bennylope · October 5, 2011 15:23 · Oct 5, 2011 · Jul 30, 2011 · Jul 30, 2011 · Jul 30, 2011
diff --git a/blogspot_to_jekyll.rb b/blogspot_to_jekyll.rb
@@ -22,8 +22,11 @@
 #  * Make sure Blogger shows full output of article in feeds.
 #  * Commenting on migrated articles will be set to false by default.
 
+# Add rubygems so that Ruby can find the installed gems
+require 'rubygems'
 require 'feedzirra'
 require 'date'
+require 'time'
 require 'optparse'
 
 
@@ -32,7 +35,10 @@ def parse_post_entries(feed, verbose)
   feed.entries.each do |post|
     obj = Hash.new
     created_datetime = post.last_modified
-    creation_date = Date.strptime(created_datetime.to_s, "%Y-%m-%d")
+    # The previous line, immediately below, threw an ArgumentError, "invalid date"
+    # and just using a time object instead solved the error
+    #creation_date = Date.strptime(created_datetime.to_s, "%Y-%m-%d")
+    creation_date = Date.parse(created_datetime.strftime("%Y-%m-%d"))
     title = post.title
     file_name = creation_date.to_s + "-" + title.split(/  */).join("-").delete('\/') + ".html"
     content = post.content
@@ -108,4 +114,4 @@ def main
   puts "Done!"
 end
 
-main()
+main()
diff --git a/blogspot_to_jekyll.rb b/blogspot_to_jekyll.rb
@@ -5,7 +5,7 @@
 # Basic Usage
 # -----------
 #
-#   ruby blogger_to_jekyll.rb feed_url
+#   ./blogger_to_jekyll.rb feed_url
 #
 #  where `feed_url` can have the following format:
 #
@@ -16,6 +16,11 @@
 # 
 #  * feedzirra: https://github.com/pauldix/feedzirra
 #
+# Notes
+# -----
+#
+#  * Make sure Blogger shows full output of article in feeds.
+#  * Commenting on migrated articles will be set to false by default.
 
 require 'feedzirra'
 require 'date'
@@ -36,6 +41,7 @@ def parse_post_entries(feed, verbose)
     obj["title"] = title
     obj["creation_datetime"] = created_datetime
     obj["content"] = content
+    obj["categories"] = post.categories.join(" ")
     posts.push(obj)
   end
   return posts
@@ -52,7 +58,7 @@ def write_posts(posts, verbose)
 title: #{post["title"]}
 date: #{post["creation_datetime"]}
 comments: false
-categories:
+categories: #{post["categories"]}
 ---
 
 }
@@ -72,7 +78,7 @@ def write_posts(posts, verbose)
 def main
   options = {}
   opt_parser = OptionParser.new do |opt|
-    opt.banner = "Usage: blogger_to_jekyll.rb FEED_URL [OPTIONS]"
+    opt.banner = "Usage: ./blogger_to_jekyll.rb FEED_URL [OPTIONS]"
     opt.separator ""
     opt.separator "Options"
 

diff --git a/blogspot_to_jekyll.rb b/blogspot_to_jekyll.rb
@@ -30,11 +30,12 @@ def parse_post_entries(feed, verbose)
     creation_date = Date.strptime(created_datetime.to_s, "%Y-%m-%d")
     title = post.title
     file_name = creation_date.to_s + "-" + title.split(/  */).join("-").delete('\/') + ".html"
-
+    content = post.content
+
     obj["file_name"] = file_name
     obj["title"] = title
     obj["creation_datetime"] = created_datetime
-    obj["content"] = post.content
+    obj["content"] = content
     posts.push(obj)
   end
   return posts
@@ -54,7 +55,7 @@ def write_posts(posts, verbose)
 categories:
 ---
 
-%}
+}
     File.open(file_name, "w+") {|f|
       f.write(header)
       f.write(post["content"])

diff --git a/blogspot_to_jekyll.rb b/blogspot_to_jekyll.rb
@@ -11,13 +11,6 @@
 #
 #  http://{your_blog_name}.blogspot.com/feeds/posts/default
 #
-# Documentation
-# -------------
-#
-# Command-line arguments:
-#   -v 
-#
-#
 # Requirements
 # ------------
 # 

diff --git a/blogspot_to_jekyll.rb b/blogspot_to_jekyll.rb
@@ -1,47 +1,42 @@
+#!/usr/bin/env ruby
+#
 # Convert blogger (blogspot) posts to jekyll posts
 #
-# How to use
-# ----------
+# Basic Usage
+# -----------
 #
-# ruby blogger_to_jekyll.rb [feed_url]
+#   ruby blogger_to_jekyll.rb feed_url
 #
-# What it does
-# ------------
+#  where `feed_url` can have the following format:
 #
-# 1) Fetches the blog's feed
-# 2) For each post create a file with name
-#    "YYYY-MM-DD-{post-title}.html", with the following structure:
+#  http://{your_blog_name}.blogspot.com/feeds/posts/default
 #
-#       ---
-#       layout: post
-#       title: #{post-title}
-#       date: #{YYYY-mm-dd HH:MM}
-#       comments: false
-#       categories: 
-#       ---
+# Documentation
+# -------------
 #
-#       #{blog_post_content_in_html_format}
+# Command-line arguments:
+#   -v 
 #
-# 3) Write each file to a directory named `_posts`
 #
 # Requirements
 # ------------
-#
+# 
 #  * feedzirra: https://github.com/pauldix/feedzirra
 #
 
 require 'feedzirra'
 require 'date'
+require 'optparse'
 
 
-def parse_post_entries(feed)
+def parse_post_entries(feed, verbose)
   posts = []
   feed.entries.each do |post|
     obj = Hash.new
     created_datetime = post.last_modified
     creation_date = Date.strptime(created_datetime.to_s, "%Y-%m-%d")
     title = post.title
-    file_name = creation_date.to_s + "-" + title.split(/  */).join("-").delete('\/') + ".markdown"
+    file_name = creation_date.to_s + "-" + title.split(/  */).join("-").delete('\/') + ".html"
 
     obj["file_name"] = file_name
     obj["title"] = title
@@ -52,9 +47,10 @@ def parse_post_entries(feed)
   return posts
 end
 
-def write_posts(posts)
+def write_posts(posts, verbose)
   Dir.mkdir("_posts") unless File.directory?("_posts")
 
+  total = posts.length, i = 1
   posts.each do |post|
     file_name = "_posts/".concat(post["file_name"])
     header = %{---           
@@ -71,20 +67,45 @@ def write_posts(posts)
       f.write(post["content"])
       f.close
     }
+
+    if verbose
+      puts "  [#{i}/#{total[0]}] Written post #{file_name}"
+      i += 1
+    end
   end
 end
 
 def main
-  feed_url = ARGV.first
+  options = {}
+  opt_parser = OptionParser.new do |opt|
+    opt.banner = "Usage: blogger_to_jekyll.rb FEED_URL [OPTIONS]"
+    opt.separator ""
+    opt.separator "Options"
+
+    opt.on("-v", "--verbose", "Print out all.") do
+      options[:verbose] = true
+    end
+  end
+
+  opt_parser.parse!
 
-  puts "Fetching feed..."
+  if ARGV[0]
+    feed_url = ARGV.first
+  else
+    puts opt_parser
+    exit()
+  end
+
+  puts "Fetching feed #{feed_url}..."
   feed = Feedzirra::Feed.fetch_and_parse(feed_url)
 
   puts "Parsing feed..."
-  posts = parse_post_entries(feed)
+  posts = parse_post_entries(feed, options[:verbose])
 
-  puts "Writing posts..."
-  write_posts(posts)
+  puts "Writing posts to _posts/..."
+  write_posts(posts, options[:verbose])
+
+  puts "Done!"
 end
 
 main()
diff --git a/blogspot_to_jekyll.rb b/blogspot_to_jekyll.rb
@@ -1,5 +1,10 @@
 # Convert blogger (blogspot) posts to jekyll posts
 #
+# How to use
+# ----------
+#
+# ruby blogger_to_jekyll.rb [feed_url]
+#
 # What it does
 # ------------
 #
@@ -9,29 +14,26 @@
 #
 #       ---
 #       layout: post
-#       title: {post-title}
-#       date: {YYYY-mm-dd HH:MM}
+#       title: #{post-title}
+#       date: #{YYYY-mm-dd HH:MM}
 #       comments: false
 #       categories: 
 #       ---
 #
 #       #{blog_post_content_in_html_format}
+#
 # 3) Write each file to a directory named `_posts`
 #
 # Requirements
 # ------------
 #
 #  * feedzirra: https://github.com/pauldix/feedzirra
 #
-# How to use
-# ----------
-#
-# ruby blogger_to_jekyll.rb [feed_url]
-#
 
 require 'feedzirra'
 require 'date'
 
+
 def parse_post_entries(feed)
   posts = []
   feed.entries.each do |post|
@@ -72,12 +74,15 @@ def write_posts(posts)
   end
 end
 
-def main(feed_url="http://feeds.feedburner.com/Kennys/dev/null?format=xml")
+def main
+  feed_url = ARGV.first
+
   puts "Fetching feed..."
   feed = Feedzirra::Feed.fetch_and_parse(feed_url)
 
   puts "Parsing feed..."
   posts = parse_post_entries(feed)
+
   puts "Writing posts..."
   write_posts(posts)
 end

diff --git a/blogspot_to_jekyll.rb b/blogspot_to_jekyll.rb
@@ -1,19 +1,33 @@
-# Short overview:
-# 1) Fetch blogger feed
-# 2) For each post in feed
-#    1) create a file with name `YYYY-MM-DD-post-title.markdown`, with
-#       the following structure:
+# Convert blogger (blogspot) posts to jekyll posts
+#
+# What it does
+# ------------
+#
+# 1) Fetches the blog's feed
+# 2) For each post create a file with name
+#    "YYYY-MM-DD-{post-title}.html", with the following structure:
 #
 #       ---
 #       layout: post
-#       title: `post-title`
-#       date: 2011-07-30 10:44
-#       comments: true
+#       title: {post-title}
+#       date: {YYYY-mm-dd HH:MM}
+#       comments: false
 #       categories: 
 #       ---
 #
-#       #{blog_post_content_in_markdown_format}
-# 3) Write each file to a directory `_posts`
+#       #{blog_post_content_in_html_format}
+# 3) Write each file to a directory named `_posts`
+#
+# Requirements
+# ------------
+#
+#  * feedzirra: https://github.com/pauldix/feedzirra
+#
+# How to use
+# ----------
+#
+# ruby blogger_to_jekyll.rb [feed_url]
+#
 
 require 'feedzirra'
 require 'date'

diff --git a/blogspot_to_jekyll.rb b/blogspot_to_jekyll.rb
@@ -0,0 +1,71 @@
+# Short overview:
+# 1) Fetch blogger feed
+# 2) For each post in feed
+#    1) create a file with name `YYYY-MM-DD-post-title.markdown`, with
+#       the following structure:
+#
+#       ---
+#       layout: post
+#       title: `post-title`
+#       date: 2011-07-30 10:44
+#       comments: true
+#       categories: 
+#       ---
+#
+#       #{blog_post_content_in_markdown_format}
+# 3) Write each file to a directory `_posts`
+
+require 'feedzirra'
+require 'date'
+
+def parse_post_entries(feed)
+  posts = []
+  feed.entries.each do |post|
+    obj = Hash.new
+    created_datetime = post.last_modified
+    creation_date = Date.strptime(created_datetime.to_s, "%Y-%m-%d")
+    title = post.title
+    file_name = creation_date.to_s + "-" + title.split(/  */).join("-").delete('\/') + ".markdown"
+
+    obj["file_name"] = file_name
+    obj["title"] = title
+    obj["creation_datetime"] = created_datetime
+    obj["content"] = post.content
+    posts.push(obj)
+  end
+  return posts
+end
+
+def write_posts(posts)
+  Dir.mkdir("_posts") unless File.directory?("_posts")
+
+  posts.each do |post|
+    file_name = "_posts/".concat(post["file_name"])
+    header = %{---           
+layout: post
+title: #{post["title"]}
+date: #{post["creation_datetime"]}
+comments: false
+categories:
+---
+
+%}
+    File.open(file_name, "w+") {|f|
+      f.write(header)
+      f.write(post["content"])
+      f.close
+    }
+  end
+end
+
+def main(feed_url="http://feeds.feedburner.com/Kennys/dev/null?format=xml")
+  puts "Fetching feed..."
+  feed = Feedzirra::Feed.fetch_and_parse(feed_url)
+
+  puts "Parsing feed..."
+  posts = parse_post_entries(feed)
+  puts "Writing posts..."
+  write_posts(posts)
+end
+
+main()