diff --git a/docs/_tests/quotes1.html b/docs/_tests/quotes1.html new file mode 100644 index 000000000..71aff8847 --- /dev/null +++ b/docs/_tests/quotes1.html @@ -0,0 +1,281 @@ + + + + + Quotes to Scrape + + + + +
+
+
+

+ Quotes to Scrape +

+
+
+

+ + Login + +

+
+
+ + +
+
+ +
+ “The world as we have created it is a process of our thinking. It cannot be changed without changing our thinking.” + by + (about) + +
+ Tags: + + + change + + deep-thoughts + + thinking + + world + +
+
+ +
+ “It is our choices, Harry, that show what we truly are, far more than our abilities.” + by + (about) + +
+ Tags: + + + abilities + + choices + +
+
+ +
+ “There are only two ways to live your life. One is as though nothing is a miracle. The other is as though everything is a miracle.” + by + (about) + +
+ Tags: + + + inspirational + + life + + live + + miracle + + miracles + +
+
+ +
+ “The person, be it gentleman or lady, who has not pleasure in a good novel, must be intolerably stupid.” + by + (about) + +
+ Tags: + + + aliteracy + + books + + classic + + humor + +
+
+ +
+ “Imperfection is beauty, madness is genius and it's better to be absolutely ridiculous than absolutely boring.” + by + (about) + +
+ Tags: + + + be-yourself + + inspirational + +
+
+ +
+ “Try not to become a man of success. Rather become a man of value.” + by + (about) + +
+ Tags: + + + adulthood + + success + + value + +
+
+ +
+ “It is better to be hated for what you are than to be loved for what you are not.” + by + (about) + +
+ Tags: + + + life + + love + +
+
+ +
+ “I have not failed. I've just found 10,000 ways that won't work.” + by + (about) + +
+ Tags: + + + edison + + failure + + inspirational + + paraphrased + +
+
+ +
+ “A woman is like a tea bag; you never know how strong it is until it's in hot water.” + by + (about) + +
+ Tags: + + + misattributed-eleanor-roosevelt + +
+
+ +
+ “A day without sunshine is like, you know, night.” + by + (about) + +
+ Tags: + + + humor + + obvious + + simile + +
+
+ + +
+
+ +

Top Ten tags

+ + + love + + + + inspirational + + + + life + + + + humor + + + + books + + + + reading + + + + friendship + + + + friends + + + + truth + + + + simile + + + +
+
+ +
+ + + \ No newline at end of file diff --git a/docs/conftest.py b/docs/conftest.py index 91c1d4428..8c735e838 100644 --- a/docs/conftest.py +++ b/docs/conftest.py @@ -1,16 +1,29 @@ -from doctest import ELLIPSIS +import os +from doctest import ELLIPSIS, NORMALIZE_WHITESPACE +from scrapy.http.response.html import HtmlResponse from sybil import Sybil from sybil.parsers.codeblock import CodeBlockParser from sybil.parsers.doctest import DocTestParser from sybil.parsers.skip import skip +def load_response(url, filename): + input_path = os.path.join(os.path.dirname(__file__), '_tests', filename) + with open(input_path, 'rb') as input_file: + return HtmlResponse(url, body=input_file.read()) + + +def setup(namespace): + namespace['load_response'] = load_response + + pytest_collect_file = Sybil( parsers=[ - DocTestParser(optionflags=ELLIPSIS), + DocTestParser(optionflags=ELLIPSIS | NORMALIZE_WHITESPACE), CodeBlockParser(future_imports=['print_function']), skip, ], pattern='*.rst', + setup=setup, ).pytest() diff --git a/docs/intro/tutorial.rst b/docs/intro/tutorial.rst index 0629b9e19..996e3b475 100644 --- a/docs/intro/tutorial.rst +++ b/docs/intro/tutorial.rst @@ -235,13 +235,16 @@ You will see something like:: [s] shelp() Shell help (print this help) [s] fetch(req_or_url) Fetch request (or URL) and update local objects [s] view(response) View response in a browser - >>> Using the shell, you can try selecting elements using `CSS`_ with the response -object:: +object: - >>> response.css('title') - [] +.. invisible-code-block: python + + response = load_response('http://quotes.toscrape.com/page/1/', 'quotes1.html') + +>>> response.css('title') +[] The result of running ``response.css('title')`` is a list-like object called :class:`~scrapy.selector.SelectorList`, which represents a list of @@ -372,6 +375,9 @@ we want:: We get a list of selectors for the quote HTML elements with:: >>> response.css("div.quote") + [, + , + ...] Each of the selectors returned by the query above allows us to run further queries over their sub-elements. Let's assign the first selector to a @@ -404,10 +410,9 @@ quotes elements and put them together into a Python dictionary:: ... author = quote.css("small.author::text").get() ... tags = quote.css("div.tags a.tag::text").getall() ... print(dict(text=text, author=author, tags=tags)) - {'tags': ['change', 'deep-thoughts', 'thinking', 'world'], 'author': 'Albert Einstein', 'text': '“The world as we have created it is a process of our thinking. It cannot be changed without changing our thinking.”'} - {'tags': ['abilities', 'choices'], 'author': 'J.K. Rowling', 'text': '“It is our choices, Harry, that show what we truly are, far more than our abilities.”'} - ... a few more of these, omitted for brevity - >>> + {'text': '“The world as we have created it is a process of our thinking. It cannot be changed without changing our thinking.”', 'author': 'Albert Einstein', 'tags': ['change', 'deep-thoughts', 'thinking', 'world']} + {'text': '“It is our choices, Harry, that show what we truly are, far more than our abilities.”', 'author': 'J.K. Rowling', 'tags': ['abilities', 'choices']} + ... Extracting data in our spider ----------------------------- @@ -521,7 +526,7 @@ There is also an ``attrib`` property available (see :ref:`selecting-attributes` for more):: >>> response.css('li.next a').attrib['href'] - '/page/2' + '/page/2/' Let's see now our spider modified to recursively follow the link to the next page, extracting data from it:: diff --git a/pytest.ini b/pytest.ini index 8c5a2cd54..3f1cc5800 100644 --- a/pytest.ini +++ b/pytest.ini @@ -7,7 +7,6 @@ addopts = --doctest-modules --ignore=docs/_ext --ignore=docs/conf.py - --ignore=docs/intro/tutorial.rst --ignore=docs/news.rst --ignore=docs/topics/commands.rst --ignore=docs/topics/debug.rst