Initial commit

code/ep2023-scrapy.py

@@ -0,0 +1,14 @@
+import scrapy
+
+
+class EuroPython2023Spider(scrapy.Spider):
+    name = "europython"
+
+    start_urls = [
+        "https://ep2023.europython.eu/sessions",
+        "https://ep2023.europython.eu/tutorials",
+    ]
+
+    def parse(self, response):
+        for session in response.css("h2 a::text").getall():
+            yield {"title": session}

code/exercise-1.py

@@ -0,0 +1,22 @@
+# Exercise 1
+
+# Target: https://quotes.toscrape.com/
+
+# On this page, you will find a collection of quotes along with their respective
+# authors. Each quote is accompanied by a link that directs you to a dedicated
+# page providing additional details about the author, the quote itself, and a list of associated tags.
+
+# Your task is to extract all of this information and export it into a JSON lines file.
+
+# TIP: your parse method can be used to yield items or schedule new requests for later processing.
+import scrapy
+
+
+class QuotesSpider(scrapy.Spider):
+    name = "quotes"
+    allowed_domains = ["quotes.toscrape.com"]
+    start_urls = ["https://quotes.toscrape.com"]
+
+    def parse(self, response):
+        # TODO
+        ...

code/exercise-2.py

@@ -0,0 +1,26 @@
+# Exercise 2
+
+# Target: https://quotes.toscrape.com/scroll
+
+# There has been another modification to the layout. Our quotes page
+# now features an infinite scroll functionality, meaning that new
+# content is dynamically loaded as you reach the bottom of the page.
+
+# TIP: To understand this behavior, open your browser and access
+# our target page. Press F12 to open the developer tools and
+# select the "Network" tab. Observe what occurs in the network
+# requests when you navigate to the end of the page.
+import scrapy
+
+
+class QuotesScrollSpider(scrapy.Spider):
+    name = "quotes_scroll"
+    allowed_domains = ["quotes.toscrape.com"]
+
+    def start_requests(self):
+        # TODO
+        ...
+
+    def parse(self, response):
+        # TODO
+        ...

code/exercise-3.py

@@ -0,0 +1,21 @@
+# Exercise 2
+
+# Target: https://quotes.toscrape.com/js/
+
+# The spider you created in the first exercise has ceased to function.
+# Although no errors are evident in the logs, the spider is not returning any data.
+
+# TIP: To troubleshoot, open your browser and navigate to our target page.
+# Press Ctrl+U (View Page Source) to inspect the HTML content of the page.
+import json
+import scrapy
+
+
+class QuotesJSSpider(scrapy.Spider):
+    name = "quotes_js"
+    allowed_domains = ["quotes.toscrape.com"]
+    start_urls = ["https://quotes.toscrape.com/js/"]
+
+    def parse(self, response):
+        # TODO
+        ...

code/exercise-4.py

@@ -0,0 +1,25 @@
+import scrapy
+
+
+class QuotesViewStateSpider(scrapy.Spider):
+    name = "quotes_viewstate"
+    allowed_domains = ["quotes.toscrape.com"]
+    start_urls = ["http://quotes.toscrape.com/search.aspx"]
+
+    def parse(self, response):
+        authors = response.css("#author option::attr(value)").getall()
+
+        form_data = {
+            # TODO
+        }
+        for author in authors:
+            yield scrapy.FormRequest(
+                response.urljoin(response.css("form::attr(action)").get()),
+                callback=self.parse_author_tags,
+                formdata=form_data,
+                cb_kwargs={"author": author}
+            )
+
+    def parse_author_tags(self, response, author):
+        # TODO
+        ...

code/groups-requests.py

@@ -0,0 +1,13 @@
+import requests
+from parsel import Selector
+
+
+start_urls = [
+    "http://python.org.br",
+]
+for url in start_urls:
+    response = requests.get(url)
+    content = Selector(text=response.text)
+
+    for group in content.css("h4.card-title::text").getall():
+        print(group)

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

code/monitoring/monitoring/middlewares.py

@@ -0,0 +1,102 @@
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/spider-middleware.html
+
+# useful for handling different item types with a single interface
+from itemadapter import ItemAdapter, is_item
+from scrapy import signals
+
+
+class MonitoringSpiderMiddleware:
+    # 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 MonitoringDownloaderMiddleware:
+    # 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)

code/monitoring/monitoring/monitors.py

@@ -0,0 +1,24 @@
+from spidermon import Monitor, MonitorSuite, monitors
+from spidermon.contrib.actions.reports.files import CreateFileReport
+
+
+@monitors.name("Item count")
+class ItemCountMonitor(Monitor):
+    @monitors.name("Minimum number of items")
+    def test_minimum_number_of_items(self):
+        item_extracted = getattr(self.data.stats, "item_scraped_count", 0)
+        minimum_threshold = 10
+
+        msg = "Extracted less than {} items".format(minimum_threshold)
+        self.assertTrue(item_extracted >= minimum_threshold, msg=msg)
+
+
+class SpiderCloseMonitorSuite(MonitorSuite):
+
+    monitors = [
+        ItemCountMonitor,
+    ]
+
+    monitors_finished_actions = [
+        CreateFileReport,
+    ]

code/monitoring/monitoring/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 MonitoringPipeline:
+    def process_item(self, item, spider):
+        return item

code/monitoring/monitoring/settings.py

@@ -0,0 +1,106 @@
+# Scrapy settings for monitoring 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 = "monitoring"
+
+SPIDER_MODULES = ["monitoring.spiders"]
+NEWSPIDER_MODULE = "monitoring.spiders"
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+# USER_AGENT = "monitoring (+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 = {
+#    "monitoring.middlewares.MonitoringSpiderMiddleware": 543,
+# }
+
+# Enable or disable downloader middlewares
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+# DOWNLOADER_MIDDLEWARES = {
+#    "monitoring.middlewares.MonitoringDownloaderMiddleware": 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 = {
+#    "monitoring.pipelines.MonitoringPipeline": 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"
+
+# Monitoring
+# SPIDERMON_ENABLED = True
+
+# EXTENSIONS = {
+#     "spidermon.contrib.scrapy.extensions.Spidermon": 500,
+# }
+
+# SPIDERMON_SPIDER_CLOSE_MONITORS = ("monitoring.monitors.SpiderCloseMonitorSuite",)
+
+# SPIDERMON_REPORT_TEMPLATE = "reports/email/monitors/result.jinja"
+# SPIDERMON_REPORT_CONTEXT = {"report_title": "Spidermon File Report"}
+# SPIDERMON_REPORT_FILENAME = "my_report.html"

code/monitoring/monitoring/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.

code/monitoring/monitoring/spiders/quote.py

@@ -0,0 +1,30 @@
+import scrapy
+
+
+class QuoteSpider(scrapy.Spider):
+    name = "quote"
+    allowed_domains = ["quotes.toscrape.com"]
+    api_url = "https://quotes.toscrape.com/api/quotes?page={page}"
+
+    def start_requests(self):
+        yield scrapy.Request(self.api_url.format(page=1))
+
+    def parse(self, response):
+        data = response.json()
+        current_page = data.get("page")
+
+        for quote in data.get("quotes"):
+            yield {
+                "quote": quote.get("text"),
+                "author": quote.get("author").get("name"),
+                "author_url": response.urljoin(
+                    quote.get("author").get("goodreads_link")
+                ),
+                "tags": quote.get("tags"),
+            }
+
+        if data.get("has_next"):
+            next_page = current_page + 1
+            yield scrapy.Request(
+                self.api_url.format(page=next_page),
+            )

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

code/parsing-data-css.py

@@ -0,0 +1,18 @@
+import scrapy
+
+
+class EuroPython2023Spider(scrapy.Spider):
+    name = "europython"
+
+    start_urls = [
+        "https://ep2023.europython.eu/sessions",
+        "https://ep2023.europython.eu/tutorials",
+    ]
+
+    def parse(self, response):
+        sessions = response.css(".mt-12")
+        for session in sessions:
+            yield {
+                "title": session.css("h2 a::text").get(),
+                "presenter": session.css("p a::text").get(),
+            }

code/parsing-data-mixed.py

@@ -0,0 +1,18 @@
+import scrapy
+
+
+class EuroPython2023Spider(scrapy.Spider):
+    name = "europython"
+
+    start_urls = [
+        "https://ep2023.europython.eu/sessions",
+        "https://ep2023.europython.eu/tutorials",
+    ]
+
+    def parse(self, response):
+        sessions = response.css(".mt-12")
+        for session in sessions:
+            yield {
+                "title": session.xpath("./h2/a/text()").get(),
+                "presenter": session.xpath("./p/a/text()").get(),
+            }

code/parsing-data-xpath.py

@@ -0,0 +1,18 @@
+import scrapy
+
+
+class EuroPython2023Spider(scrapy.Spider):
+    name = "europython"
+
+    start_urls = [
+        "https://ep2023.europython.eu/sessions",
+        "https://ep2023.europython.eu/tutorials",
+    ]
+
+    def parse(self, response):
+        sessions = response.xpath("//div[contains(@class, 'mt-12')]")
+        for session in sessions:
+            yield {
+                "title": session.xpath("./h2/a/text()").get(),
+                "presenter": session.xpath("./p/a/text()").get(),
+            }

code/quotes-playwright.py

@@ -0,0 +1,37 @@
+import scrapy
+from scrapy_playwright.page import PageMethod
+
+
+class QuotesPlaywrightSpider(scrapy.Spider):
+    name = "quotes-playwright"
+    custom_settings = {
+        "DOWNLOAD_HANDLERS": {
+            "http": "scrapy_playwright.handler.ScrapyPlaywrightDownloadHandler",
+            "https": "scrapy_playwright.handler.ScrapyPlaywrightDownloadHandler",
+        },
+        "TWISTED_REACTOR": "twisted.internet.asyncioreactor.AsyncioSelectorReactor",
+    }
+
+    def start_requests(self):
+        yield scrapy.Request(
+            url="http://quotes.toscrape.com/scroll",
+            meta=dict(
+                playwright=True,
+                playwright_include_page=True,
+                playwright_page_methods=[
+                    PageMethod("wait_for_selector", "div.quote"),
+                    PageMethod(
+                        "evaluate", "window.scrollBy(0, document.body.scrollHeight)"
+                    ),
+                    PageMethod(
+                        "wait_for_selector", "div.quote:nth-child(11)"
+                    ),
+                ],
+            ),
+        )
+
+    async def parse(self, response):
+        page = response.meta["playwright_page"]
+        await page.screenshot(path="quotes.png", full_page=True)
+        await page.close()
+        return {"quote_count": len(response.css("div.quote"))}

code/requirements

@@ -0,0 +1,6 @@
+requests
+scrapy
+scrapy-playwright
+spidermon
+ipython
+ipdb