first commit

.gitignore

@@ -0,0 +1,3 @@
+__pycache__
+.venv
+cars.jl

README.md

@@ -0,0 +1,7 @@
+## Installition
+pip install scrapy<br />
+set last_page in post_scrape/spiders/car_spider.py
+
+## Run
+cd src/<br />
+scrapy crawl car -O cars.jl

src/post_scrape/items.py

@@ -0,0 +1,12 @@
+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class PostScrapeItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    pass

src/post_scrape/middlewares.py

@@ -0,0 +1,103 @@
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/spider-middleware.html
+
+from scrapy import signals
+
+# useful for handling different item types with a single interface
+from itemadapter import is_item, ItemAdapter
+
+
+class PostScrapeSpiderMiddleware:
+    # 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, 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 Request 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 PostScrapeDownloaderMiddleware:
+    # 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)

src/post_scrape/pipelines.py

@@ -0,0 +1,13 @@
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: https://docs.scrapy.org/en/latest/topics/item-pipeline.html
+
+
+# useful for handling different item types with a single interface
+from itemadapter import ItemAdapter
+
+
+class PostScrapePipeline:
+    def process_item(self, item, spider):
+        return item

src/post_scrape/settings.py

@@ -0,0 +1,88 @@
+# Scrapy settings for post_scrape project
+#
+# For simplicity, this file contains only settings considered important or
+# commonly used. You can find more settings consulting the documentation:
+#
+#     https://docs.scrapy.org/en/latest/topics/settings.html
+#     https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+#     https://docs.scrapy.org/en/latest/topics/spider-middleware.html
+
+BOT_NAME = 'post_scrape'
+
+SPIDER_MODULES = ['post_scrape.spiders']
+NEWSPIDER_MODULE = 'post_scrape.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'post_scrape (+http://www.yourdomain.com)'
+
+# Obey robots.txt rules
+ROBOTSTXT_OBEY = True
+
+# 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://docs.scrapy.org/en/latest/topics/settings.html#download-delay
+# See also autothrottle settings and docs
+#DOWNLOAD_DELAY = 3
+# 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://docs.scrapy.org/en/latest/topics/spider-middleware.html
+#SPIDER_MIDDLEWARES = {
+#    'post_scrape.middlewares.PostScrapeSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'post_scrape.middlewares.PostScrapeDownloaderMiddleware': 543,
+#}
+
+# Enable or disable extensions
+# See https://docs.scrapy.org/en/latest/topics/extensions.html
+#EXTENSIONS = {
+#    'scrapy.extensions.telnet.TelnetConsole': None,
+#}
+
+# Configure item pipelines
+# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
+#ITEM_PIPELINES = {
+#    'post_scrape.pipelines.PostScrapePipeline': 300,
+#}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See https://docs.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://docs.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'

src/post_scrape/spiders/__init__.py

@@ -0,0 +1,4 @@
+# This package will contain the spiders of your Scrapy project
+#
+# Please refer to the documentation for information on how to create and manage
+# your spiders.

src/post_scrape/spiders/car_spider.py

@@ -0,0 +1,118 @@
+import scrapy
+
+
+class ToScrapeCSSSpider(scrapy.Spider):
+    name = "car"
+    headers = {
+            'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/105.0.0.0 Safari/537.36'
+        }
+    last_page = 1
+
+    def start_requests(self):
+        urls = [
+            'https://turbo.az/autos',
+        ]
+
+        for url in urls:
+            yield scrapy.Request(url=url, headers=self.headers, callback=self.parse)
+
+    def parse(self, response):
+        posts = response.xpath('//div[@class="products-container"]//div[@class="products"]')[2].xpath('./div/a[@class="products-i__link"]/@href')
+
+        for p in posts:
+            yield response.follow(f"https://turbo.az{p.get()}", callback=self.parse_detail_url, headers=self.headers)
+
+        next_page = response.xpath('//a[@rel="next"]/@href').get()
+        if next_page is not None and int(next_page[next_page.rfind('=')+1:]) <= self.last_page:
+            yield response.follow(f"https://turbo.az{next_page}", callback=self.parse, headers=self.headers)
+
+    def parse_detail_url(self, r):
+        if r.xpath('//div[@class="shop-container"]'):
+            avto_salon = True
+            phone = r.xpath('//div[@class="shop-contact--phones-list"]//a[@class="shop-contact--phones-number"]/text()').getall()
+        else:
+            avto_salon = False
+            phone = r.xpath('//a[@class="phone"]/text()').get()
+
+        barter, loan = False, False
+
+        if r.xpath('//li[@class="product-properties-i product-properties-i_loan"]'):
+            loan = True
+        if r.xpath('//li[@class="product-properties-i product-properties-i_barter"]'):
+            barter = True
+
+        seats_count = r.xpath('//label[@for="ad_seats_count"]')
+        prior_owners_count = r.xpath('//label[@for="ad_prior_owners_count"]')
+
+        price = r.xpath('//li[@class="product-properties-i product-properties_price"]//div[@class="product-price"]/text()').get().replace(' ', '')
+        currency = r.xpath('//li[@class="product-properties-i product-properties_price"]//div[@class="product-price"]/span/text()').get()
+        extra_fields = r.xpath('//p[@class="product-extras-i"]/text()').getall()
+        description = r.xpath('//div[@class="product-description"]/p/text()').getall()
+        market = r.xpath('//li[@class="product-properties-i product-properties-market"]//div/text()').get()
+        data = r.xpath('//li[@class="product-properties-i"]/div[@class="product-properties-value"]/text()').getall()
+        data2 = r.xpath('//li[@class="product-properties-i"]/div[@class="product-properties-value"]/a/text()').getall()
+
+        if seats_count and prior_owners_count:
+            if '4 və daha çox' in data and '8+' in data:
+                prior_owners_count = data.pop(data.index('4 və daha çox'))
+                seats_count = data.pop(data.index('8+'))
+            elif '4 və daha çox' in data:
+                prior_owners_count = data.pop(data.index('4 və daha çox'))
+                seats_count = r.xpath('//li[@class="product-properties-i"]/div[@class="product-properties-value"]/span/text()').get()
+            elif '8+' in data:
+                seats_count = data.pop(data.index('8+'))
+                prior_owners_count = r.xpath('//li[@class="product-properties-i"]/div[@class="product-properties-value"]/span/text()').get()
+            else:
+                seats_count, prior_owners_count = r.xpath('//li[@class="product-properties-i"]/div[@class="product-properties-value"]/span/text()').getall()
+
+        elif seats_count:
+            if '8+' in data:
+                seats_count = data.pop(data.index('8+'))
+            else:
+                seats_count = r.xpath('//li[@class="product-properties-i"]/div[@class="product-properties-value"]/span/text()').get()
+            prior_owners_count = None
+        elif prior_owners_count:
+            if '4 və daha çox' in data:
+                prior_owners_count = data.pop(data.index('4 və daha çox'))
+            else:
+                prior_owners_count = r.xpath('//li[@class="product-properties-i"]/div[@class="product-properties-value"]/span/text()').get()
+            seats_count = None
+        else:
+            seats_count = None
+            prior_owners_count = None
+
+        if len(data) < 11:
+            crashed, painted = None, None
+        else:
+            crashed = 'Vuruğu yoxdur' not in data[10]
+            painted = 'rənglənməyib' not in data[10]
+
+        yield {
+            'url': r.url,
+            'avto_salon': avto_salon,
+            'phone': phone,
+            'extra_fields': extra_fields,
+            'description': description,
+            'city': data[0],
+            'brand': data2[0],
+            'model': data2[1],
+            'year': int(data2[2]),
+            'category': data[1],
+            'color': data[2],
+            'engine_volume': int(float(data[3][:-2])*1000),
+            'engine_power': int(data[4][:-5]),
+            'fuel_type': data[5],
+            'mileage': int(data[6][:-3].replace(' ', '')),
+            'mileage_type': data[6][-2:],
+            'transmission': data[7],
+            'gear': data[8],
+            'price': int(price),
+            'currency': currency,
+            'loan': loan,
+            'barter': barter,
+            'market': market,
+            'seats_count': seats_count,
+            'prior_owners_count': prior_owners_count,
+            'crashed':  crashed,
+            'painted': painted,
+        }

src/scrapy.cfg

@@ -0,0 +1,11 @@
+# Automatically created by: scrapy startproject
+#
+# For more information about the [deploy] section see:
+# https://scrapyd.readthedocs.io/en/latest/deploy.html
+
+[settings]
+default = post_scrape.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = post_scrape