From 25bf4c25c84d8fdebbceda63b669e6c313fd837a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Adri=C3=A1n=20Chaves?= Date: Thu, 23 Nov 2023 15:44:49 +0100 Subject: [PATCH] Fill with the results of following the tutorial --- .gitignore | 3 + README.rst | 54 ++++++++ requirements.txt | 4 + scrapinghub.yml | 4 + scrapy.cfg | 11 ++ tutorial/__init__.py | 0 tutorial/items.py | 12 ++ tutorial/middlewares.py | 103 +++++++++++++++ tutorial/pipelines.py | 13 ++ tutorial/settings.py | 121 ++++++++++++++++++ tutorial/spiders/__init__.py | 4 + tutorial/spiders/books_toscrape_com.py | 21 +++ .../spiders/books_toscrape_com_extract.py | 19 +++ .../spiders/quotes_toscrape_com_scroll_api.py | 18 +++ .../quotes_toscrape_com_scroll_browser.py | 28 ++++ .../spiders/quotes_toscrape_com_search.py | 51 ++++++++ 16 files changed, 466 insertions(+) create mode 100644 .gitignore create mode 100644 requirements.txt create mode 100644 scrapinghub.yml create mode 100644 scrapy.cfg create mode 100644 tutorial/__init__.py create mode 100644 tutorial/items.py create mode 100644 tutorial/middlewares.py create mode 100644 tutorial/pipelines.py create mode 100644 tutorial/settings.py create mode 100644 tutorial/spiders/__init__.py create mode 100644 tutorial/spiders/books_toscrape_com.py create mode 100644 tutorial/spiders/books_toscrape_com_extract.py create mode 100644 tutorial/spiders/quotes_toscrape_com_scroll_api.py create mode 100644 tutorial/spiders/quotes_toscrape_com_scroll_browser.py create mode 100644 tutorial/spiders/quotes_toscrape_com_search.py diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..b3d9926 --- /dev/null +++ b/.gitignore @@ -0,0 +1,3 @@ +/books.csv +/quotes.csv +/tutorial-env/ diff --git a/README.rst b/README.rst index e79863c..6d238b4 100644 --- a/README.rst +++ b/README.rst @@ -6,3 +6,57 @@ Scrapy_ project built following `Zyte’s web scraping tutorial`_. .. _Scrapy: https://scrapy.org/ .. _Zyte’s web scraping tutorial: https://docs.zyte.com/web-scraping/tutorial/index.html + +Requirements +============ + +Python 3.8 or higher. + + +Setup +===== + +To be able to use this project, you must first: + +#. Create a Python virtual environment. + + - On **Windows**: + + .. code-block:: shell + + python3 -m venv tutorial-env + tutorial-env\Scripts\activate.bat + + - On **macOS** and **Linux**: + + .. code-block:: shell + + python3 -m venv tutorial-env + . tutorial-env/bin/activate + +#. Install the project requirements: + + .. code-block:: shell + + pip install --upgrade -r requirements.txt + +#. To be able to deploy to `Scrapy Cloud`_, copy your `Scrapy Cloud API key`_, + run ``shub login`` and, when prompted, paste your API key and press Enter. + + .. _Scrapy Cloud: https://docs.zyte.com/scrapy-cloud/get-started.html + .. _Scrapy Cloud API key: https://app.zyte.com/o/settings/apikey + +#. To be able to use `Zyte API`_, append the following line to + ``tutorial/settings.py``, replacing ``YOUR_API_KEY`` with your `Zyte API + key`_: + + .. code-block:: python + + ZYTE_API_KEY = "YOUR_API_KEY" + + .. _Zyte API: https://docs.zyte.com/zyte-api/get-started.html + .. _Zyte API key: https://app.zyte.com/o/zyte-api/api-access + + .. tip:: For local development, you can alternatively use an environment + variable with that name. In Scrapy Cloud, the ``ZYTE_API_KEY`` setting + will be automatically defined with your Zyte API key. diff --git a/requirements.txt b/requirements.txt new file mode 100644 index 0000000..e962697 --- /dev/null +++ b/requirements.txt @@ -0,0 +1,4 @@ +scrapy +scrapy-zyte-api +shub +zyte-spider-templates diff --git a/scrapinghub.yml b/scrapinghub.yml new file mode 100644 index 0000000..1414142 --- /dev/null +++ b/scrapinghub.yml @@ -0,0 +1,4 @@ +requirements: + file: requirements.txt +stacks: + default: scrapy:2.11 diff --git a/scrapy.cfg b/scrapy.cfg new file mode 100644 index 0000000..d79f6f1 --- /dev/null +++ b/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 = tutorial.settings + +[deploy] +#url = http://localhost:6800/ +project = tutorial diff --git a/tutorial/__init__.py b/tutorial/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/tutorial/items.py b/tutorial/items.py new file mode 100644 index 0000000..20c7fa5 --- /dev/null +++ b/tutorial/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 TutorialItem(scrapy.Item): + # define the fields for your item here like: + # name = scrapy.Field() + pass diff --git a/tutorial/middlewares.py b/tutorial/middlewares.py new file mode 100644 index 0000000..320587e --- /dev/null +++ b/tutorial/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 TutorialSpiderMiddleware: + # 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 TutorialDownloaderMiddleware: + # 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) diff --git a/tutorial/pipelines.py b/tutorial/pipelines.py new file mode 100644 index 0000000..857cf72 --- /dev/null +++ b/tutorial/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 TutorialPipeline: + def process_item(self, item, spider): + return item diff --git a/tutorial/settings.py b/tutorial/settings.py new file mode 100644 index 0000000..4ed7f4f --- /dev/null +++ b/tutorial/settings.py @@ -0,0 +1,121 @@ +# Scrapy settings for tutorial 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 = "tutorial" + +SPIDER_MODULES = [ + "tutorial.spiders", + "zyte_spider_templates.spiders", +] +NEWSPIDER_MODULE = "tutorial.spiders" + + +# Crawl responsibly by identifying yourself (and your website) on the user-agent +#USER_AGENT = "tutorial (+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 = { +# "tutorial.middlewares.TutorialSpiderMiddleware": 543, +#} + +# Enable or disable downloader middlewares +# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html +#DOWNLOADER_MIDDLEWARES = { +# "tutorial.middlewares.TutorialDownloaderMiddleware": 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 = { +# "tutorial.pipelines.TutorialPipeline": 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 +REQUEST_FINGERPRINTER_IMPLEMENTATION = "2.7" +TWISTED_REACTOR = "twisted.internet.asyncioreactor.AsyncioSelectorReactor" +FEED_EXPORT_ENCODING = "utf-8" + +# Custom settings +DOWNLOAD_HANDLERS = { + "http": "scrapy_zyte_api.ScrapyZyteAPIDownloadHandler", + "https": "scrapy_zyte_api.ScrapyZyteAPIDownloadHandler", +} +DOWNLOADER_MIDDLEWARES = { + "scrapy_poet.InjectionMiddleware": 543, + "scrapy_zyte_api.ScrapyZyteAPIDownloaderMiddleware": 1000, +} +REQUEST_FINGERPRINTER_CLASS = "scrapy_zyte_api.ScrapyZyteAPIRequestFingerprinter" +ZYTE_API_TRANSPARENT_MODE = True +SPIDER_MIDDLEWARES = { + "scrapy_poet.RetryMiddleware": 275, + "zyte_spider_templates.middlewares.CrawlingLogsMiddleware": 1000, +} +SCRAPY_POET_DISCOVER = [ + "zyte_spider_templates.page_objects", +] +SCRAPY_POET_PROVIDERS = { + "scrapy_zyte_api.providers.ZyteApiProvider": 1100, +} +CLOSESPIDER_TIMEOUT_NO_ITEM = 600 +SCHEDULER_DISK_QUEUE = "scrapy.squeues.PickleFifoDiskQueue" +SCHEDULER_MEMORY_QUEUE = "scrapy.squeues.FifoMemoryQueue" diff --git a/tutorial/spiders/__init__.py b/tutorial/spiders/__init__.py new file mode 100644 index 0000000..ebd689a --- /dev/null +++ b/tutorial/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. diff --git a/tutorial/spiders/books_toscrape_com.py b/tutorial/spiders/books_toscrape_com.py new file mode 100644 index 0000000..33bb904 --- /dev/null +++ b/tutorial/spiders/books_toscrape_com.py @@ -0,0 +1,21 @@ +from scrapy import Spider + + +class BooksToScrapeComSpider(Spider): + name = "books_toscrape_com" + start_urls = [ + "http://books.toscrape.com/catalogue/category/books/mystery_3/index.html" + ] + + def parse(self, response): + next_page_links = response.css(".next a") + yield from response.follow_all(next_page_links) + book_links = response.css("article a") + yield from response.follow_all(book_links, callback=self.parse_book) + + def parse_book(self, response): + yield { + "name": response.css("h1::text").get(), + "price": response.css(".price_color::text").re_first("£(.*)"), + "url": response.url, + } diff --git a/tutorial/spiders/books_toscrape_com_extract.py b/tutorial/spiders/books_toscrape_com_extract.py new file mode 100644 index 0000000..e4ceed1 --- /dev/null +++ b/tutorial/spiders/books_toscrape_com_extract.py @@ -0,0 +1,19 @@ +from scrapy import Spider + + +class BooksToScrapeComExtractSpider(Spider): + name = "books_toscrape_com_extract" + start_urls = [ + "http://books.toscrape.com/catalogue/category/books/mystery_3/index.html" + ] + + def parse(self, response): + next_page_links = response.css(".next a") + yield from response.follow_all(next_page_links) + book_links = response.css("article a") + for request in response.follow_all(book_links, callback=self.parse_book): + request.meta["zyte_api_automap"] = {"product": True} + yield request + + def parse_book(self, response): + yield response.raw_api_response["product"] diff --git a/tutorial/spiders/quotes_toscrape_com_scroll_api.py b/tutorial/spiders/quotes_toscrape_com_scroll_api.py new file mode 100644 index 0000000..0a2edbf --- /dev/null +++ b/tutorial/spiders/quotes_toscrape_com_scroll_api.py @@ -0,0 +1,18 @@ +import json +from scrapy import Spider + + +class QuotesToScrapeComScrollAPISpider(Spider): + name = "quotes_toscrape_com_scroll_api" + start_urls = [ + f"http://quotes.toscrape.com/api/quotes?page={n}" for n in range(1, 11) + ] + + def parse(self, response): + data = json.loads(response.text) + for quote in data["quotes"]: + yield { + "author": quote["author"]["name"], + "tags": quote["tags"], + "text": quote["text"], + } diff --git a/tutorial/spiders/quotes_toscrape_com_scroll_browser.py b/tutorial/spiders/quotes_toscrape_com_scroll_browser.py new file mode 100644 index 0000000..2ee9eca --- /dev/null +++ b/tutorial/spiders/quotes_toscrape_com_scroll_browser.py @@ -0,0 +1,28 @@ +from scrapy import Request, Spider + + +class QuotesToScrapeComScrollBrowserSpider(Spider): + name = "quotes_toscrape_com_scroll_browser" + + def start_requests(self): + yield Request( + "http://quotes.toscrape.com/scroll", + meta={ + "zyte_api_automap": { + "browserHtml": True, + "actions": [ + { + "action": "scrollBottom", + }, + ], + }, + }, + ) + + def parse(self, response): + for quote in response.css(".quote"): + yield { + "author": quote.css(".author::text").get(), + "tags": quote.css(".tag::text").getall(), + "text": quote.css(".text::text").get()[1:-1], + } diff --git a/tutorial/spiders/quotes_toscrape_com_search.py b/tutorial/spiders/quotes_toscrape_com_search.py new file mode 100644 index 0000000..c90cbe2 --- /dev/null +++ b/tutorial/spiders/quotes_toscrape_com_search.py @@ -0,0 +1,51 @@ +from scrapy import Request, Spider + + +class QuotesToScrapeComSearchSpider(Spider): + name = "quotes_toscrape_com_search" + + def start_requests(self): + yield Request( + "http://quotes.toscrape.com/search.aspx", + meta={ + "zyte_api_automap": { + "browserHtml": True, + "actions": [ + { + "action": "select", + "selector": {"type": "css", "value": "#author"}, + "values": ["Albert Einstein"], + }, + { + "action": "waitForSelector", + "selector": { + "type": "css", + "value": "[value=\"world\"]", + "state": "attached", + }, + }, + { + "action": "select", + "selector": {"type": "css", "value": "#tag"}, + "values": ["world"], + }, + { + "action": "click", + "selector": {"type": "css", "value": "[type='submit']"}, + }, + { + "action": "waitForSelector", + "selector": {"type": "css", "value": ".quote"}, + }, + ], + }, + }, + ) + + def parse(self, response): + for quote in response.css(".quote"): + yield { + "author": quote.css(".author::text").get(), + "tags": quote.css(".tag::text").getall(), + "text": quote.css(".content::text").get()[1:-1], + }