Initial commit

ImmoScrap/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 ImmoscrapItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    pass

ImmoScrap/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 ImmoscrapSpiderMiddleware:
+    # 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 ImmoscrapDownloaderMiddleware:
+    # 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)

ImmoScrap/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 ImmoscrapPipeline:
+    def process_item(self, item, spider):
+        return item

ImmoScrap/settings.py

@@ -0,0 +1,88 @@
+# Scrapy settings for ImmoScrap 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 = 'ImmoScrap'
+
+SPIDER_MODULES = ['ImmoScrap.spiders']
+NEWSPIDER_MODULE = 'ImmoScrap.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'ImmoScrap (+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://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 = {
+#    'ImmoScrap.middlewares.ImmoscrapSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'ImmoScrap.middlewares.ImmoscrapDownloaderMiddleware': 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 = {
+#    'ImmoScrap.pipelines.ImmoscrapPipeline': 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'

ImmoScrap/spiders/Leboncoin.py

@@ -0,0 +1,36 @@
+import scrapy
+
+
+filters = {"category": {"id": "9"},
+           "enums": {"real_estate_type": ["1", "2", "5"], "ad_type": ["offer"]},
+           "ranges": {"rooms": {}, "square": {}, "price": {"min": 0, "max": 300000}},
+           "location": {"area": {"lat": 45.521971, "lng": 4.869926, "radius": 1000}, "city_zipcodes": [], "departments": [], "disable_region": False, "locations": [], "regions": []},
+           "keywords": {"type": "all"},
+           "owner": {}}
+
+data = {"pivot": "0,0,0", "limit": 100, "limit_alu": 1,
+        "filters": filters,
+        "sort_by": "time", "sort_order": "desc"}
+
+headers = {"User-Agent": "LBC;Android;6.0;Android SDK built for x86;phone;616a1ca77ca70180;wwan;4.30.4.0;70400;3",
+           "api_key": "ba0c2dad52b3ec", "Content-Type": "application/json; charset=UTF-8", "Accept-Encoding": "gzip, deflate"}
+
+
+
+class LeboncoinSpider(scrapy.Spider):
+    name = "leboncoin"
+
+    def start_requests(self):
+        urls = [
+            'https://api.leboncoin.fr/api/adfinder/v1/search',
+            'http://quotes.toscrape.com/page/2/',
+        ]
+        for url in urls:
+            yield scrapy.Request(url=url, callback=self.parse)
+
+    def parse(self, response):
+        page = response.url.split("/")[-2]
+        filename = 'quotes-%s.html' % page
+        with open(filename, 'wb') as f:
+            f.write(response.body)
+        self.log('Saved file %s' % filename)

ImmoScrap/spiders/Seloger.py

@@ -0,0 +1,72 @@
+import scrapy
+from urllib.parse import urlencode
+# from math import ceil
+
+# The only requrement to bypass protections on seloger is to spoof User-Agent
+
+
+class SelogerSpider(scrapy.Spider):
+    name = "seloger"
+
+    baseurl = 'https://www.seloger.com/list.htm'
+    vienne_area = r'uyztGgtx\zLeTdNcPvb@iJpFi@tDLdHtAbNxI|LvJx`@zi@|@bB|Eld@p@jNg@xn@gApPwBzR_FlVcBhEkDdBaDZgLeB{Aw@mwBi}BmBwAaEwEeAsBI}CxNij@'
+    stetienne_area = r'}mktGwtwYp@aClDsF`CaHpA_HfFgFlPkIjc@{HjDsBtK?dm@eKxIx@bCbBtDdKRpC}@`GTjIgArGcC`G{@jEyH`L{AbGcCrBmBjDuQ~L_EjDsFvA{G|C_Rx@mBj@eHh@gTN}Ey@oHoC_KkNuE}Cg@mDScGReK'
+    params = {'projects': '2,5',
+              'types': '1,2,12,11',
+              'natures': '1',
+              'price': 'NaN/300000',
+              'sort': 'd_dt_crea',
+              'enterprise': 0,
+              'qsVersion': 1.0,
+              'LISTING-LISTpg': 1}
+    vienne_params = params.copy()
+    vienne_params['searchareas'] = vienne_area
+    stetienne_params = params.copy()
+    stetienne_params['searchareas'] = stetienne_area
+
+    headers = {'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:78.0) Gecko/20100101 Firefox/78.0'}
+
+    pagination_xpath = '//div[has-class("ckWPHD")]//text()'
+    ads_css_sel = '.ListContent__SmartClassifiedExtended-sc-1viyr2k-2'
+    url_css_sel = '.dXJclF::attr(href)'
+    type_css_sel = '.joPkKZ::text'
+    price_css_sel = '.mVWFG::text'
+    infos_css_sel = ".eJYQQA"    # Contains Rooms, bedrooms, area
+
+    def start_requests(self):
+        urls = [
+            f'{self.baseurl}?{urlencode(self.vienne_params)},'
+            f'{self.baseurl}?{urlencode(self.stetienne_params)}'
+        ]
+        for url in urls:
+            yield scrapy.Request(url=url, headers=self.headers, callback=self.parse)
+
+    def parse(self, response):
+        ads = response.css(self.ads_css_sel)
+        for ad in ads:
+            infos = ad.css(self.infos_css_sel)
+
+            yield {
+                'url': ad.css(self.url_css_sel).get().split('?')[0],
+                'type': ad.css(self.type_css_sel).get(),
+                'price': ad.css(self.price_css_sel).get().replace('\xa0', ' '),
+                'rooms': infos.xpath('./li[contains(., "p")]/text()').get(),
+                'bedrooms': infos.xpath('./li[contains(., "ch")]/text()').get(),
+                'area': infos.xpath('./li[contains(., "m²")]/text()').get()
+            }
+            """
+            pricefloat = float(price.replace(',', '.').replace(' ', '').replace('€', ''))
+            areafloat = float(area.replace(',', '.').replace(' ', '').replace('m²', ''))
+            pricesqmint = round(pricefloat / areafloat)
+            print(url, type, price, rooms, bedrooms, area, pricesqmint)
+            """
+        active_page = response.url
+        active_page_nb = int(active_page.split('LISTING-LISTpg=')[1])
+
+        current_ads_nb = response.xpath(self.pagination_xpath).getall()[4]
+        total_ads_nb = response.xpath(self.pagination_xpath).getall()[-1]
+
+        if current_ads_nb != total_ads_nb:    # If not last page
+            next_page_nb = active_page_nb + 1
+            next_page = active_page.split('LISTING-LISTpg=')[0] + f'LISTING-LISTpg={next_page_nb}'
+            yield response.follow(next_page, headers=self.headers, callback=self.parse)

ImmoScrap/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.

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 = ImmoScrap.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = ImmoScrap