1.商品爬取

#!/usr/bin/env python
# -*- encoding: utf-8 -*-
# Created on 2019-02-02 08:59:40
# Project: oneDrug from pyspider.libs.base_handler import *
from pymongo import MongoClient
import re class Handler(BaseHandler):
crawl_config = {
} def __init__(self):
self.client = MongoClient('mongodb://localhost:27017')
self.drug = self.client.drug def insert_goods(self, data):
collection = self.drug['goods']
collection.update({'goods_id': data['goods_id']}, data, True) def insert_comments(self, data):
collection = self.drug['comments']
collection.insert_one(data) @every(minutes=24 * 60)
def on_start(self):
self.crawl('https://www.111.com.cn/categories/', callback=self.categories_page, validate_cert=False,
fetch_type='js') @config(age=10 * 24 * 60 * 60)
def categories_page(self, response):
for each in response.doc('.allsort em > a').items():
self.crawl(each.attr.href, callback=self.cagetory_list_page, validate_cert=False, fetch_type='js') @config(priority=1)
def cagetory_list_page(self, response):
for each in response.doc('#itemSearchList a[target="_blank"][class="product_pic pro_img"]').items():
self.crawl(each.attr.href, callback=self.detail_page, validate_cert=False, fetch_type='js')
next = response.doc('#search_table > div.turnPageBottom > a.page_next').attr.href
self.crawl(next, callback=self.cagetory_list_page, validate_cert=False, fetch_type='js') @config(priority=2)
def detail_page(self, response):
goods_id = response.doc('#gallery_view > ul > li.item_number').text()
cagetory_one = response.doc('body > div.wrap.clearfix > div > span:nth-child(3) > a').text()
cagetory_two = response.doc('body > div.wrap.clearfix > div > span:nth-child(5) > a').text()
cagetory_three = response.doc('body > div.wrap.clearfix > div > span:nth-child(7) > a').text()
merchants = response.doc('div.middle_property > span:nth-child(1)').text()
goods_name = response.doc('div.middle_property > h1').text()
goods_desc = response.doc('div.middle_property > span.red.giftRed').text()
goods_price = response.doc(
'div.middle_property > div.shangpin_info > dl:nth-child(2) > dd > span.good_price').text()
total_comments = response.doc('#fristReviewCount > span > a').text() brand = response.doc(
'#tabCon > div:nth-child(1) > div.goods_intro > table > tbody > tr:nth-child(2) > td:nth-child(2)').text()
spec = response.doc(
'#tabCon > div:nth-child(1) > div.goods_intro > table > tbody > tr:nth-child(2) > td:nth-child(4)').text()
weight = response.doc(
'#tabCon > div:nth-child(1) > div.goods_intro > table > tbody > tr:nth-child(3) > td:nth-child(2)').text()
manufacturers = response.doc(
'#tabCon > div:nth-child(1) > div.goods_intro > table > tbody > tr:nth-child(3) > td:nth-child(4)').text()
approval_number = response.doc(
'#tabCon > div:nth-child(1) > div.goods_intro > table > tbody > tr:nth-child(4) > td:nth-child(2)').text()
drug_type = response.doc(
'#tabCon > div:nth-child(1) > div.goods_intro > table > tbody > tr:nth-child(4) > td:nth-child(4)').text() instructions = {}
if response.doc('#prodDetailCotentDiv > table > tbody > tr:nth-child(1) > th').text():
for i in range(3, 22):
instructions_key = \
response.doc('#prodDetailCotentDiv > table > tbody > tr:nth-child({}) > th'.format(i)).text().split(
" ")[0]
instructions_value = response.doc(
'#prodDetailCotentDiv > table > tbody > tr:nth-child({}) > td'.format(i)).text()
instructions[instructions_key] = instructions_value total_comments = response.doc('#itemComments > span').text()
good_comments = response.doc('#productExperience > div > ul > li:nth-child(2) > a > span').text()
mid_comments = response.doc('#productExperience > div > ul > li:nth-child(3) > a > span').text()
bad_comments = response.doc('#productExperience > div > ul > li:nth-child(4) > a > span').text() url_id = re.findall('\d+', response.url)[1] goods_data = {
'url_id': url_id,
'goods_id': goods_id,
'goods_name': goods_name,
'goods_desc': goods_desc,
'goods_price': goods_price,
'merchants': merchants,
'cagetory': {
'': cagetory_one,
'': cagetory_two,
'': cagetory_three
},
'drug_detail': {
'brand': brand,
'spec': spec,
'weight': weight,
'manufacturers': manufacturers,
'approval_number': approval_number,
'drug_type': drug_type
},
'instructions': instructions,
'comments': {
'total_comments': total_comments,
'good_comments': good_comments,
'mid_comments': mid_comments,
'bad_comments': bad_comments
}
}
self.insert_goods(goods_data)

2.评论爬取

from pymongo import MongoClient
import requests
from bs4 import BeautifulSoup
import re
import socket class Drug:
def __init__(self):
self.clint = MongoClient('mongodb://localhost:27017')
self.drug = self.clint.drug
self.collection = self.drug['goods']
self.comm_collection = self.drug['comments'] def dbmodify(self):
for data in self.collection.find({},{"goods_id":1,"goods_price":1}):
try:
_id = data['_id']
id = data['goods_id'].split(":")[1]
price = data['goods_price'].split("¥")[1]
self.collection.update({'_id': _id},{'$set':{'goods_id':id,'goods_price':price}})
print(_id, id, price)
except IndexError:
pass def getBaseArgument(self,goods_id):
base_url = 'https://www.111.com.cn/interfaces/review/list/html.action'
data = {
'goodsId': goods_id,
'pageIndex': 1,
'score': '1&_19020301'
}
try:
self.collection.update_one({'url_id': goods_id}, {'$set': {'commspider': True}})
requests.packages.urllib3.disable_warnings()
requests.adapters.DEFAULT_RETRIES = 5
# 设置连接活跃状态为False
s = requests.session()
s.keep_alive = False
r = s.get(base_url, params=data, timeout = 5,verify=False)
r.close()
soup = BeautifulSoup(r.text, 'html.parser')
if soup.find_all("div", class_="view_no_result"):
return "No Comments!"
else:
total_page_text = soup.find_all(text=re.compile(r'共\d+页'))[0]
pattern = re.compile(r'\d+')
total_page = pattern.findall(total_page_text)
return total_page[0]
except requests.exceptions.RequestException as e:
print(e) def getCommlist(self,goods_id, total_page):
base_url = 'https://www.111.com.cn/interfaces/review/list/html.action'
try:
for i in range(1, int(total_page)):
data = {
'goodsId': goods_id,
'pageIndex': i,
'score': '1&_19020301'
}
try:
requests.packages.urllib3.disable_warnings()
requests.adapters.DEFAULT_RETRIES = 15
# 设置连接活跃状态为False
s = requests.session()
s.keep_alive = False
r = s.get(base_url, params=data, timeout = 5,verify=False)
r.close()
soup = BeautifulSoup(r.text, 'html.parser')
for tr in soup.find_all("tr"):
comments = {}
try:
comments['goodsId'] = goods_id
comments['content'] = tr.find('p').text.strip()
comments['date'] = tr.find('p', attrs={'class': 'eval_date'}).text.strip()
self.comm_collection.insert_one(comments)
except:
print(goods_id + "Have some problem!\n")
print(comments)
except requests.exceptions.RequestException as e:
print(e)
except ValueError:
return "No Comments! Try next!" def getComments(self):
i = 0
goods_list = []
for data in self.collection.find({'commspider': False}, {"url_id"}):
id = data['url_id']
goods_list.append(id)
length = len(goods_list)
print("总共 {} 条商品".format(length))
for good in goods_list:
total_page = self.getBaseArgument(good)
comments = self.getCommlist(good,total_page)
i = i + 1
print("总共 {} 条商品\n目前第 {} 条\n商品编号 {} \n".format(length,i, good))
print(comments) test = Drug().getComments()

基于pydpier爬取1药网(转载)的更多相关文章

  1. Python爬取中国天气网

    Python爬取中国天气网 基于requests库制作的爬虫. 使用方法:打开终端输入 “python3 weather.py 北京(或你所在的城市)" 程序正常运行需要在同文件夹下加入一个 ...

  2. 爬取西刺网的免费IP

    在写爬虫时,经常需要切换IP,所以很有必要自已在数据维护库中维护一个IP池,这样,就可以在需用的时候随机切换IP,我的方法是爬取西刺网的免费IP,存入数据库中,然后在scrapy 工程中加入tools ...

  3. python爬虫基础应用----爬取校花网视频

    一.爬虫简单介绍 爬虫是什么? 爬虫是首先使用模拟浏览器访问网站获取数据,然后通过解析过滤获得有价值的信息,最后保存到到自己库中的程序. 爬虫程序包括哪些模块? python中的爬虫程序主要包括,re ...

  4. selenium爬取煎蛋网

    selenium爬取煎蛋网 直接上代码 from selenium import webdriver from selenium.webdriver.support.ui import WebDriv ...

  5. Scrapy实战篇(一)之爬取链家网成交房源数据(上)

    今天,我们就以链家网南京地区为例,来学习爬取链家网的成交房源数据. 这里推荐使用火狐浏览器,并且安装firebug和firepath两款插件,你会发现,这两款插件会给我们后续的数据提取带来很大的方便. ...

  6. (python爬取小故事网并写入mysql)

    前言: 这是一篇来自整理EVERNOTE的笔记所产生的小博客,实现功能主要为用广度优先算法爬取小故事网,爬满100个链接并写入mysql,虽然CS作为双学位已经修习了三年多了,但不仅理论知识一般,动手 ...

  7. Python Scrapy 爬取煎蛋网妹子图实例(一)

    前面介绍了爬虫框架的一个实例,那个比较简单,这里在介绍一个实例 爬取 煎蛋网 妹子图,遗憾的是 上周煎蛋网还有妹子图了,但是这周妹子图变成了 随手拍, 不过没关系,我们爬图的目的是为了加强实战应用,管 ...

  8. 利用Python网络爬虫爬取学校官网十条标题

    利用Python网络爬虫爬取学校官网十条标题 案例代码: # __author : "J" # date : 2018-03-06 # 导入需要用到的库文件 import urll ...

  9. Python的scrapy之爬取顶点小说网的所有小说

    闲来无事用Python的scrapy框架练练手,爬取顶点小说网的所有小说的详细信息. 看一下网页的构造: tr标签里面的 td 使我们所要爬取的信息 下面是我们要爬取的二级页面 小说的简介信息: 下面 ...

随机推荐

  1. Smarty3——内置函数

    Table of Content {$var} {$append} {assign} {block} {call} {config_load} {debug} {extends} {for} {for ...

  2. css总结13:CSS 伪类(Pseudo-classes)

    1 伪类作用:CSS伪类是用来添加一些选择器的特殊效果. 2 常用示例: 2.1anchor伪类:代码:   正常语法: a{color:#FF0000;}/* 文字颜色 */   伪类语法: a:l ...

  3. ios7适配--uitableviewcell选中效果

    ios7 UITableViewCell selectionStyle won't go back to blue up vote6down votefavorite 2 Xcode 5.0, iOS ...

  4. 设计模式06: Adapter 适配器模式(结构型模式)

    Adapter 适配器模式(结构型模式) 适配(转换)的概念无处不在:电源转接头.电源适配器.水管转接头... 动机(Motivation)在软件系统中,由于应用环境的变化,常常需要将“一些现存的对象 ...

  5. IO流-File,字节流,缓冲流

    1.1 IO概述 回想之前写过的程序,数据都是在内存中,一旦程序运行结束,这些数据都没有了,等下次再想使用这些数据,可是已经没有了.那怎么办呢?能不能把运算完的数据都保存下来,下次程序启动的时候,再把 ...

  6. k8s(未完待续)

    K8s简介Kubernetes(k8s)是自动化容器操作的开源平台,这些操作包括部署,调度和节点集群间扩展. 使用Kubernetes可以  自动化容器的部署和复制  随时扩展或收缩容器规模  将容器 ...

  7. 关于Java中SQL语句的拼接规则

    实现目标语句是这个注意,这里的java变量是idd int idd; String sql = "SELECT id, piUrl FROM picinfos WHERE id BETWEE ...

  8. 洛谷P3254 圆桌问题(最大流)

    传送门 一道良心啊……没那么多麻烦了…… 从$S$向所有单位连边,容量为单位人数,从所有桌子向$T$连边,容量为桌子能坐的人数,从每一个单位向所有桌子连边,容量为$1$,然后跑一个最大流,看一看$S$ ...

  9. ssh免密码登录、secureCRT免密码登录详解

    再放一张真机实现图: 接下来就详细讲述实现细节. 实现过程中吃了不少苦头,这个不对,那个不通.好在慢慢一点点摸索出来了,经验分享在这里. 希望能终结网上ssh免密码登录,以及SecureCRT免密码登 ...

  10. 在makefile通过宏定义来控制源程序的编译

    在Makefile中我们可以通过宏定义来控制源程序的编译.只要在Makefile中的CFLAGS中通过选项-D来指定你于定义的宏即可. 如:CFLAGS += -D _XXX在编译的时候加上此选项就可 ...