zetaben-Html2Feedbooks 0.1

data/README

@@ -0,0 +1,11 @@
+HTML2Feedbooks
+==============
+
+A script to automate basic publishing work on Feedbooks.com.
+
+Usage
+-----
+
+./html2fb URL.html
+
+You can change settings in confs/conf.yaml

data/bin/html2fb.rb

@@ -0,0 +1,31 @@
+#!/usr/bin/ruby
+require 'open-uri'
+require 'conf.rb'
+require 'downloader.rb'
+require 'document.rb'
+require 'parser.rb'
+require 'feedbooks.rb'
+
+include HTML2FB
+
+valid=false
+entry=ARGV[0]
+while !valid
+	url=nil
+	begin
+		url=Downloader.valid_url?(entry)
+		valid=true
+	rescue Exception => e 
+		STDERR.puts 'Invalid URL' unless entry.nil? || entry==''
+		valid=false
+		puts e
+	end
+	print "URL : " if entry.nil? || entry==''
+	entry=STDIN.readline.strip unless valid
+end
+conf=Conf.new('conf.yaml')
+content=Downloader.download(url)
+#puts content.size
+doc=Parser.new(conf).parse(content)
+puts doc.toc.to_yaml
+doc.to_feedbooks(conf)

data/confs/conf.yaml

@@ -0,0 +1,26 @@
+remove: 
+   class:
+        - totoc
+        - pagenum
+        - totoi
+        - img
+   expr:
+        - 'table' 
+        - //pre
+   between:
+        - 
+          - "//body"
+          - "//body/h3[4]"
+   after:
+          - '/html/body/h4[3]'
+select:
+   expr: h3
+   select: 
+        expr: h4
+
+fb:
+   user: #ask#
+   bookid: #ask#
+   booktype: userbook
+   pass: #ask#
+   host: 'feedbooks.com'

data/lib/app.rb

@@ -0,0 +1,49 @@
+require 'digest/md5'
+require 'open-uri'
+require 'net/http'
+require 'time'
+
+class AtomPost
+	attr_accessor :title
+	attr_accessor :content
+	attr_accessor :date
+	attr_accessor :author
+	attr_accessor :addr
+	attr_accessor :user
+	attr_accessor :pass
+
+	def initialize(addrs=nil)
+		self.addr=addrs unless addrs.nil?
+	end
+
+	def send
+		raise StandardError.new('Missing Address') if addr.nil?
+		#3: Detailed control
+		url = URI.parse(addr)
+		req = Net::HTTP::Post.new(url.path)
+		req.basic_auth user,pass  unless user.nil?
+
+		req.body  = '<?xml version="1.0"?>'+"\n"
+		req.body  +='<entry xmlns="http://www.w3.org/2005/Atom">'+"\n"
+		req.body  +='<title>'+title+'</title>'+"\n"
+		req.body  +='<id>'+Digest::MD5.hexdigest(title+content)+'</id>'+"\n"
+		req.body  +='<updated>'+date.xmlschema+'</updated>'+"\n"
+		req.body  +='<author><name>'+author+'</name></author>'+"\n"
+		req.body  +='<content>'+content+'</content>'+"\n"
+		req.body  +='</entry>'+"\n"
+
+		req.set_content_type('application/atom+xml;type=entry')
+
+		File.open('/tmp/test4.txt','w') do |f|
+			f << req.body
+		end
+
+		res = Net::HTTP.new(url.host, url.port).start {|http| http.request(req) }
+		case res
+		when Net::HTTPSuccess, Net::HTTPRedirection
+			# OK
+		else
+			res.error!
+		end
+	end
+end

data/lib/conf.rb

@@ -0,0 +1,22 @@
+
+module HTML2FB
+	class Conf
+		def initialize(file)
+			['./',"#{File.dirname(__FILE__)}/","#{File.dirname(__FILE__)}/../confs/"].each do |p|
+				f=p+file
+				begin
+					if File.readable?(f) && File.exists?(f)
+						@conf=File.open(f,'r'){|txt| YAML::load(txt)}
+						return 
+					end
+				rescue Exception => e 
+					STDERR.puts('unreadable conf : '+f+"\n"+e)
+				end
+			end
+		end
+
+		def [](x)
+			@conf[x]
+		end
+	end
+end

data/lib/document.rb

@@ -0,0 +1,56 @@
+module HTML2FB
+
+	class Section
+		attr_accessor :title
+		attr_accessor :content
+
+		def initialize
+			@content=[]
+		end
+
+		def to_html
+			content.collect{|e|e.to_html}.join
+		end
+
+		def titles
+			tit=[]
+			content.each do |f|
+				if f.is_a?Section
+					tit.push f.title
+				else
+					tit.push '#text'
+				end
+			end
+
+			return [title,tit]
+		end
+
+		def to_s
+			return "title :#{title}  \n"+content.collect{|a|a.to_s}.join("\n\n")
+		end
+	end
+
+	class Document < Section
+		def toc
+			#return content
+			return content.collect{|a|a.titles}
+		end
+		
+	end
+
+	class Text
+		attr_accessor :content
+
+		def initialize(c='')
+			@content=c
+		end
+
+		def to_html
+			@content
+		end
+
+		def to_s
+			@content
+		end
+	end
+end

data/lib/downloader.rb

@@ -0,0 +1,24 @@
+require 'open-uri'
+require 'tempfile'
+
+module HTML2FB
+	class Downloader
+		def self.valid_url?(entry)
+			uri=URI.parse(entry)
+			Kernel.open(uri.to_s,'r')
+			return uri
+		end
+
+		def self.download(uri)
+			print "Downloading   "
+			puts uri.to_s
+			#tmp=Tempfile.new(uri.gsub(/[^a-z0-9]/,'_'))
+			#tmp.open('w'){|a|
+			#	uri.open('r'){|b|
+			#		a.write b
+			#	}
+			#}
+			Kernel.open(uri.to_s,'r').read
+		end
+	end
+end

data/lib/feedbooks.rb

@@ -0,0 +1,99 @@
+require 'app.rb'
+require 'hpricot'
+require 'digest/md5'
+
+module HTML2FB
+
+	class FBSession
+
+		attr_accessor :bookid
+		attr_accessor :booktype
+		attr_accessor :user
+		attr_accessor :pass
+		attr_accessor :host
+		@@fbsession=nil
+		def initialize(conf)
+			StandardError.new('Already in session') unless @@fbsession.nil?
+			@@fbsession=self
+			self.bookid=ask(conf['fb']['bookid'],"Book Id")
+			self.booktype=ask(conf['fb']['booktype'],"Book Type")
+			self.user=ask(conf['fb']['user'],"User")
+			self.pass=ask(conf['fb']['pass'],"Pass")
+			self.host=conf['fb']['host']
+			self.host='feedbooks.com' if @host.nil?
+		end
+
+		def self.session
+			return @@fbsession
+		end
+
+		def pass=(pas)
+
+			if pas.gsub(/[^a-z0-9]/,'').size==32
+				@pass=pas
+			else
+				@pass= Digest::MD5.hexdigest(pas)
+			end
+		end
+	end
+
+
+	class Document
+		def to_feedbooks(conf)
+			FBSession.new(conf)
+			#File.open('/tmp/test3.html','w') do |f|
+				content.each do |e|
+			#		f << e.to_feedbooks(conf)
+					 e.to_feedbooks(conf)
+			#		f << " \n " *  10
+				end
+			#end
+		end
+	end
+
+	class Section
+		@@level=0
+		def to_feedbooks(conf)
+			fb=FBSession.session
+			post=AtomPost.new "http://#{fb.host}/#{fb.booktype}/#{fb.bookid}/contents.atom"
+			doc=Hpricot('<div xmlns:xhtml="http://www.w3.org/1999/xhtml">'+to_html+'</div>')
+			doc.traverse_all_element do |e|
+				unless e.is_a?Hpricot::Text 
+					e.stag.name='xhtml:'+e.stag.name
+					e.etag.name='xhtml:'+e.etag.name unless e.etag.nil?
+				end
+			end
+			post.content=doc.to_html
+			post.user=fb.user
+			post.pass=fb.pass
+			post.date=Time.now
+			post.author=fb.user
+			post.title=title
+			post.send
+		end
+
+		alias :old_to_html :to_html
+
+		def to_html
+			ret=nil
+			@@level+=1
+			if @@level==1
+				ret=old_to_html
+			else
+				ret="<h#{@@level+1}>"+title+"</h#{@@level+1}>"+old_to_html
+			end
+			@@level-=1
+			ret
+		end
+	end
+end
+
+def ask(txt,disp='Prompt')
+	return txt unless txt.nil? || txt =='#ask#'
+	begin
+		txt=nil
+		print disp+' : '
+		txt=STDIN.readline.strip
+	end while txt.nil? || txt.size==0
+	txt
+end

data/lib/parser.rb

@@ -0,0 +1,138 @@
+require 'hpricot'
+require 'document.rb'
+
+module HTML2FB
+	class Parser
+
+		def initialize(conf)
+			@conf=conf
+		end
+
+		def parse(txt)
+			pdoc=Hpricot(txt)
+			doc=Document.new
+			remove_objs(pdoc)
+			ti=pdoc.at('title')
+			doc.title= ti.inner_text.strip unless ti.nil?
+			#			pdoc.search('//h3').each do |e|
+			#				doc.content.push(e.inner_text)
+			#			end
+
+			parse_text(pdoc,doc)	
+
+			return doc
+		end
+		protected
+
+		def remove_objs(doc)
+			if @conf['remove'] then
+				@conf['remove']['class'].each do |cl|
+					doc.search('.'+cl).remove
+				end unless @conf['remove']['class'].nil?
+				@conf['remove']['expr'].each do |cl|
+					doc.search(cl).remove
+				end unless @conf['remove']['expr'].nil?
+				@conf['remove']['before'].each do |cl|
+					x=doc.at(cl)
+					x.preceding.remove
+					x.parent.children.delete(x)
+				end unless @conf['remove']['before'].nil?
+				@conf['remove']['between'].each do |cl|
+#					puts "between "+cl.inspect
+					doc.between(cl.first,cl.last).remove
+				end unless @conf['remove']['between'].nil?
+				@conf['remove']['after'].each do |cl|
+					x=doc.at(cl)
+					x.following.remove
+					x.parent.children.delete(x)
+				end unless @conf['remove']['after'].nil?
+			end
+			File.open('/tmp/test.html','w'){|f| f.write doc.to_html}
+		end
+
+		def parse_text(doc,ret)
+			ti  = doc.search('//'+@conf['select']['expr'])
+			tit = ti.zip ti[1..-1]+[nil]
+
+			tit.each do |a|
+				s=Section.new
+				tmp=doc.between(a.first.xpath,a.last.nil? ? nil : a.last.xpath).to_html
+				tmp.sub!(a.first.to_original_html,'')
+				s.content =[Text.new(tmp)]
+				s.title = a.first.inner_text.to_s
+				ret.content.push s
+				
+			end
+
+			if @conf['select']['select']
+				conf=@conf['select']
+				parse_rec(ret,conf)
+			end
+		end
+
+		protected
+
+		def parse_rec(el,conf) 
+			return if conf.nil?
+			if el.is_a?Section
+				el.content.each do |l|
+					if l.is_a?Section
+						parse_rec(l,conf['select'])
+					else
+						doc=Hpricot(l.content)
+						ti  = doc.search('//'+conf['expr'])
+						return if ti.size ==0
+						tit = ti.zip ti[1..-1]+[nil]
+
+						tit.each do |a|
+							s=Section.new
+							tmp=doc.between(a.first.xpath,a.last.nil? ? nil : a.last.xpath).to_html
+							s.content = [Text.new(tmp)]
+							s.title = a.first.inner_text.to_s
+							el.content.push s
+							l.content.sub!(tmp,'')
+							l.content.sub!(a.first.to_original_html,'')
+						end
+
+					end
+				end
+			end
+		end
+	end
+end
+
+
+class String
+	def blank?
+		self==""
+	end
+end
+
+class NilClass
+	def blank?
+		true
+	end
+end
+
+module Hpricot::Traverse
+	def between(i,j)
+		#puts i,j
+		unless j.nil?
+			prec=self.at(i).preceding
+			Hpricot::Elements[*self.at(j).preceding.find_all{|el| !prec.include?el}]
+		else
+			self.at(i).following
+		end
+	end
+end
+
+
+class Hpricot::Elements
+	def between(i,j)
+		Hpricot::Elements[*self.collect{|a| a.between(i,j)}]
+	end
+
+	def -(a)
+		Hpricot::Elements[*self.find_all{|el| !a.include?el}]
+	end
+end

metadata

@@ -0,0 +1,70 @@
+--- !ruby/object:Gem::Specification 
+name: zetaben-Html2Feedbooks
+version: !ruby/object:Gem::Version 
+  version: "0.1"
+platform: ruby
+authors: 
+- Benoit Larroque
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2009-04-28 00:00:00 -07:00
+default_executable: html2fb.rb
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: hpricot
+  type: :runtime
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: "0.6"
+    version: 
+description: Html2Feedbooks is script to automate basic publishing on feedbooks.com
+email: zeta dot ben at gmail dot com
+executables: 
+- html2fb.rb
+extensions: []
+
+extra_rdoc_files: []
+
+files: 
+- README
+- confs/conf.yaml
+- lib/app.rb
+- lib/conf.rb
+- lib/document.rb
+- lib/downloader.rb
+- lib/feedbooks.rb
+- bin/html2fb.rb
+- lib/parser.rb
+has_rdoc: true
+homepage: http://github.com/Html2Feedbooks
+post_install_message: 
+rdoc_options: []
+
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.2.0
+signing_key: 
+specification_version: 2
+summary: Html2Feedbooks is script to automate basic publishing on feedbooks.com
+test_files: []
+