https://github.com/scrapy/scrapy/commit/a38a99e0e2f3d69bb7a7aa50403c7aef3854cf00 From 1075587dbd15e5ccb9a83c4ca14086c1e135fe12 Mon Sep 17 00:00:00 2001 From: Paul Tremberth Date: Wed, 30 Mar 2016 14:31:10 +0200 Subject: [PATCH] Add support for Sphinx 1.4 See http://www.sphinx-doc.org/en/stable/changes.html#release-1-4-released-mar-28-2016 sphinx_rtd_theme has become optional, needs to be added to reqs https://github.com/sphinx-doc/sphinx/pull/2320 changes node entries tuples to 5 values instead of 4 `sh` syntax highlighting added very locally in selectors.rst because of this warning/error with Sphinx 1.4: ``` Warning, treated as error: /home/paul/src/scrapy/docs/topics/selectors.rst:743: WARNING: Could not lex literal_block as "python". Highlighting skipped. ``` --- docs/_ext/scrapydocs.py | 4 ++-- docs/topics/selectors.rst | 4 ++++ 2 files changed, 6 insertions(+), 2 deletions(-) diff --git a/docs/_ext/scrapydocs.py b/docs/_ext/scrapydocs.py index f0827f2..83b0d2c 100644 --- a/docs/_ext/scrapydocs.py +++ b/docs/_ext/scrapydocs.py @@ -18,7 +18,7 @@ def is_setting_index(node): if node.tagname == 'index': # index entries for setting directives look like: # [(u'pair', u'SETTING_NAME; setting', u'std:setting-SETTING_NAME', '')] - entry_type, info, refid, _ = node['entries'][0] + entry_type, info, refid = node['entries'][0][:3] return entry_type == 'pair' and info.endswith('; setting') return False @@ -30,7 +30,7 @@ def get_setting_target(node): def get_setting_name_and_refid(node): """Extract setting name from directive index node""" - entry_type, info, refid, _ = node['entries'][0] + entry_type, info, refid = node['entries'][0][:3] return info.replace('; setting', ''), refid diff --git a/docs/topics/selectors.rst b/docs/topics/selectors.rst index 688c2b7..12415d0 100644 --- a/docs/topics/selectors.rst +++ b/docs/topics/selectors.rst @@ -738,10 +738,14 @@ simple/convenient XPaths. You can use the Let's show an example that illustrates this with Github blog atom feed. +.. highlight:: sh + First, we open the shell with the url we want to scrape:: $ scrapy shell https://github.com/blog.atom +.. highlight:: python + Once in the shell we can try selecting all ```` objects and see that it doesn't work (because the Atom XML namespace is obfuscating those nodes)::