Merge pull request #1774 from scrapy/backport-1.1

[MRG+1] [1.1.x][backport] #1766, #1770, #1750, #1662, #1765

docs/news.rst

@@ -97,6 +97,7 @@ Additional New Features and Enhancements
 
 - Dict-like settings now have per-key priorities
   (:issue:`1135`, :issue:`1149` and :issue:`1586`).
+- Sending non-ASCII emails (:issue:`1662`)
 - ``CloseSpider`` and ``SpiderState`` extensions now get disabled if no relevant
   setting is set (:issue:`1723`, :issue:`1725`).
 - Added method ``ExecutionEngine.close`` (:issue:`1423`).
@@ -105,7 +106,7 @@ Additional New Features and Enhancements
   :issue:`1335`, :issue:`1683`, :issue:`1660`, :issue:`1642`, :issue:`1721`,
   :issue:`1727`).
 - Other refactoring, optimizations and cleanup (:issue:`1476`, :issue:`1481`,
-  :issue:`1477`, :issue:`1315` and :issue:`1290`).
+  :issue:`1477`, :issue:`1315`, :issue:`1290` and :issue:`1750`).
 
 .. _`Code of Conduct`: https://github.com/scrapy/scrapy/blob/master/CODE_OF_CONDUCT.md
 
@@ -124,6 +125,9 @@ Deprecations and Removals
   + ``scrapy.utils.datatypes.MultiValueDict``
   + ``scrapy.utils.datatypes.SiteNode``
 
+- The previously bundled ``scrapy.xlib.pydispatch`` library was deprecated and
+  replaced by `pydispatcher <https://pypi.python.org/pypi/PyDispatcher>`_.
+
 
 Relocations
 ~~~~~~~~~~~

docs/topics/email.rst

@@ -76,7 +76,7 @@ uses `Twisted non-blocking IO`_, like the rest of the framework.
         :param settings: the e-mail recipients
         :type settings: :class:`scrapy.settings.Settings` object
 
-    .. method:: send(to, subject, body, cc=None, attachs=(), mimetype='text/plain')
+    .. method:: send(to, subject, body, cc=None, attachs=(), mimetype='text/plain', charset=None)
 
         Send email to the given recipients.
 
@@ -102,6 +102,9 @@ uses `Twisted non-blocking IO`_, like the rest of the framework.
         :param mimetype: the MIME type of the e-mail
         :type mimetype: str
 
+        :param charset: the character encoding to use for the e-mail contents
+        :type charset: str
+
 
 .. _topics-email-settings:
 

scrapy/core/engine.py

@@ -177,12 +177,23 @@ class ExecutionEngine(object):
         return d
 
     def spider_is_idle(self, spider):
-        scraper_idle = self.scraper.slot.is_idle()
-        pending = self.slot.scheduler.has_pending_requests()
-        downloading = bool(self.downloader.active)
-        pending_start_requests = self.slot.start_requests is not None
-        idle = scraper_idle and not (pending or downloading or pending_start_requests)
-        return idle
+        if not self.scraper.slot.is_idle():
+            # scraper is not idle
+            return False
+
+        if self.downloader.active:
+            # downloader has pending requests
+            return False
+
+        if self.slot.start_requests is not None:
+            # not all start requests are handled
+            return False
+
+        if self.slot.scheduler.has_pending_requests():
+            # scheduler has pending requests
+            return False
+
+        return True
 
     @property
     def open_spiders(self):

scrapy/http/cookies.py

@@ -137,13 +137,29 @@ class WrappedRequest(object):
         """
         return self.request.meta.get('is_unverifiable', False)
 
-    # python3 uses request.unverifiable
+    def get_origin_req_host(self):
+        return urlparse_cached(self.request).hostname
+
+    # python3 uses attributes instead of methods
+    @property
+    def full_url(self):
+        return self.get_full_url()
+
+    @property
+    def host(self):
+        return self.get_host()
+
+    @property
+    def type(self):
+        return self.get_type()
+
     @property
     def unverifiable(self):
         return self.is_unverifiable()
 
-    def get_origin_req_host(self):
-        return urlparse_cached(self.request).hostname
+    @property
+    def origin_req_host(self):
+        return self.get_origin_req_host()
 
     def has_header(self, name):
         return name in self.request.headers

scrapy/mail.py

@@ -43,7 +43,7 @@ class MailSender(object):
             settings['MAIL_PASS'], settings.getint('MAIL_PORT'),
             settings.getbool('MAIL_TLS'), settings.getbool('MAIL_SSL'))
 
-    def send(self, to, subject, body, cc=None, attachs=(), mimetype='text/plain', _callback=None):
+    def send(self, to, subject, body, cc=None, attachs=(), mimetype='text/plain', charset=None, _callback=None):
         if attachs:
             msg = MIMEMultipart()
         else:
@@ -57,8 +57,11 @@ class MailSender(object):
             rcpts.extend(cc)
             msg['Cc'] = COMMASPACE.join(cc)
 
+        if charset:
+            msg.set_charset(charset)
+
         if attachs:
-            msg.attach(MIMEText(body))
+            msg.attach(MIMEText(body, 'plain', charset or 'us-ascii'))
             for attach_name, mimetype, f in attachs:
                 part = MIMEBase(*mimetype.split('/'))
                 part.set_payload(f.read())

scrapy/spiders/sitemap.py

@@ -32,7 +32,7 @@ class SitemapSpider(Spider):
 
     def _parse_sitemap(self, response):
         if response.url.endswith('/robots.txt'):
-            for url in sitemap_urls_from_robots(response.body):
+            for url in sitemap_urls_from_robots(response.text):
                 yield Request(url, callback=self._parse_sitemap)
         else:
             body = self._get_sitemap_body(response)

scrapy/xlib/pydispatch.py

@@ -0,0 +1,19 @@
+from __future__ import absolute_import
+
+import warnings
+from scrapy.exceptions import ScrapyDeprecationWarning
+
+from pydispatch import (
+    dispatcher,
+    errors,
+    robust,
+    robustapply,
+    saferef,
+)
+
+warnings.warn("Importing from scrapy.xlib.pydispatch is deprecated and will"
+              " no longer be supported in future Scrapy versions."
+              " If you just want to connect signals use the from_crawler class method,"
+              " otherwise import pydispatch directly if needed."
+              " See: https://github.com/scrapy/scrapy/issues/1762",
+              ScrapyDeprecationWarning, stacklevel=2)

tests/test_http_cookies.py

@@ -14,12 +14,15 @@ class WrappedRequestTest(TestCase):
 
     def test_get_full_url(self):
         self.assertEqual(self.wrapped.get_full_url(), self.request.url)
+        self.assertEqual(self.wrapped.full_url, self.request.url)
 
     def test_get_host(self):
         self.assertEqual(self.wrapped.get_host(), urlparse(self.request.url).netloc)
+        self.assertEqual(self.wrapped.host, urlparse(self.request.url).netloc)
 
     def test_get_type(self):
         self.assertEqual(self.wrapped.get_type(), urlparse(self.request.url).scheme)
+        self.assertEqual(self.wrapped.type, urlparse(self.request.url).scheme)
 
     def test_is_unverifiable(self):
         self.assertFalse(self.wrapped.is_unverifiable())
@@ -32,6 +35,7 @@ class WrappedRequestTest(TestCase):
 
     def test_get_origin_req_host(self):
         self.assertEqual(self.wrapped.get_origin_req_host(), 'www.example.com')
+        self.assertEqual(self.wrapped.origin_req_host, 'www.example.com')
 
     def test_has_header(self):
         self.assertTrue(self.wrapped.has_header('content-type'))

tests/test_mail.py

@@ -1,5 +1,8 @@
+# coding=utf-8
+
 import unittest
 from io import BytesIO
+from email.charset import Charset
 
 from scrapy.mail import MailSender
 
@@ -54,11 +57,58 @@ class MailSenderTest(unittest.TestCase):
 
         text, attach = payload
         self.assertEqual(text.get_payload(decode=True), b'body')
+        self.assertEqual(text.get_charset(), Charset('us-ascii'))
         self.assertEqual(attach.get_payload(decode=True), b'content')
 
     def _catch_mail_sent(self, **kwargs):
         self.catched_msg = dict(**kwargs)
 
+    def test_send_utf8(self):
+        subject = u'sübjèçt'
+        body = u'bödÿ-àéïöñß'
+        mailsender = MailSender(debug=True)
+        mailsender.send(to=['test@scrapy.org'], subject=subject, body=body,
+                        charset='utf-8', _callback=self._catch_mail_sent)
+
+        assert self.catched_msg
+        self.assertEqual(self.catched_msg['subject'], subject)
+        self.assertEqual(self.catched_msg['body'], body)
+
+        msg = self.catched_msg['msg']
+        self.assertEqual(msg['subject'], subject)
+        self.assertEqual(msg.get_payload(), body)
+        self.assertEqual(msg.get_charset(), Charset('utf-8'))
+        self.assertEqual(msg.get('Content-Type'), 'text/plain; charset="utf-8"')
+
+    def test_send_attach_utf8(self):
+        subject = u'sübjèçt'
+        body = u'bödÿ-àéïöñß'
+        attach = BytesIO()
+        attach.write(body.encode('utf-8'))
+        attach.seek(0)
+        attachs = [('attachment', 'text/plain', attach)]
+
+        mailsender = MailSender(debug=True)
+        mailsender.send(to=['test@scrapy.org'], subject=subject, body=body,
+                        attachs=attachs, charset='utf-8', _callback=self._catch_mail_sent)
+
+        assert self.catched_msg
+        self.assertEqual(self.catched_msg['subject'], subject)
+        self.assertEqual(self.catched_msg['body'], body)
+
+        msg = self.catched_msg['msg']
+        self.assertEqual(msg['subject'], subject)
+        self.assertEqual(msg.get_charset(), Charset('utf-8'))
+        self.assertEqual(msg.get('Content-Type'), 'multipart/mixed; charset="utf-8"')
+
+        payload = msg.get_payload()
+        assert isinstance(payload, list)
+        self.assertEqual(len(payload), 2)
+
+        text, attach = payload
+        self.assertEqual(text.get_payload(decode=True).decode('utf-8'), body)
+        self.assertEqual(text.get_charset(), Charset('utf-8'))
+        self.assertEqual(attach.get_payload(decode=True).decode('utf-8'), body)
 
 if __name__ == "__main__":
     unittest.main()

tests/test_pydispatch_deprecated.py

@@ -0,0 +1,12 @@
+import unittest
+import warnings
+from six.moves import reload_module
+
+
+class DeprecatedPydispatchTest(unittest.TestCase):
+    def test_import_xlib_pydispatch_show_warning(self):
+        with warnings.catch_warnings(record=True) as w:
+            from scrapy.xlib import pydispatch
+            reload_module(pydispatch)
+        self.assertIn('Importing from scrapy.xlib.pydispatch is deprecated',
+                      str(w[0].message))

tests/test_spider.py

@@ -328,6 +328,18 @@ class SitemapSpiderTest(SpiderTest):
         r = Response(url="http://www.example.com/sitemap.xml.gz", body=self.GZBODY)
         self.assertSitemapBody(r, self.BODY)
 
+    def test_get_sitemap_urls_from_robotstxt(self):
+        robots = b"""# Sitemap files
+Sitemap: http://example.com/sitemap.xml
+Sitemap: http://example.com/sitemap-product-index.xml
+"""
+
+        r = TextResponse(url="http://www.example.com/robots.txt", body=robots)
+        spider = self.spider_class("example.com")
+        self.assertEqual([req.url for req in spider._parse_sitemap(r)],
+                         ['http://example.com/sitemap.xml',
+                          'http://example.com/sitemap-product-index.xml'])
+
 
 class BaseSpiderDeprecationTest(unittest.TestCase):