Python Scrapy Added

Author: MetinQardasov11

.gitignore

@@ -0,0 +1,78 @@
+*.log
+*.pot
+*.pyc
+__pycache__/
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+media
+*.py[cod]
+*$py.class
+*.so
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+*.manifest
+*.spec
+pip-log.txt
+pip-delete-this-directory.txt
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+*.mo
+instance/
+.webassets-cache
+.scrapy
+docs/_build/
+.pybuilder/
+target/
+.ipynb_checkpoints
+profile_default/
+ipython_config.py
+.pdm.toml
+__pypackages__/
+celerybeat-schedule
+celerybeat.pid
+*.sage.py
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+.spyderproject
+.spyproject
+.ropeproject
+/site
+.mypy_cache/
+.dmypy.json
+dmypy.json
+.pyre/
+.pytype/
+cython_debug/

example/__init__.py

@@ -0,0 +1,20 @@
+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class ExampleItem(scrapy.Item):
+    restaurant_name = scrapy.Field()
+    address = scrapy.Field()
+    country = scrapy.Field()
+    state = scrapy.Field()
+    city = scrapy.Field()
+    phone_number = scrapy.Field()
+    kitchen_type = scrapy.Field()
+    rating = scrapy.Field()
+    comment_title = scrapy.Field()
+    comment_content = scrapy.Field()
+    

example/items.py

@@ -0,0 +1,100 @@
+# 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 ItemAdapter
+
+
+class ExampleSpiderMiddleware:
+    # 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
+
+    async def process_start(self, start):
+        # Called with an async iterator over the spider start() method or the
+        # maching method of an earlier spider middleware.
+        async for item_or_request in start:
+            yield item_or_request
+
+    def spider_opened(self, spider):
+        spider.logger.info("Spider opened: %s" % spider.name)
+
+
+class ExampleDownloaderMiddleware:
+    # 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)

example/middlewares.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 ExamplePipeline:
+    def process_item(self, item, spider):
+        return item

example/pipelines.py

@@ -0,0 +1,87 @@
+# Scrapy settings for example 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 = "example"
+
+SPIDER_MODULES = ["example.spiders"]
+NEWSPIDER_MODULE = "example.spiders"
+
+ADDONS = {}
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+USER_AGENT = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/115.0.0.0 Safari/537.36"
+
+# Obey robots.txt rules
+ROBOTSTXT_OBEY = False
+
+# Concurrency and throttling settings
+#CONCURRENT_REQUESTS = 16
+CONCURRENT_REQUESTS_PER_DOMAIN = 1
+DOWNLOAD_DELAY = 1
+
+# 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 = {
+#    "example.middlewares.ExampleSpiderMiddleware": 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    "example.middlewares.ExampleDownloaderMiddleware": 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 = {
+#    "example.pipelines.ExamplePipeline": 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"
+
+# Set settings whose default value is deprecated to a future-proof value
+FEED_EXPORT_ENCODING = "utf-8"

example/settings.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.

example/spiders/__init__.py

@@ -0,0 +1,55 @@
+import scrapy
+from example.items import ExampleItem
+from scrapy import Request
+from urllib.parse import urljoin
+
+
+class ExampleNewSpider(scrapy.Spider):
+    name = "example_new"
+    allowed_domains = ["www.tripadvisor.com"]
+    start_urls = [
+        "https://www.tripadvisor.com/Restaurants-g295424-Dubai_Emirate_of_Dubai.html"
+    ]
+    
+    def start_requests(self):
+        headers = {
+        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/115.0.0.0 Safari/537.36",
+        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
+        "Accept-Language": "en-US,en;q=0.9",
+        "Accept-Encoding": "gzip, deflate, br",
+        "Connection": "keep-alive",
+        "Upgrade-Insecure-Requests": "1",
+        "Sec-Fetch-Dest": "document",
+        "Sec-Fetch-Mode": "navigate",
+        "Sec-Fetch-Site": "none",
+        "Sec-Fetch-User": "?1"
+    }
+        for url in self.start_urls:
+            yield scrapy.Request(url=url, headers=headers, callback=self.parse)
+
+    def parse(self, response):
+        for href in response.xpath('//div[@class="title"]/a[@class="property_title"]/@href'):
+            url = urljoin(response.url, href.extract())
+            yield Request(url, callback=self.parse_page)
+
+        next_page = response.xpath('//a[contains(@class, "next")]/@href')
+        if next_page:
+            next_page_url = urljoin(response.url, next_page.extract_first())
+            yield Request(next_page_url, callback=self.parse)
+
+    def parse_page(self, response):
+        item = ExampleItem()
+
+        item["restaurant_name"] = response.xpath('//h1/text()').get()
+        item["address"] = response.xpath('//span[contains(@class,"detailLinkText")]/text()').get()
+        item["city"] = response.xpath('//span[@class="extended-address"]/text()').get()
+        item["state"] = response.xpath('//span[@class="locality"]/text()').get()
+        item["country"] = response.xpath('//span[@class="country-name"]/text()').get()
+        item["phone_number"] = response.xpath('//span[contains(@class,"mobile")]/text()').get()
+        item["kitchen_type"] = response.xpath('//div[@class="header_links"]/a/text()').get()
+        item["rating"] = response.xpath('//span[contains(@class,"ZDEqb")]/text()').get()
+
+        item["comment_title"] = response.xpath('(//div[contains(@class,"review-container")]//span[@class="noQuotes"]/text())[1]').get()
+        item["comment_content"] = response.xpath('(//div[contains(@class,"review-container")]//p[@class="partial_entry"]/text())[1]').get()
+
+        yield item