[doc] Add allowed_domains to example spiders

docs/intro/overview.rst

@@ -29,6 +29,7 @@ https://quotes.toscrape.com, following the pagination:
 
     class QuotesSpider(scrapy.Spider):
         name = "quotes"
+        allowed_domains = ["quotes.toscrape.com"]
         start_urls = [
             "https://quotes.toscrape.com/tag/humor/",
         ]

docs/topics/debug.rst

@@ -16,6 +16,7 @@ Consider the following Scrapy spider below:
 
     class MySpider(scrapy.Spider):
         name = "myspider"
+        allowed_domains = ["example.com"]
         start_urls = (
             "http://example.com/page1",
             "http://example.com/page2",

docs/topics/logging.rst

@@ -118,6 +118,7 @@ instance, which can be accessed and used like this:
 
     class MySpider(scrapy.Spider):
         name = "myspider"
+        allowed_domains = ["scrapy.org"]
         start_urls = ["https://scrapy.org"]
 
         def parse(self, response):
@@ -136,6 +137,7 @@ Python logger you want. For example:
 
     class MySpider(scrapy.Spider):
         name = "myspider"
+        allowed_domains = ["scrapy.org"]
         start_urls = ["https://scrapy.org"]
 
         def parse(self, response):

docs/topics/request-response.rst

@@ -344,6 +344,7 @@ errors if needed:
 
     class ErrbackSpider(scrapy.Spider):
         name = "errback_example"
+        allowed_domains = ["www.httpbin.org", "example.invalid"]
         start_urls = [
             "http://www.httpbin.org/",  # HTTP 200 expected
             "http://www.httpbin.org/status/404",  # Not found error
@@ -712,6 +713,7 @@ signals will stop the download of a given response. See the following example:
 
     class StopSpider(scrapy.Spider):
         name = "stop"
+        allowed_domains = ["docs.scrapy.org"]
         start_urls = ["https://docs.scrapy.org/en/latest/"]
 
         @classmethod
@@ -889,6 +891,7 @@ method for this job. Here's an example spider which uses it:
 
     class LoginSpider(scrapy.Spider):
         name = "example.com"
+        allowed_domains = ["www.example.com"]
         start_urls = ["http://www.example.com/users/login.php"]
 
         def parse(self, response):

docs/topics/settings.rst

@@ -219,6 +219,7 @@ In a spider, settings are available through ``self.settings``:
 
     class MySpider(scrapy.Spider):
         name = "myspider"
+        allowed_domains = ["example.com"]
         start_urls = ["http://example.com"]
 
         def parse(self, response):
@@ -2012,6 +2013,7 @@ In order to use the reactor installed by Scrapy:
 
     class QuotesSpider(scrapy.Spider):
         name = "quotes"
+        allowed_domains = ["quotes.toscrape.com"]
 
         def __init__(self, *args, **kwargs):
             self.timeout = int(kwargs.pop("timeout", "60"))
@@ -2041,6 +2043,7 @@ which raises an exception, becomes:
 
     class QuotesSpider(scrapy.Spider):
         name = "quotes"
+        allowed_domains = ["quotes.toscrape.com"]
 
         def __init__(self, *args, **kwargs):
             self.timeout = int(kwargs.pop("timeout", "60"))

docs/topics/shell.rst

@@ -253,6 +253,7 @@ Here's an example of how you would call it from your spider:
 
     class MySpider(scrapy.Spider):
         name = "myspider"
+        allowed_domains = ["example.com", "example.org", "example.net"]
         start_urls = [
             "http://example.com",
             "http://example.org",

docs/topics/signals.rst

@@ -66,6 +66,7 @@ Let's take an example using :ref:`coroutines <topics-coroutines>`:
 
     class SignalSpider(scrapy.Spider):
         name = "signals"
+        allowed_domains = ["quotes.toscrape.com"]
         start_urls = ["https://quotes.toscrape.com/page/1/"]
 
         @classmethod

docs/topics/spiders.rst

@@ -312,6 +312,7 @@ Spiders can access arguments in their `__init__` methods:
 
     class MySpider(scrapy.Spider):
         name = "myspider"
+        allowed_domains = ["www.example.com"]
 
         def __init__(self, category=None, *args, **kwargs):
             super(MySpider, self).__init__(*args, **kwargs)
@@ -329,6 +330,7 @@ The above example can also be written as follows:
 
     class MySpider(scrapy.Spider):
         name = "myspider"
+        allowed_domains = ["www.example.com"]
 
         async def start(self):
             yield scrapy.Request(f"http://www.example.com/categories/{self.category}")
@@ -867,6 +869,7 @@ Simplest example: process all urls discovered through sitemaps using the
 
 
     class MySpider(SitemapSpider):
+        allowed_domains = ["www.example.com"]
         sitemap_urls = ["http://www.example.com/sitemap.xml"]
 
         def parse(self, response):
@@ -881,6 +884,7 @@ callback:
 
 
     class MySpider(SitemapSpider):
+        allowed_domains = ["www.example.com"]
         sitemap_urls = ["http://www.example.com/sitemap.xml"]
         sitemap_rules = [
             ("/product/", "parse_product"),
@@ -902,6 +906,7 @@ whose url contains ``/sitemap_shop``:
 
 
     class MySpider(SitemapSpider):
+        allowed_domains = ["www.example.com"]
         sitemap_urls = ["http://www.example.com/robots.txt"]
         sitemap_rules = [
             ("/shop/", "parse_shop"),
@@ -919,6 +924,7 @@ Combine SitemapSpider with other sources of urls:
 
 
     class MySpider(SitemapSpider):
+        allowed_domains = ["www.example.com"]
         sitemap_urls = ["http://www.example.com/robots.txt"]
         sitemap_rules = [
             ("/shop/", "parse_shop"),