Fill with the results of following the tutorial

.gitignore

@@ -0,0 +1,3 @@
+/books.csv
+/quotes.csv
+/tutorial-env/

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.

requirements.txt

@@ -0,0 +1,4 @@
+scrapy
+scrapy-zyte-api
+shub
+zyte-spider-templates

scrapinghub.yml

@@ -0,0 +1,4 @@
+requirements:
+  file: requirements.txt
+stacks:
+  default: scrapy:2.11

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

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

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)

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

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"

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.

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,
+        }

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"]