text classid = collection.insert({'classname': title, 'pid': classid}) classurl = '%s,%s' % (classid, url) #拼串 r.lpush('classurl', classurl) #入库 def Public(url): headers = {'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.1.6) Gecko/20091201 Firefox/3.5.6'} #协议头 req_timeout = 5 req = Request(url=url, headers=headers) f = urlopen(req, None, req_timeout) s = f.read() s = s.decode("utf-8") # beautifulsoup提取 soup = BeautifulSoup(s, 'html.parser') links = soup.find_all(name='li', class_="first-item") for link in links: selector = etree.HTML(str(link)) # indexTitleUrls = selector.xpath('//a[@class="index-title"]/@href') # # 获取一级类别url和title # for titleurl in indexTitleUrls: # print(titleurl) indexTitles = selector.xpath('//a[@class="index-title"]/text()') for title in indexTitles: # 第二级url print(title) classid = collection.insert({'classname': title, 'pid': None}) secClassFind(selector, classid) print('---------') # secItems = selector.xpath('//div[@class="sec-items"]/a') # for secItem in secItems: # print(secItem.get('href')) # print(secItem.text) print('-----------------------------') # # myip.collection.insert({'name':secItem.text}) # r.lpush('mylist', secItem.get('href')) # collection.find_one({'_id': ObjectId('5a14c8916d123842bcea5835')}) # connection = pymongo.MongoClient(host="192.168.60.112") # 连接MongDB数据库 # post_info = connection.myip # 指定数据库名称(yande_test),没有则创建 # post_sub = post_info.test # 获取集合名:test Public('http://www.dianping.com/')