Merge pull request #1015 from Mmdixon/pandas-update

Update pandas documentation (0.24.2)

Author: jmerle

lib/docs/filters/pandas/entries.rb

@@ -2,8 +2,10 @@ module Docs
   class Pandas
     class EntriesFilter < Docs::EntriesFilter
       def get_name
-        if subpath.start_with?('generated')
-          name = at_css('dt').content.strip
+        if subpath.start_with?('generated') || (subpath.include?('reference') && !subpath.include?('reference/index'))
+          name_node = at_css('dt')
+          name_node = at_css('h1') if name_node.nil?
+          name = name_node.content.strip
           name.sub! %r{\(.*}, '()'
           name.remove! %r{\s=.*}
           name.remove! %r{\A(class(method)?) (pandas\.)?}
@@ -16,7 +18,7 @@ def get_name
       end
 
       def get_type
-        if subpath.start_with?('generated')
+        if subpath.start_with?('generated') || (subpath.include?('reference') && !subpath.include?('reference/index'))
           css('.toctree-l2.current > a').last.content.remove(/\s\(.+?\)/)
         else
           'Manual'

lib/docs/scrapers/pandas.rb

@@ -14,40 +14,51 @@ class Pandas < UrlScraper
     options[:container] = '.document'
 
     options[:skip] = %w(internals.html release.html contributing.html whatsnew.html)
+    options[:skip_patterns] = [/whatsnew\//]
 
     options[:attribution] = <<-HTML
       &copy; 2008&ndash;2012, AQR Capital Management, LLC, Lambda Foundry, Inc. and PyData Development Team<br>
       Licensed under the 3-clause BSD License.
     HTML
 
+    version '0.25' do
+      self.release = '0.25.0'
+      self.base_url = "https://pandas.pydata.org/pandas-docs/version/#{self.release}/"
+    end
+
+    version '0.24' do
+      self.release = '0.24.2'
+      self.base_url = "https://pandas.pydata.org/pandas-docs/version/#{self.release}/"
+    end
+
     version '0.23' do
       self.release = '0.23.4'
-      self.base_url = "http://pandas.pydata.org/pandas-docs/version/#{self.release}/"
+      self.base_url = "https://pandas.pydata.org/pandas-docs/version/#{self.release}/"
     end
 
     version '0.22' do
       self.release = '0.22.0'
-      self.base_url = "http://pandas.pydata.org/pandas-docs/version/#{self.release}/"
+      self.base_url = "https://pandas.pydata.org/pandas-docs/version/#{self.release}/"
     end
 
     version '0.21' do
-      self.release = '0.21.0'
-      self.base_url = "http://pandas.pydata.org/pandas-docs/version/#{self.release}/"
+      self.release = '0.21.1'
+      self.base_url = "https://pandas.pydata.org/pandas-docs/version/#{self.release}/"
     end
 
     version '0.20' do
       self.release = '0.20.3'
-      self.base_url = "http://pandas.pydata.org/pandas-docs/version/#{self.release}/"
+      self.base_url = "https://pandas.pydata.org/pandas-docs/version/#{self.release}/"
     end
 
     version '0.19' do
       self.release = '0.19.2'
-      self.base_url = "http://pandas.pydata.org/pandas-docs/version/#{self.release}/"
+      self.base_url = "https://pandas.pydata.org/pandas-docs/version/#{self.release}/"
     end
 
     version '0.18' do
       self.release = '0.18.1'
-      self.base_url = "http://pandas.pydata.org/pandas-docs/version/#{self.release}/"
+      self.base_url = "https://pandas.pydata.org/pandas-docs/version/#{self.release}/"
     end
 
     def get_latest_version(opts)