gronod/headphones
1
0
Fork 1
mirror of https://github.com/rembo10/headphones.git synced 2026-05-02 09:49:36 +01:00
Code Issues Packages Projects Releases Wiki Activity

Include html5lib for BeautifulSoup

Browse Source 
BeautifulSoup needs lxml or html5, have included html5lib.

Also latest BeautifulSoup 4.1.3
This commit is contained in:
Ade
2012-09-06 10:47:07 +12:00
parent 7aac60cecd
commit b8c5782765
136 changed files with 87265 additions and 2428 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
html5lib/tests/testdata/encoding/test-yahoo-jp.dat vendored Normal file
View File

@@ -0,0 +1,10 @@
#data
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=euc-jp">
<!--京-->
<title>Yahoo! JAPAN</title>
<meta name="description" content="日本最大級のポータルサイト。検索、オークション、ニュース、メール、コミュニティ、ショッピング、など80以上のサービスを展開。あなたの生活をより豊かにする「ライフ・エンジン」を目指していきます。">
<style type="text/css" media="all">
#encoding
euc_jp

394
html5lib/tests/testdata/encoding/tests1.dat vendored Normal file
View File

File diff suppressed because one or more lines are too long

115
html5lib/tests/testdata/encoding/tests2.dat vendored Normal file
View File

@@ -0,0 +1,115 @@
#data
<meta
#encoding
windows-1252
#data
<
#encoding
windows-1252
#data
<!
#encoding
windows-1252
#data
<meta charset = "
#encoding
windows-1252
#data
<meta charset=euc_jp
#encoding
windows-1252
#data
<meta <meta charset='euc_jp'>
#encoding
euc_jp
#data
<meta charset = 'euc_jp'>
#encoding
euc_jp
#data
<!-- -->
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
#encoding
utf-8
#data
<!-- -->
<meta http-equiv="Content-Type" content="text/html; charset=utf
#encoding
windows-1252
#data
<meta http-equiv="Content-Type<meta charset="utf-8">
#encoding
windows-1252
#data
<meta http-equiv="Content-Type" content="text/html; charset='utf-8'">
#encoding
utf-8
#data
<meta http-equiv="Content-Type" content="text/html; charset='utf-8">
#encoding
windows-1252
#data
<meta
#encoding
windows-1252
#data
<meta charset =
#encoding
windows-1252
#data
<meta charset= utf-8
>
#encoding
utf-8
#data
<meta content = "text/html;
#encoding
windows-1252
#data
<meta charset="UTF-16">
#encoding
utf-8
#data
<meta charset="UTF-16LE">
#encoding
utf-8
#data
<meta charset="UTF-16BE">
#encoding
utf-8
#data
<html a=ñ>
<meta charset="utf-8">
#encoding
utf-8
#data
<html ñ>
<meta charset="utf-8">
#encoding
utf-8
#data
<html>ñ
<meta charset="utf-8">
#encoding
utf-8