Standardizing all actions

.github/workflows/python-test.yml

@@ -8,10 +8,12 @@ jobs:
     strategy:
       matrix:
         include:
-          - python-version: "3.7.x"  # Min Python version (No 3.6 version)
+          - python-version: "3.7.x"  # Min Python version (No 3.6 version in GitHub repository)
           - python-version: "3.8.x"
           - python-version: "3.9.x"
           - python-version: "3.10.x"
+          - python-version: "3.11.x"
+          - python-version: "3.12.x"
           - python-version: "3.x"  # Last Python version
     steps:
       - uses: actions/checkout@v3

README.md

@@ -46,7 +46,7 @@ class MySpider(scrapy.Spider):
 ## Advanced usage
 
 `PuppeteerRequest`'s first argument is a browser action.
-Avalable actions are defined in `scrapypuppeteer.actions` module as subclasses of `PuppeteerServiceAction`.
+Available actions are defined in `scrapypuppeteer.actions` module as subclasses of `PuppeteerServiceAction`.
 Passing a URL into request is a shortcut for `GoTo(url)` action. 
 
 Here is the list of available actions:

examples/settings.py

@@ -1,12 +1,12 @@
-BOT_NAME = 'scrapypuppeteer'
+BOT_NAME = "scrapypuppeteer"
 
-SPIDER_MODULES = ['examples.spiders']
-NEWSPIDER_MODULE = 'examples.spiders'
+SPIDER_MODULES = ["examples.spiders"]
+NEWSPIDER_MODULE = "examples.spiders"
 
 CONCURRENT_REQUESTS = 1
 
 DOWNLOADER_MIDDLEWARES = {
-    'scrapypuppeteer.middleware.PuppeteerServiceDownloaderMiddleware': 1042
+    "scrapypuppeteer.middleware.PuppeteerServiceDownloaderMiddleware": 1042
 }
 
-PUPPETEER_SERVICE_URL = 'http://localhost:3000'
+PUPPETEER_SERVICE_URL = "http://localhost:3000"

examples/spiders/auto_recaptcha.py

@@ -14,37 +14,44 @@ class AutoRecaptchaSpider(scrapy.Spider):
     start_urls = ["https://www.google.com/recaptcha/api2/demo"]
 
     custom_settings = {
-        'DOWNLOADER_MIDDLEWARES': {
-            'scrapypuppeteer.middleware.PuppeteerRecaptchaDownloaderMiddleware': 1041,
-            'scrapypuppeteer.middleware.PuppeteerServiceDownloaderMiddleware': 1042
+        "DOWNLOADER_MIDDLEWARES": {
+            "scrapypuppeteer.middleware.PuppeteerRecaptchaDownloaderMiddleware": 1041,
+            "scrapypuppeteer.middleware.PuppeteerServiceDownloaderMiddleware": 1042,
+        },
+        "PUPPETEER_INCLUDE_META": True,
+        "RECAPTCHA_ACTIVATION": True,
+        "RECAPTCHA_SOLVING": True,
+        "RECAPTCHA_SUBMIT_SELECTORS": {
+            "www.google.com/recaptcha/api2/demo": "#recaptcha-demo-submit",
         },
-        'PUPPETEER_INCLUDE_META': True,
-
-        'RECAPTCHA_ACTIVATION': True,
-        'RECAPTCHA_SOLVING': True,
-        'RECAPTCHA_SUBMIT_SELECTORS': {
-            'www.google.com/recaptcha/api2/demo': '#recaptcha-demo-submit',
-        }
     }
 
     def start_requests(self):
         for url in self.start_urls:
             action = GoTo(url=url)
-            yield PuppeteerRequest(action=action, callback=self.parse_html, errback=self.error, close_page=False)
+            yield PuppeteerRequest(
+                action=action,
+                callback=self.parse_html,
+                errback=self.error,
+                close_page=False,
+            )
 
     def parse_html(self, response: PuppeteerResponse, **kwargs):
-        with open(f"recaptcha_page.html", 'wb') as f:
+        with open(f"recaptcha_page.html", "wb") as f:
             f.write(response.body)
-        action = Screenshot(options={
-            'full_page': True,
-        })
-        yield response.follow(action,
-                              callback=self.make_screenshot,
-                              errback=self.error,
-                              close_page=True)
+        action = Screenshot(
+            options={
+                "full_page": True,
+            }
+        )
+        yield response.follow(
+            action, callback=self.make_screenshot, errback=self.error, close_page=True
+        )
 
     def make_screenshot(self, response: PuppeteerScreenshotResponse, **kwargs):
-        data = response.screenshot  # Note that data is string containing bytes, don't forget to decode them!
+        data = (
+            response.screenshot
+        )  # Note that data is string containing bytes, don't forget to decode them!
         with open("imageToSave.png", "wb") as fh:
             fh.write(base64.b64decode(data))
 

examples/spiders/manual_recaptcha.py

@@ -16,29 +16,47 @@ class ManualRecaptchaSpider(scrapy.Spider):
     def start_requests(self):
         for url in self.start_urls:
             action = GoTo(url=url)
-            yield PuppeteerRequest(action=action, callback=self.solve_recaptcha, errback=self.error, close_page=False)
+            yield PuppeteerRequest(
+                action=action,
+                callback=self.solve_recaptcha,
+                errback=self.error,
+                close_page=False,
+            )
 
     def solve_recaptcha(self, response: PuppeteerResponse, **kwargs):
         action = RecaptchaSolver()
-        yield response.follow(action=action, callback=self.submit_recaptcha, errback=self.error, close_page=False)
+        yield response.follow(
+            action=action,
+            callback=self.submit_recaptcha,
+            errback=self.error,
+            close_page=False,
+        )
 
     def submit_recaptcha(self, response, **kwargs):
-        action = Click('#recaptcha-demo-submit')
-        yield response.follow(action=action, callback=self.parse_html, errback=self.error, close_page=False)
+        action = Click("#recaptcha-demo-submit")
+        yield response.follow(
+            action=action,
+            callback=self.parse_html,
+            errback=self.error,
+            close_page=False,
+        )
 
     def parse_html(self, response: PuppeteerResponse, **kwargs):
-        with open(f"recaptcha_page.html", 'wb') as f:
+        with open(f"recaptcha_page.html", "wb") as f:
             f.write(response.body)
-        action = Screenshot(options={
-            'full_page': True,
-        })
-        yield response.follow(action,
-                              callback=self.make_screenshot,
-                              errback=self.error,
-                              close_page=True)
+        action = Screenshot(
+            options={
+                "full_page": True,
+            }
+        )
+        yield response.follow(
+            action, callback=self.make_screenshot, errback=self.error, close_page=True
+        )
 
     def make_screenshot(self, response: PuppeteerScreenshotResponse, **kwargs):
-        data = response.screenshot  # Note that data is string containing bytes, don't forget to decode them!
+        data = (
+            response.screenshot
+        )  # Note that data is string containing bytes, don't forget to decode them!
         with open("imageToSave.png", "wb") as fh:
             fh.write(base64.b64decode(data))
 

examples/spiders/meduza.py

@@ -4,18 +4,18 @@
 
 
 class MeduzaSpider(scrapy.Spider):
-    name = 'meduza'
+    name = "meduza"
 
     def start_requests(self):
-        yield PuppeteerRequest('https://meduza.io', callback=self.parse_main_page)
+        yield PuppeteerRequest("https://meduza.io", callback=self.parse_main_page)
 
     def parse_main_page(self, response: PuppeteerHtmlResponse):
-        for article_url in response.css('a.Link-isInBlockTitle::attr(href)').getall():
+        for article_url in response.css("a.Link-isInBlockTitle::attr(href)").getall():
             yield response.follow(article_url, callback=self.parse_article)
 
     def parse_article(self, response: PuppeteerHtmlResponse):
         yield {
-            'url': response.url,
-            'title': response.css('h1::text').get(),
-            'text': '\n'.join(response.css('p.SimpleBlock-p::text').getall())
+            "url": response.url,
+            "title": response.css("h1::text").get(),
+            "text": "\n".join(response.css("p.SimpleBlock-p::text").getall()),
         }

examples/spiders/webscraperio.py

@@ -8,103 +8,115 @@ class EcommerceSiteSpider(scrapy.Spider):
 
     @staticmethod
     def extract_items(list_page_response):
-        for item_selector in list_page_response.css('div.row div.thumbnail'):
+        for item_selector in list_page_response.css("div.row div.thumbnail"):
             yield {
-                'link': item_selector.css('a.title::attr(href)').get(),
-                'title': item_selector.css('a.title::attr(title)').get(),
-                'price': item_selector.css('h4.price::text').get(),
-                'description': item_selector.css('p.description::text').get(),
-                'rating': len(item_selector.css('span.glyphicon-star')),
-                'reviews_count': int(item_selector
-                                     .css('.ratings p.pull-right::text')
-                                     .re_first(r'\d+'))
+                "link": item_selector.css("a.title::attr(href)").get(),
+                "title": item_selector.css("a.title::attr(title)").get(),
+                "price": item_selector.css("h4.price::text").get(),
+                "description": item_selector.css("p.description::text").get(),
+                "rating": len(item_selector.css("span.glyphicon-star")),
+                "reviews_count": int(
+                    item_selector.css(".ratings p.pull-right::text").re_first(r"\d+")
+                ),
             }
 
     @staticmethod
     def extract_item(detail_page_response):
         yield {
-            'link': detail_page_response.url,
-            'title': detail_page_response.css('h4.price + h4::text').get(),
-            'price': detail_page_response.css('h4.price::text').get(),
-            'description': detail_page_response.css('p.description::text').get(),
-            'rating': len(detail_page_response.css('span.glyphicon-star')),
-            'reviews_count': int(detail_page_response
-                                 .css('.ratings::text')
-                                 .re_first('\d+'))
+            "link": detail_page_response.url,
+            "title": detail_page_response.css("h4.price + h4::text").get(),
+            "price": detail_page_response.css("h4.price::text").get(),
+            "description": detail_page_response.css("p.description::text").get(),
+            "rating": len(detail_page_response.css("span.glyphicon-star")),
+            "reviews_count": int(
+                detail_page_response.css(".ratings::text").re_first("\d+")
+            ),
         }
 
 
 class AjaxPaginationSpider(EcommerceSiteSpider):
-    name = 'e-commerce-ajax'
+    name = "e-commerce-ajax"
 
     def __init__(self, **kwargs):
         super().__init__(**kwargs)
-        self.start_url = 'https://webscraper.io/test-sites/e-commerce/ajax/computers/laptops'
+        self.start_url = (
+            "https://webscraper.io/test-sites/e-commerce/ajax/computers/laptops"
+        )
         self.next_page_ix = 1
 
     def start_requests(self):
-        yield PuppeteerRequest(GoTo(self.start_url),
-                               close_page=False,
-                               callback=self.process_list_page)
+        yield PuppeteerRequest(
+            GoTo(self.start_url), close_page=False, callback=self.process_list_page
+        )
 
     def process_list_page(self, response):
         yield from self.extract_items(response)
         self.next_page_ix += 1
         next_page_selector = f'button[data-id="{self.next_page_ix}"]'
         if response.css(next_page_selector):
-            yield response.follow(Click(next_page_selector,
-                                        wait_options={'selectorOrTimeout': 3000}),
-                                  close_page=False,
-                                  callback=self.process_list_page)
+            yield response.follow(
+                Click(next_page_selector, wait_options={"selectorOrTimeout": 3000}),
+                close_page=False,
+                callback=self.process_list_page,
+            )
 
 
 class MoreSpider(EcommerceSiteSpider):
-    name = 'e-commerce-more'
+    name = "e-commerce-more"
 
     def __init__(self, **kwargs):
         super().__init__(**kwargs)
-        self.start_url = 'https://webscraper.io/test-sites/e-commerce/more/computers/laptops'
+        self.start_url = (
+            "https://webscraper.io/test-sites/e-commerce/more/computers/laptops"
+        )
         self.seen_item_links = set()
 
     def start_requests(self):
-        yield PuppeteerRequest(GoTo(self.start_url, wait_options={'selectorOrTimeout': 10000}),
-                               close_page=False,
-                               callback=self.process_list_page)
+        yield PuppeteerRequest(
+            GoTo(self.start_url, wait_options={"selectorOrTimeout": 10000}),
+            close_page=False,
+            callback=self.process_list_page,
+        )
 
     def process_list_page(self, response):
         for item in self.extract_items(response):
-            if item['link'] not in self.seen_item_links:
-                self.seen_item_links.add(item['link'])
+            if item["link"] not in self.seen_item_links:
+                self.seen_item_links.add(item["link"])
                 yield item
-        more_selector = '.ecomerce-items-scroll-more'
+        more_selector = ".ecomerce-items-scroll-more"
         more_button = response.css(more_selector)
-        if 'style' not in more_button.attrib:
-            yield response.follow(Click(more_selector,
-                                        wait_options={'selectorOrTimeout': 1000}),
-                                  close_page=False,
-                                  callback=self.process_list_page)
+        if "style" not in more_button.attrib:
+            yield response.follow(
+                Click(more_selector, wait_options={"selectorOrTimeout": 1000}),
+                close_page=False,
+                callback=self.process_list_page,
+            )
 
 
 class ScrollSpider(EcommerceSiteSpider):
-    name = 'e-commerce-scroll'
+    name = "e-commerce-scroll"
 
     def __init__(self, **kwargs):
         super().__init__(**kwargs)
-        self.start_url = 'https://webscraper.io/test-sites/e-commerce/scroll/computers/laptops'
+        self.start_url = (
+            "https://webscraper.io/test-sites/e-commerce/scroll/computers/laptops"
+        )
         self.seen_item_links = set()
 
     def start_requests(self):
-        yield PuppeteerRequest(GoTo(self.start_url),
-                               close_page=False,
-                               callback=self.process_list_page)
+        yield PuppeteerRequest(
+            GoTo(self.start_url), close_page=False, callback=self.process_list_page
+        )
 
     def process_list_page(self, response):
         items = self.extract_items(response)
-        new_items = [i for i in items if i['link'] not in self.seen_item_links]
+        new_items = [i for i in items if i["link"] not in self.seen_item_links]
         if new_items:
             for item in new_items:
-                self.seen_item_links.add(item['link'])
+                self.seen_item_links.add(item["link"])
                 yield item
-            yield response.follow(Scroll(wait_options={'selectorOrTimeout': 1000}),
-                                  close_page=False,
-                                  callback=self.process_list_page)
+            yield response.follow(
+                Scroll(wait_options={"selectorOrTimeout": 1000}),
+                close_page=False,
+                callback=self.process_list_page,
+            )