scrapy 框架抓取藝龍酒店（熱門城市酒店信息）

一、scrapy框架

---

Spiders文件-

Yi_long.py

import requests
import re
import time
import json


class Yi_long():
    def __init__(self):
        headers = {
            "Accept": "application/json, text/javascript, */*; q=0.01",
            "Accept-Encoding": "gzip, deflate",
            "Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8",
            "Cache-Control": "no-cache",
            "Host": "www.elong.com",
            "Referer": "http://www.elong.com/",
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36",
        }
        city_name_url = 'http://www.elong.com/ajax/search/stayincity?_=1565849748672'
        #http://hotel.qunar.com/render/hoteldiv.jsp?&__jscallback=XQScript_8
        session = requests.Session()
        response = session.get(city_name_url, headers = headers,verify=False)
        # response.encoding = 'utf-8'
        self.city_list = json.loads(response.text)
        # 熱點城市
        self.hotCityList = self.city_list["hotCityList"]
        # print(self.hotCityList)
        # self.hotelCityList = self.city_list["hotelCityList"]
        # print(hotelCityList)
        with open('D:/Scrapywork/elong_hotels_master/all_city.txt', 'w',encoding='utf-8') as f:
            f.write(json.dumps(self.hotCityList))
            # f.write(json.dumps(self.hotelCityList))


    def get_url(self):
        url = 'http://hotel.elong.com/search/list_cn_%s.html'
        # 熱點城市
        for cityId in self.hotCityList:
        # for cityId in self.hotelCityList:
            yield url % (cityId["cityId"])



        with open(r'D:/Scrapywork/elong_hotels_master/all_city.txt','r',encoding='utf-8') as f:
            cold_city_list = f.read()
            # print(type(cold_city_list))
        for cityid in (json.loads(cold_city_list)):
            # print(cityid["cityId"])
            if cityid not in self.hotCityList:
            # if cityid not in self.hotelCityList:
                yield url % (cityid["cityId"])


    def get_cold_city(self):
        pass


if __name__ == '__main__':
    Yilong = Yi_long()
    city_list = Yilong.get_url()
    for city in city_list:
        print(city)

---

 elong.py

# -*- coding: utf-8 -*-
import scrapy
import requests
import re
from .yi_long import Yi_long
from scrapy import Request


class ElongSpider(scrapy.Spider):
    name = 'elong'
    allowed_domains = ['www.elong.com']
    start_urls = ['http://www.elong.com/']

    def start_requests(self):
        Yilong = Yi_long()
        urls = Yilong.get_url()
        for url in urls:
            headers = {
                "Accept": "application/json, text/javascript, */*; q=0.01",
                "Accept-Encoding": "gzip, deflate",
                "Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8",
                "Content-Type": "application/x-www-form-urlencoded; charset=UTF-8",
                "Host": "hotel.elong.com",
                "Origin": "http://hotel.elong.com",
                "Pragma": "no-cache",
                "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36",
                "X-Requested-With": "XMLHttpRequest",
            }

            yield Request(url, callback=self.parse) #headers=headers,data=data,


# {"city": "上海", "hotelname": "上海大飯店", "hoteladdress": "徐家彙路679-1號", "score": "4.5", "comment": "6014", "price": "350"},
    def parse(self, response):
        # result =response.text
        city = response.xpath('//div[@data-wrap="cityWrap"]/label/input/@citynamecn').extract()[0]
        hotelname = re.compile('data-hotelname="(.*?)"').findall(response.text)
        # print(hotelname)
        hoteladdress = re.compile('data-hoteladdress="(.*?)"').findall(response.text)
        # print(hoteladdress) <span class="c555 block mt5" data-score="4.1">共<b>365</b>條點評</span>
        # score = re.compile('data-score="(\d+?)"').findall(response.text)
        score = re.compile('<i class="t20 c37e">(.*?)&nbsp;</i>').findall(response.text)
        # print("score", score)
        comment = response.xpath('//div[@class="h_info_comt"]/a/span[2]/b/text()').extract()
        # print("comment ",comment)  # 共954條點評
        price = re.compile('<span class="h_pri_num ">(\d+?)</span>').findall(response.text)
        # print("price",price)
        yield {"city": city,'hotelname': hotelname,'hoteladdress': hoteladdress, 'score': score,'comment':comment,'price':price}

---

item.py

# -*- coding: utf-8 -*-

# Define here the models for your scraped items
#
# See documentation in:
# https://doc.scrapy.org/en/latest/topics/items.html

import scrapy


class ElongHotelsMasterItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()


    pass

---

middlewares.py

---

# -*- coding: utf-8 -*-

# Define here the models for your spider middleware
#
# See documentation in:
# https://doc.scrapy.org/en/latest/topics/spider-middleware.html

from scrapy import signals


class ElongHotelsMasterSpiderMiddleware(object):
    # Not all methods need to be defined. If a method is not defined,
    # scrapy acts as if the spider middleware does not modify the
    # passed objects.

    @classmethod
    def from_crawler(cls, crawler):
        # This method is used by Scrapy to create your spiders.
        s = cls()
        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
        return s

    def process_spider_input(self, response, spider):
        # Called for each response that goes through the spider
        # middleware and into the spider.

        # Should return None or raise an exception.
        return None

    def process_spider_output(self, response, result, spider):
        # Called with the results returned from the Spider, after
        # it has processed the response.

        # Must return an iterable of Request, dict or Item objects.
        for i in result:
            yield i

    def process_spider_exception(self, response, exception, spider):
        # Called when a spider or process_spider_input() method
        # (from other spider middleware) raises an exception.

        # Should return either None or an iterable of Response, dict
        # or Item objects.
        pass

    def process_start_requests(self, start_requests, spider):
        # Called with the start requests of the spider, and works
        # similarly to the process_spider_output() method, except
        # that it doesn’t have a response associated.

        # Must return only requests (not items).
        for r in start_requests:
            yield r

    def spider_opened(self, spider):
        spider.logger.info('Spider opened: %s' % spider.name)


class ElongHotelsMasterDownloaderMiddleware(object):
    # Not all methods need to be defined. If a method is not defined,
    # scrapy acts as if the downloader middleware does not modify the
    # passed objects.

    @classmethod
    def from_crawler(cls, crawler):
        # This method is used by Scrapy to create your spiders.
        s = cls()
        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
        return s

    def process_request(self, request, spider):
        # Called for each request that goes through the downloader
        # middleware.

        # Must either:
        # - return None: continue processing this request
        # - or return a Response object
        # - or return a Request object
        # - or raise IgnoreRequest: process_exception() methods of
        #   installed downloader middleware will be called
        return None

    def process_response(self, request, response, spider):
        # Called with the response returned from the downloader.

        # Must either;
        # - return a Response object
        # - return a Request object
        # - or raise IgnoreRequest
        return response

    def process_exception(self, request, exception, spider):
        # Called when a download handler or a process_request()
        # (from other downloader middleware) raises an exception.

        # Must either:
        # - return None: continue processing this exception
        # - return a Response object: stops process_exception() chain
        # - return a Request object: stops process_exception() chain
        pass

    def spider_opened(self, spider):
        spider.logger.info('Spider opened: %s' % spider.name)

---

# -*- coding: utf-8 -*-

# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html
import json
import datetime
import os
import pymongo



class ElongHotelsMasterPipeline(object):

    def open_spider(self, spider):
        today = datetime.datetime.now().strftime('%Y%m%d')
        self.path = r'json/%s' % today
        if not os.path.exists(self.path):
            os.makedirs(self.path)

        self.client = pymongo.MongoClient()
        self.db = self.client.elong
        self.collection = self.db[today]

    def close_spider(self, spider):
        self.db.close()
        self.client.close()

    def process_item(self, item, spider):
        self.write_in_json(item)

        return item

    def write_in_mongo(self, hotel_info):

        self.collection.insert(hotel_info)

    # {"city": "上海", "hotelname": "上海大飯店", "hoteladdress": "徐家彙路679-1號", "score": "4.5", "comment": "共6014條點評", "price": "350"},
    def write_in_json(self, item):
        if item['city']:
            city = item['city']
            hotelname = item['hotelname']
            hoteladdress = item['hoteladdress']
            score = item['score']
            comment = item['comment']
            price= item['price']
            print(city)
            with open(os.path.join(self.path, city) + '.json', 'w', encoding='utf-8') as fp:
                fp.write('{')
                for i, hotel in enumerate(hotelname):
                    hotel_info = {
                        "city": city,
                        "hotelname": hotel,
                        "hoteladdress": hoteladdress[i],
                        "score": score[i],
                        "comment": comment[i],
                        "price": price[i]
                    }
                    fp.write(json.dumps(hotel_info, ensure_ascii=False) + ',\n')
                    self.write_in_mongo(hotel_info)
                fp.write('}')

---

settings.py

# -*- coding: utf-8 -*-

# Scrapy settings for elong_hotels_master project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
#     https://doc.scrapy.org/en/latest/topics/settings.html
#     https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#     https://doc.scrapy.org/en/latest/topics/spider-middleware.html

BOT_NAME = 'elong_hotels_master'

SPIDER_MODULES = ['elong_hotels_master.spiders']
NEWSPIDER_MODULE = 'elong_hotels_master.spiders'


# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'elong_hotels_master (+http://www.yourdomain.com)'

# Obey robots.txt rules
ROBOTSTXT_OBEY = False

# Configure maximum concurrent requests performed by Scrapy (default: 16)
#CONCURRENT_REQUESTS = 32

# Configure a delay for requests for the same website (default: 0)
# See https://doc.scrapy.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
DOWNLOAD_DELAY = 2
# The download delay setting will honor only one of:
#CONCURRENT_REQUESTS_PER_DOMAIN = 16
#CONCURRENT_REQUESTS_PER_IP = 16

# Disable cookies (enabled by default)
#COOKIES_ENABLED = False

# Disable Telnet Console (enabled by default)
#TELNETCONSOLE_ENABLED = False

# Override the default request headers:
DEFAULT_REQUEST_HEADERS = {
  'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
#   'Accept-Language': 'en',
}

# Enable or disable spider middlewares
# See https://doc.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
#    'elong_hotels_master.middlewares.ElongHotelsMasterSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'elong_hotels_master.middlewares.ElongHotelsMasterDownloaderMiddleware': 543,
#}

# Enable or disable extensions
# See https://doc.scrapy.org/en/latest/topics/extensions.html
#EXTENSIONS = {
#    'scrapy.extensions.telnet.TelnetConsole': None,
#}

# Configure item pipelines
# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
# MONGO_URI = '127.0.0.1'
# MONGO_PORT = 27017
# MONGO_DATABASE = 'elong'
# COLLECTION_NAME = 'yi_long_hotel'

ITEM_PIPELINES = {
   'elong_hotels_master.pipelines.ElongHotelsMasterPipeline': 300,
}

# Enable and configure the AutoThrottle extension (disabled by default)
# See https://doc.scrapy.org/en/latest/topics/autothrottle.html
AUTOTHROTTLE_ENABLED = True
# The initial download delay
AUTOTHROTTLE_START_DELAY = 5
# The maximum download delay to be set in case of high latencies
AUTOTHROTTLE_MAX_DELAY = 60
# The average number of requests Scrapy should be sending in parallel to
# each remote server
#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
# Enable showing throttling stats for every response received:
#AUTOTHROTTLE_DEBUG = False

# Enable and configure HTTP caching (disabled by default)
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
#HTTPCACHE_ENABLED = True
#HTTPCACHE_EXPIRATION_SECS = 0
#HTTPCACHE_DIR = 'httpcache'
#HTTPCACHE_IGNORE_HTTP_CODES = []
#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'

---

 

run_elong.py

from scrapy.cmdline import execute
execute(['scrapy','crawl','elong'])

---

返回結果：