diff --git a/docs/topics/commands.rst b/docs/topics/commands.rst index 3088017cb..ef9c45196 100644 --- a/docs/topics/commands.rst +++ b/docs/topics/commands.rst @@ -458,9 +458,9 @@ Usage example:: >>> STATUS DEPTH LEVEL 1 <<< # Scraped Items ------------------------------------------------------------ - [{'name': u'Example item', - 'category': u'Furniture', - 'length': u'12 cm'}] + [{'name': 'Example item', + 'category': 'Furniture', + 'length': '12 cm'}] # Requests ----------------------------------------------------------------- [] diff --git a/docs/topics/items.rst b/docs/topics/items.rst index 4423bbda2..ae44aecd3 100644 --- a/docs/topics/items.rst +++ b/docs/topics/items.rst @@ -86,7 +86,7 @@ Creating items :: >>> product = Product(name='Desktop PC', price=1000) - >>> print product + >>> print(product) Product(name='Desktop PC', price=1000) Getting field values @@ -161,11 +161,11 @@ Other common tasks Copying items:: >>> product2 = Product(product) - >>> print product2 + >>> print(product2) Product(name='Desktop PC', price=1000) >>> product3 = product2.copy() - >>> print product3 + >>> print(product3) Product(name='Desktop PC', price=1000) Creating dicts from items:: diff --git a/docs/topics/jobs.rst b/docs/topics/jobs.rst index 06c7fff3d..8e1574376 100644 --- a/docs/topics/jobs.rst +++ b/docs/topics/jobs.rst @@ -84,7 +84,7 @@ So, for example, this won't work:: return scrapy.Request('http://www.example.com', callback=lambda r: self.other_callback(r, somearg)) def other_callback(self, response, somearg): - print "the argument passed is:", somearg + print("the argument passed is: %s" % somearg) But this will:: @@ -94,7 +94,7 @@ But this will:: def other_callback(self, response): somearg = response.meta['somearg'] - print "the argument passed is:", somearg + print("the argument passed is: %s" % somearg) If you wish to log the requests that couldn't be serialized, you can set the :setting:`SCHEDULER_DEBUG` setting to ``True`` in the project's settings page. diff --git a/docs/topics/loaders.rst b/docs/topics/loaders.rst index a895b535c..f3b6aa4a1 100644 --- a/docs/topics/loaders.rst +++ b/docs/topics/loaders.rst @@ -678,10 +678,10 @@ Here is a list of all built-in processors: >>> from scrapy.loader.processors import Join >>> proc = Join() >>> proc(['one', 'two', 'three']) - u'one two three' + 'one two three' >>> proc = Join('
') >>> proc(['one', 'two', 'three']) - u'one
two
three' + 'one
two
three' .. class:: Compose(\*functions, \**default_loader_context) @@ -744,9 +744,9 @@ Here is a list of all built-in processors: ... return None if x == 'world' else x ... >>> from scrapy.loader.processors import MapCompose - >>> proc = MapCompose(filter_world, unicode.upper) - >>> proc([u'hello', u'world', u'this', u'is', u'scrapy']) - [u'HELLO, u'THIS', u'IS', u'SCRAPY'] + >>> proc = MapCompose(filter_world, str.upper) + >>> proc(['hello', 'world', 'this', 'is', 'scrapy']) + ['HELLO, 'THIS', 'IS', 'SCRAPY'] As with the Compose processor, functions can receive Loader contexts, and constructor keyword arguments are used as default context values. See @@ -772,7 +772,7 @@ Here is a list of all built-in processors: >>> import json >>> proc_single_json_str = Compose(json.loads, SelectJmes("foo")) >>> proc_single_json_str('{"foo": "bar"}') - u'bar' + 'bar' >>> proc_json_list = Compose(json.loads, MapCompose(SelectJmes('foo'))) >>> proc_json_list('[{"foo":"bar"}, {"baz":"tar"}]') - [u'bar'] + ['bar'] diff --git a/docs/topics/selectors.rst b/docs/topics/selectors.rst index 8ac40c3cc..25c1f0aab 100644 --- a/docs/topics/selectors.rst +++ b/docs/topics/selectors.rst @@ -235,17 +235,17 @@ Here's an example used to extract image names from the :ref:`HTML code ` above:: >>> response.xpath('//a[contains(@href, "image")]/text()').re(r'Name:\s*(.*)') - [u'My image 1', - u'My image 2', - u'My image 3', - u'My image 4', - u'My image 5'] + ['My image 1', + 'My image 2', + 'My image 3', + 'My image 4', + 'My image 5'] There's an additional helper reciprocating ``.extract_first()`` for ``.re()``, named ``.re_first()``. Use it to extract just the first matching string:: >>> response.xpath('//a[contains(@href, "image")]/text()').re_first(r'Name:\s*(.*)') - u'My image 1' + 'My image 1' .. _topics-selectors-relative-xpaths: @@ -431,26 +431,26 @@ with groups of itemscopes and corresponding itemprops:: ... print " properties:", props.extract() ... print - current scope: [u'http://schema.org/Product'] - properties: [u'name', u'aggregateRating', u'offers', u'description', u'review', u'review'] + current scope: ['http://schema.org/Product'] + properties: ['name', 'aggregateRating', 'offers', 'description', 'review', 'review'] - current scope: [u'http://schema.org/AggregateRating'] - properties: [u'ratingValue', u'reviewCount'] + current scope: ['http://schema.org/AggregateRating'] + properties: ['ratingValue', 'reviewCount'] - current scope: [u'http://schema.org/Offer'] - properties: [u'price', u'availability'] + current scope: ['http://schema.org/Offer'] + properties: ['price', 'availability'] - current scope: [u'http://schema.org/Review'] - properties: [u'name', u'author', u'datePublished', u'reviewRating', u'description'] + current scope: ['http://schema.org/Review'] + properties: ['name', 'author', 'datePublished', 'reviewRating', 'description'] - current scope: [u'http://schema.org/Rating'] - properties: [u'worstRating', u'ratingValue', u'bestRating'] + current scope: ['http://schema.org/Rating'] + properties: ['worstRating', 'ratingValue', 'bestRating'] - current scope: [u'http://schema.org/Review'] - properties: [u'name', u'author', u'datePublished', u'reviewRating', u'description'] + current scope: ['http://schema.org/Review'] + properties: ['name', 'author', 'datePublished', 'reviewRating', 'description'] - current scope: [u'http://schema.org/Rating'] - properties: [u'worstRating', u'ratingValue', u'bestRating'] + current scope: ['http://schema.org/Rating'] + properties: ['worstRating', 'ratingValue', 'bestRating'] >>> @@ -543,22 +543,22 @@ Example:: This gets all first ``
  • `` elements under whatever it is its parent:: >>> xp("//li[1]") - [u'
  • 1
    • ', u'
  • 4
    • '] + ['
  • 1
    • ', '
  • 4
    • '] And this gets the first ``
  • `` element in the whole document:: >>> xp("(//li)[1]") - [u'
  • 1
    • '] + ['
  • 1
    • '] This gets all first ``
  • `` elements under an ``