weeheavy/pelican-theme
1
0
Fork 0
forked from github/pelican
Code Pull requests Activity

Merge pull request #347 from sametmax/pandoc-parse-raw

Browse source 
Added strip raw option to wordpress xml importer
This commit is contained in:
Alexis Metaireau 2012-06-09 14:27:44 -07:00
commit cbe47d4416
4 changed files with 728 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

27
pelican/tools/pelican_import.py
View file

@ -25,8 +25,14 @@ def wp2fields(xml):
items = soup.rss.channel.findAll('item')
for item in items:
if item.fetch('wp:status')[0].contents[0] == "publish":
title = item.title.contents[0]
try:
title = item.title.contents[0]
except IndexError:
continue
content = item.fetch('content:encoded')[0].contents[0]
filename = item.fetch('wp:post_name')[0].contents[0]
@ -197,7 +203,7 @@ def build_markdown_header(title, date, author, categories, tags):
header += '\n'
return header
def fields2pelican(fields, out_markup, output_path, dircat=False):
def fields2pelican(fields, out_markup, output_path, dircat=False, strip_raw=False):
for title, content, filename, date, author, categories, tags, in_markup in fields:
if (in_markup == "markdown") or (out_markup == "markdown") :
ext = '.md'
@ -230,10 +236,13 @@ def fields2pelican(fields, out_markup, output_path, dircat=False):
paragraphs = [u'<p>{}</p>'.format(p) for p in paragraphs]
new_content = ''.join(paragraphs)
fp.write(content)
fp.write(new_content)
cmd = 'pandoc --normalize --reference-links --from=html --to={0} -o "{1}" "{2}"'.format(
out_markup, out_filename, html_filename)
parse_raw = '--parse-raw' if not strip_raw else ''
cmd = ('pandoc --normalize --reference-links {0} --from=html'
' --to={1} -o "{2}" "{3}"').format(
parse_raw, out_markup, out_filename, html_filename)
try:
rc = subprocess.call(cmd, shell=True)
@ -279,6 +288,10 @@ def main():
help='Output markup format (supports rst & markdown)')
parser.add_argument('--dir-cat', action='store_true', dest='dircat',
help='Put files in directories with categories name')
parser.add_argument('--strip-raw', action='store_true', dest='strip_raw',
help="Strip raw HTML code that can't be converted to "
"markup such as flash embeds or iframes (wordpress import only)")
args = parser.parse_args()
input_type = None
@ -306,4 +319,6 @@ def main():
elif input_type == 'feed':
fields = feed2fields(args.input)
fields2pelican(fields, args.markup, args.output, dircat=args.dircat or False)
fields2pelican(fields, args.markup, args.output,
dircat=args.dircat or False,
strip_raw=args.strip_raw or False)

578
tests/content/wordpressexport.xml Normal file
View file

@ -0,0 +1,578 @@
<?xml version="1.0" encoding="UTF-8" ?>
<!-- This is a WordPress eXtended RSS file generated by WordPress as an export of your site. -->
<!-- It contains information about your site's posts, pages, comments, categories, and other content. -->
<!-- You may use this file to transfer that content from one site to another. -->
<!-- This file is not intended to serve as a complete backup of your site. -->
<!-- To import this information into a WordPress site follow these steps: -->
<!-- 1. Log in to that site as an administrator. -->
<!-- 2. Go to Tools: Import in the WordPress admin panel. -->
<!-- 3. Install the "WordPress" importer from the list. -->
<!-- 4. Activate & Run Importer. -->
<!-- 5. Upload this file using the form provided on that page. -->
<!-- 6. You will first be asked to map the authors in this export file to users -->
<!-- on the site. For each author, you may choose to map to an -->
<!-- existing user on the site or to create a new user. -->
<!-- 7. WordPress will then import each of the posts, pages, comments, categories, etc. -->
<!-- contained in this file into your site. -->
<!-- generator="WordPress/3.3.1" created="2012-05-13 01:13" -->
<rss version="2.0"
xmlns:excerpt="http://wordpress.org/export/1.1/excerpt/"
xmlns:content="http://purl.org/rss/1.0/modules/content/"
xmlns:wfw="http://wellformedweb.org/CommentAPI/"
xmlns:dc="http://purl.org/dc/elements/1.1/"
xmlns:wp="http://wordpress.org/export/1.1/"
>
<channel>
<title>Pelican test channel</title>
<link>http://thisisa.test</link>
<description>Not a real feed, just for test</description>
<pubDate>Sun, 13 May 2012 01:13:52 +0000</pubDate>
<language>en</language>
<wp:wxr_version>1.1</wp:wxr_version>
<wp:base_site_url>http://thisisa.test</wp:base_site_url>
<wp:base_blog_url>http://thisisa.test</wp:base_blog_url>
<wp:author><wp:author_id>2</wp:author_id><wp:author_login>Bob</wp:author_login><wp:author_email>bob@thisisa.test</wp:author_email><wp:author_display_name><![CDATA[Bob]]></wp:author_display_name><wp:author_first_name><![CDATA[Bob]]></wp:author_first_name><wp:author_last_name><![CDATA[]]></wp:author_last_name></wp:author>
<wp:author><wp:author_id>3</wp:author_id><wp:author_login>Jonh</wp:author_login><wp:author_email>jonh@thisisa.test</wp:author_email><wp:author_display_name><![CDATA[Jonh]]></wp:author_display_name><wp:author_first_name><![CDATA[Jonh]]></wp:author_first_name><wp:author_last_name><![CDATA[]]></wp:author_last_name></wp:author>
<wp:category><wp:term_id>7</wp:term_id><wp:category_nicename>categ-1</wp:category_nicename><wp:category_parent></wp:category_parent><wp:cat_name><![CDATA[Category 1]]></wp:cat_name></wp:category>
<wp:category><wp:term_id>11</wp:term_id><wp:category_nicename>categ-2</wp:category_nicename><wp:category_parent></wp:category_parent><wp:cat_name><![CDATA[Category 2]]></wp:cat_name></wp:category>
<wp:category><wp:term_id>1</wp:term_id><wp:category_nicename>uncategorized</wp:category_nicename><wp:category_parent></wp:category_parent><wp:cat_name><![CDATA[Uncategorized]]></wp:cat_name></wp:category>
<wp:category><wp:term_id>15</wp:term_id><wp:category_nicename>categ-3</wp:category_nicename><wp:category_parent></wp:category_parent><wp:cat_name><![CDATA[Category 3]]></wp:cat_name></wp:category>
<wp:tag><wp:term_id>25</wp:term_id><wp:tag_slug>tag-1</wp:tag_slug><wp:tag_name><![CDATA[tag 1]]></wp:tag_name></wp:tag>
<wp:tag><wp:term_id>122</wp:term_id><wp:tag_slug>tag2</wp:tag_slug><wp:tag_name><![CDATA[Tag2]]></wp:tag_name></wp:tag>
<wp:tag><wp:term_id>68</wp:term_id><wp:tag_slug>tag-3</wp:tag_slug><wp:tag_name><![CDATA[Tag 3]]></wp:tag_name></wp:tag>
<generator>http://wordpress.org/?v=3.3.1</generator>
<item>
<title>Empty post</title>
<link>http://thisisa.test/?attachment_id=24</link>
<pubDate>Sat, 04 Feb 2012 03:17:33 +0000</pubDate>
<dc:creator>bob</dc:creator>
<guid isPermaLink="false">https://upload.wikimedia.org/wikipedia/commons/thumb/2/2c/Pelican_lakes_entrance02.jpg/240px-Pelican_lakes_entrance02.jpg</guid>
<description></description>
<content:encoded><![CDATA[]]></content:encoded>
<excerpt:encoded><![CDATA[]]></excerpt:encoded>
<wp:post_id>24</wp:post_id>
<wp:post_date>2012-02-04 03:17:33</wp:post_date>
<wp:post_date_gmt>2012-02-04 03:17:33</wp:post_date_gmt>
<wp:comment_status>open</wp:comment_status>
<wp:ping_status>open</wp:ping_status>
<wp:post_name>empty-post</wp:post_name>
<wp:status>inherit</wp:status>
<wp:post_parent>0</wp:post_parent>
<wp:menu_order>0</wp:menu_order>
<wp:post_type>attachment</wp:post_type>
<wp:post_password></wp:post_password>
<wp:is_sticky>0</wp:is_sticky>
<wp:attachment_url>https://upload.wikimedia.org/wikipedia/commons/thumb/2/2c/Pelican_lakes_entrance02.jpg/240px-Pelican_lakes_entrance02.jpg</wp:attachment_url>
<wp:postmeta>
<wp:meta_key>_wp_attachment_metadata</wp:meta_key>
<wp:meta_value><![CDATA[a:5:{s:5:"width";s:3:"150";s:6:"height";s:3:"186";s:14:"hwstring_small";s:22:"height='96' width='77'";s:4:"file";s:20:"2012/02/pelican.png";s:10:"image_meta";a:10:{s:8:"aperture";s:1:"0";s:6:"credit";s:0:"";s:6:"camera";s:0:"";s:7:"caption";s:0:"";s:17:"created_timestamp";s:1:"0";s:9:"copyright";s:0:"";s:12:"focal_length";s:1:"0";s:3:"iso";s:1:"0";s:13:"shutter_speed";s:1:"0";s:5:"title";s:0:"";}}]]></wp:meta_value>
</wp:postmeta>
<wp:postmeta>
<wp:meta_key>_wp_attached_file</wp:meta_key>
<wp:meta_value><![CDATA[2012/02/stuff.png]]></wp:meta_value>
</wp:postmeta>
<wp:postmeta>
<wp:meta_key>_wp_attachment_image_alt</wp:meta_key>
<wp:meta_value><![CDATA[Stuff]]></wp:meta_value>
</wp:postmeta>
</item>
<item>
<title></title>
<link>http://thisisa.test/?p=168</link>
<pubDate>Thu, 01 Jan 1970 00:00:00 +0000</pubDate>
<dc:creator>bob</dc:creator>
<guid isPermaLink="false">http://thisisa.test/?p=168</guid>
<description></description>
<content:encoded><![CDATA[This is a draft with no title]]></content:encoded>
<excerpt:encoded><![CDATA[]]></excerpt:encoded>
<wp:post_id>168</wp:post_id>
<wp:post_date>2012-02-15 21:23:57</wp:post_date>
<wp:post_date_gmt>0000-00-00 00:00:00</wp:post_date_gmt>
<wp:comment_status>open</wp:comment_status>
<wp:ping_status>open</wp:ping_status>
<wp:post_name></wp:post_name>
<wp:status>draft</wp:status>
<wp:post_parent>0</wp:post_parent>
<wp:menu_order>0</wp:menu_order>
<wp:post_type>post</wp:post_type>
<wp:post_password></wp:post_password>
<wp:is_sticky>0</wp:is_sticky>
<category domain="category" nicename="categ-1"><![CDATA[Category 1]]></category>
<wp:postmeta>
<wp:meta_key>_edit_last</wp:meta_key>
<wp:meta_value><![CDATA[3]]></wp:meta_value>
</wp:postmeta>
</item>
<item>
<title>A normal post</title>
<link>http://thisisa.test/?p=173</link>
<pubDate>Thu, 01 Jan 1970 00:00:00 +0000</pubDate>
<dc:creator>bob</dc:creator>
<guid isPermaLink="false">http://thisisa.test/?p=173</guid>
<description></description>
<content:encoded><![CDATA[Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod
tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam,
quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo
consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse
cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non
proident, sunt in culpa qui officia deserunt mollit anim id est laborum.
<ul>
<li>Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod
tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam,
quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo
consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse
cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non
proident, sunt in culpa qui officia deserunt mollit anim id est laborum.</li>
<li>Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod
tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam,
quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo
consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse
cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non
proident, sunt in culpa qui officia deserunt mollit anim id est laborum.</li>
</ul>
Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod
tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam,
quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo
consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse
cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non
proident, sunt in culpa qui officia deserunt mollit anim id est laborum.]]></content:encoded>
<excerpt:encoded><![CDATA[]]></excerpt:encoded>
<wp:post_id>173</wp:post_id>
<wp:post_date>2012-02-16 15:52:55</wp:post_date>
<wp:post_date_gmt>0000-00-00 00:00:00</wp:post_date_gmt>
<wp:comment_status>open</wp:comment_status>
<wp:ping_status>open</wp:ping_status>
<wp:post_name></wp:post_name>
<wp:status>draft</wp:status>
<wp:post_parent>0</wp:post_parent>
<wp:menu_order>0</wp:menu_order>
<wp:post_type>post</wp:post_type>
<wp:post_password></wp:post_password>
<wp:is_sticky>0</wp:is_sticky>
<category domain="category" nicename="category-2"><![CDATA[Category 2]]></category>
<wp:postmeta>
<wp:meta_key>_edit_last</wp:meta_key>
<wp:meta_value><![CDATA[3]]></wp:meta_value>
</wp:postmeta>
</item>
<item>
<title>Complete draft</title>
<link>http://thisisa.test/?p=176</link>
<pubDate>Thu, 01 Jan 1970 00:00:00 +0000</pubDate>
<dc:creator>bob</dc:creator>
<guid isPermaLink="false">http://thisisa.test/?p=176</guid>
<description></description>
<content:encoded><![CDATA[Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod
tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam,
quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo
consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse
cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non
proident, sunt in culpa qui officia deserunt mollit anim id est laborum.]]></content:encoded>
<excerpt:encoded><![CDATA[]]></excerpt:encoded>
<wp:post_id>176</wp:post_id>
<wp:post_date>2012-02-17 15:11:55</wp:post_date>
<wp:post_date_gmt>0000-00-00 00:00:00</wp:post_date_gmt>
<wp:comment_status>open</wp:comment_status>
<wp:ping_status>open</wp:ping_status>
<wp:post_name></wp:post_name>
<wp:status>draft</wp:status>
<wp:post_parent>0</wp:post_parent>
<wp:menu_order>0</wp:menu_order>
<wp:post_type>post</wp:post_type>
<wp:post_password></wp:post_password>
<wp:is_sticky>0</wp:is_sticky>
<category domain="category" nicename="category-3"><![CDATA[Category 3]]></category>
<wp:postmeta>
<wp:meta_key>_edit_last</wp:meta_key>
<wp:meta_value><![CDATA[3]]></wp:meta_value>
</wp:postmeta>
</item>
<item>
<title>Page</title>
<link>http://thisisa.test/contact/</link>
<pubDate>Wed, 11 Apr 2012 11:38:08 +0000</pubDate>
<dc:creator>bob</dc:creator>
<guid isPermaLink="false">http://thisisa.test/?page_id=334</guid>
<description></description>
<content:encoded><![CDATA[Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod
tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam,
quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo
consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse
cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non
proident, sunt in culpa qui officia deserunt mollit anim id est laborum.]]></content:encoded>
<excerpt:encoded><![CDATA[]]></excerpt:encoded>
<wp:post_id>334</wp:post_id>
<wp:post_date>2012-04-11 06:38:08</wp:post_date>
<wp:post_date_gmt>2012-04-11 11:38:08</wp:post_date_gmt>
<wp:comment_status>open</wp:comment_status>
<wp:ping_status>open</wp:ping_status>
<wp:post_name>contact</wp:post_name>
<wp:status>publish</wp:status>
<wp:post_parent>0</wp:post_parent>
<wp:menu_order>0</wp:menu_order>
<wp:post_type>page</wp:post_type>
<wp:post_password></wp:post_password>
<wp:is_sticky>0</wp:is_sticky>
<wp:postmeta>
<wp:meta_key>sharing_disabled</wp:meta_key>
<wp:meta_value><![CDATA[1]]></wp:meta_value>
</wp:postmeta>
<wp:postmeta>
<wp:meta_key>_wp_page_template</wp:meta_key>
<wp:meta_value><![CDATA[default]]></wp:meta_value>
</wp:postmeta>
<wp:postmeta>
<wp:meta_key>_edit_last</wp:meta_key>
<wp:meta_value><![CDATA[3]]></wp:meta_value>
</wp:postmeta>
</item>
<item>
<title>Empty Page</title>
<link>http://thisisa.test/empty/</link>
<pubDate>Wed, 11 Apr 2012 11:38:08 +0000</pubDate>
<dc:creator>bob</dc:creator>
<guid isPermaLink="false">http://thisisa.test/?page_id=334</guid>
<description></description>
<content:encoded><![CDATA[]]></content:encoded>
<excerpt:encoded><![CDATA[]]></excerpt:encoded>
<wp:post_id>334</wp:post_id>
<wp:post_date>2012-04-11 06:38:08</wp:post_date>
<wp:post_date_gmt>2012-04-11 11:38:08</wp:post_date_gmt>
<wp:comment_status>open</wp:comment_status>
<wp:ping_status>open</wp:ping_status>
<wp:post_name>empty</wp:post_name>
<wp:status>publish</wp:status>
<wp:post_parent>0</wp:post_parent>
<wp:menu_order>0</wp:menu_order>
<wp:post_type>page</wp:post_type>
<wp:post_password></wp:post_password>
<wp:is_sticky>0</wp:is_sticky>
<wp:postmeta>
<wp:meta_key>sharing_disabled</wp:meta_key>
<wp:meta_value><![CDATA[1]]></wp:meta_value>
</wp:postmeta>
<wp:postmeta>
<wp:meta_key>_wp_page_template</wp:meta_key>
<wp:meta_value><![CDATA[default]]></wp:meta_value>
</wp:postmeta>
<wp:postmeta>
<wp:meta_key>_edit_last</wp:meta_key>
<wp:meta_value><![CDATA[3]]></wp:meta_value>
</wp:postmeta>
</item>
<item>
<title>Special chars: l&#039;é</title>
<link>http://thisisa.test/?p=471</link>
<pubDate>Thu, 01 Jan 1970 00:00:00 +0000</pubDate>
<dc:creator>bob</dc:creator>
<guid isPermaLink="false">http://thisisa.test/?p=471</guid>
<description></description>
<content:encoded><![CDATA[l&#039;é]]></content:encoded>
<excerpt:encoded><![CDATA[]]></excerpt:encoded>
<wp:post_id>471</wp:post_id>
<wp:post_date>2012-04-29 09:44:27</wp:post_date>
<wp:post_date_gmt>0000-00-00 00:00:00</wp:post_date_gmt>
<wp:comment_status>open</wp:comment_status>
<wp:ping_status>open</wp:ping_status>
<wp:post_name></wp:post_name>
<wp:status>draft</wp:status>
<wp:post_parent>0</wp:post_parent>
<wp:menu_order>0</wp:menu_order>
<wp:post_type>post</wp:post_type>
<wp:post_password></wp:post_password>
<wp:is_sticky>0</wp:is_sticky>
<category domain="category" nicename="category-1"><![CDATA[Category 1]]></category>
<wp:postmeta>
<wp:meta_key>_edit_last</wp:meta_key>
<wp:meta_value><![CDATA[3]]></wp:meta_value>
</wp:postmeta>
</item>
<item>
<title>With excerpt</title>
<link>http://thisisa.test/with-excerpt/</link>
<pubDate>Sat, 04 Feb 2012 02:03:06 +0000</pubDate>
<dc:creator>bob</dc:creator>
<guid isPermaLink="false">http://thisisa.test/?p=8</guid>
<description></description>
<content:encoded><![CDATA[Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod
tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam,
quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo
consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse
cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non
proident, sunt in culpa qui officia deserunt mollit anim id est laborum.
Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod
tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam,
quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo
consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse
cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non
proident, sunt in culpa qui officia deserunt mollit anim id est laborum.
Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod
tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam,
quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo
consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse
cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non
proident, sunt in culpa qui officia deserunt mollit anim id est laborum.]]></content:encoded>
<excerpt:encoded><![CDATA[Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod
tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam,
quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo
consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse
cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non
proident, sunt in culpa qui officia deserunt mollit anim id est laborum.]]></excerpt:encoded>
<wp:post_id>8</wp:post_id>
<wp:post_date>2012-02-04 02:03:06</wp:post_date>
<wp:post_date_gmt>2012-02-04 02:03:06</wp:post_date_gmt>
<wp:comment_status>open</wp:comment_status>
<wp:ping_status>open</wp:ping_status>
<wp:post_name>with-excerpt</wp:post_name>
<wp:status>publish</wp:status>
<wp:post_parent>0</wp:post_parent>
<wp:menu_order>0</wp:menu_order>
<wp:post_type>post</wp:post_type>
<wp:post_password></wp:post_password>
<wp:is_sticky>0</wp:is_sticky>
<category domain="category" nicename="Category 1"><![CDATA[Category 1]]></category>
<category domain="post_tag" nicename="tag-1"><![CDATA[tag 1]]></category>
<category domain="post_tag" nicename="tag2"><![CDATA[Tag2]]></category>
<wp:postmeta>
<wp:meta_key>_edit_last</wp:meta_key>
<wp:meta_value><![CDATA[3]]></wp:meta_value>
</wp:postmeta>
<wp:postmeta>
<wp:meta_key>et_bigpost</wp:meta_key>
<wp:meta_value><![CDATA[0]]></wp:meta_value>
</wp:postmeta>
<wp:postmeta>
<wp:meta_key>_thumbnail_id</wp:meta_key>
<wp:meta_value><![CDATA[32]]></wp:meta_value>
</wp:postmeta>
</item>
<item>
<title>With tags</title>
<link>http://thisisa.test/tags/</link>
<pubDate>Sat, 04 Feb 2012 21:05:25 +0000</pubDate>
<dc:creator>bob</dc:creator>
<guid isPermaLink="false">http://thisisa.test/?p=25</guid>
<description></description>
<content:encoded><![CDATA[Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod
tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam,
quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo
consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse
cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non
proident, sunt in culpa qui officia deserunt mollit anim id est laborum.]]></content:encoded>
<excerpt:encoded><![CDATA[]]></excerpt:encoded>
<wp:post_id>25</wp:post_id>
<wp:post_date>2012-02-04 21:05:25</wp:post_date>
<wp:post_date_gmt>2012-02-04 21:05:25</wp:post_date_gmt>
<wp:comment_status>open</wp:comment_status>
<wp:ping_status>open</wp:ping_status>
<wp:post_name>with-tags</wp:post_name>
<wp:status>publish</wp:status>
<wp:post_parent>0</wp:post_parent>
<wp:menu_order>0</wp:menu_order>
<wp:post_type>post</wp:post_type>
<wp:post_password></wp:post_password>
<wp:is_sticky>0</wp:is_sticky>
<category domain="category" nicename="category-3"><![CDATA[Category 3]]></category>
<category domain="post_tag" nicename="tag-1"><![CDATA[tag 1]]></category>
<category domain="post_tag" nicename="tag-2"><![CDATA[Tag2]]></category>
<category domain="post_tag" nicename="tag-3"><![CDATA[Tag 3]]></category>
<wp:postmeta>
<wp:meta_key>_edit_last</wp:meta_key>
<wp:meta_value><![CDATA[3]]></wp:meta_value>
</wp:postmeta>
<wp:postmeta>
<wp:meta_key>et_bigpost</wp:meta_key>
<wp:meta_value><![CDATA[0]]></wp:meta_value>
</wp:postmeta>
<wp:postmeta>
<wp:meta_key>_thumbnail_id</wp:meta_key>
<wp:meta_value><![CDATA[29]]></wp:meta_value>
</wp:postmeta>
</item>
<item>
<title>With comments</title>
<link>http://thisisa.test/with-comments/</link>
<pubDate>Wed, 18 Apr 2012 08:36:26 +0000</pubDate>
<dc:creator>john</dc:creator>
<guid isPermaLink="false">http://thisisa.test/?p=422</guid>
<description></description>
<content:encoded><![CDATA[Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod
tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam,
quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo
consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse
cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non
proident, sunt in culpa qui officia deserunt mollit anim id est laborum.]]></content:encoded>
<excerpt:encoded><![CDATA[]]></excerpt:encoded>
<wp:post_id>422</wp:post_id>
<wp:post_date>2012-04-18 03:36:26</wp:post_date>
<wp:post_date_gmt>2012-04-18 08:36:26</wp:post_date_gmt>
<wp:comment_status>open</wp:comment_status>
<wp:ping_status>open</wp:ping_status>
<wp:post_name>with-comments</wp:post_name>
<wp:status>publish</wp:status>
<wp:post_parent>0</wp:post_parent>
<wp:menu_order>0</wp:menu_order>
<wp:post_type>post</wp:post_type>
<wp:post_password></wp:post_password>
<wp:is_sticky>0</wp:is_sticky>
<category domain="category" nicename="category-1"><![CDATA[Category 1]]></category>
<wp:postmeta>
<wp:meta_key>_edit_last</wp:meta_key>
<wp:meta_value><![CDATA[2]]></wp:meta_value>
</wp:postmeta>
<wp:postmeta>
<wp:meta_key>_thumbnail_id</wp:meta_key>
<wp:meta_value><![CDATA[423]]></wp:meta_value>
</wp:postmeta>
<wp:comment>
<wp:comment_id>116</wp:comment_id>
<wp:comment_author><![CDATA[User2]]></wp:comment_author>
<wp:comment_author_email>User2@mail.test</wp:comment_author_email>
<wp:comment_author_url></wp:comment_author_url>
<wp:comment_author_IP>127.0.0.1</wp:comment_author_IP>
<wp:comment_date>2012-05-06 15:46:06</wp:comment_date>
<wp:comment_date_gmt>2012-05-06 20:46:06</wp:comment_date_gmt>
<wp:comment_content><![CDATA[Comment content.]]></wp:comment_content>
<wp:comment_approved>1</wp:comment_approved>
<wp:comment_type></wp:comment_type>
<wp:comment_parent>0</wp:comment_parent>
<wp:comment_user_id>0</wp:comment_user_id>
<wp:commentmeta>
<wp:meta_key>akismet_result</wp:meta_key>
<wp:meta_value><![CDATA[false]]></wp:meta_value>
</wp:commentmeta>
<wp:commentmeta>
<wp:meta_key>akismet_history</wp:meta_key>
<wp:meta_value><![CDATA[a:4:{s:4:"time";s:15:"1336337189.7974";s:7:"message";s:28:"Akismet cleared this comment";s:5:"event";s:9:"check-ham";s:4:"user";s:0:"";}]]></wp:meta_value>
</wp:commentmeta>
<wp:commentmeta>
<wp:meta_key>akismet_as_submitted</wp:meta_key>
<wp:meta_value><![CDATA[a:64:{s:15:"comment_post_ID";s:3:"422";s:14:"comment_author";s:8:"Baronsed";s:20:"comment_author_email";s:15:"User2@mail.test";s:18:"comment_author_url";s:0:"";s:15:"comment_content";s:118:"Dans les listes d'articles où celui-ci apparaît, l'image est trop grande et ralentit le chargement de toute la page.";s:12:"comment_type";s:0:"";s:14:"comment_parent";s:1:"0";s:7:"user_ID";s:1:"0";s:7:"user_ip";s:14:"127.0.0.1";s:10:"user_agent";s:74:"Mozilla/5.0 (X11; Ubuntu; Linux i686; rv:12.0) Gecko/20100101 Firefox/12.0";s:8:"referrer";s:0:"";s:4:"blog";s:19:"http://thisisa.test";s:9:"blog_lang";s:5:"en_US";s:12:"blog_charset";s:5:"UTF-8";s:9:"permalink";s:62:"http://thisisa.test/htop-un-visualiseur-interactif-de-process/";s:9:"user_role";s:0:"";s:21:"akismet_comment_nonce";s:6:"passed";s:11:"POST_author";s:8:"Baronsed";s:10:"POST_email";s:15:"User2@mail.test";s:8:"POST_url";s:0:"";s:12:"POST_comment";s:118:"Dans les listes d'articles où celui-ci apparaît, l'image est trop grande et ralentit le chargement de toute la page.";s:11:"POST_submit";s:14:"Submit Comment";s:20:"POST_comment_post_ID";s:3:"422";s:19:"POST_comment_parent";s:1:"0";s:26:"POST_akismet_comment_nonce";s:10:"96b66769dc";s:15:"SERVER_SOFTWARE";s:12:"nginx/0.8.55";s:11:"REQUEST_URI";s:21:"/wp-comments-post.php";s:4:"TERM";s:5:"xterm";s:17:"PHP_FCGI_CHILDREN";s:1:"4";s:4:"PATH";s:29:"/sbin:/usr/sbin:/bin:/usr/bin";s:1:"_";s:25:"/usr/local/bin/spawn-fcgi";s:3:"PWD";s:1:"/";s:4:"LANG";s:11:"en_US.UTF-8";s:5:"SHLVL";s:1:"2";s:21:"PHP_FCGI_MAX_REQUESTS";s:4:"1000";s:9:"FCGI_ROLE";s:9:"RESPONDER";s:12:"QUERY_STRING";s:0:"";s:14:"REQUEST_METHOD";s:4:"POST";s:12:"CONTENT_TYPE";s:33:"application/x-www-form-urlencoded";s:14:"CONTENT_LENGTH";s:3:"277";s:11:"SCRIPT_NAME";s:21:"/wp-comments-post.php";s:12:"DOCUMENT_URI";s:21:"/wp-comments-post.php";s:13:"DOCUMENT_ROOT";s:14:"/home/blog";s:15:"SERVER_PROTOCOL";s:8:"HTTP/1.1";s:17:"GATEWAY_INTERFACE";s:7:"CGI/1.1";s:11:"REMOTE_ADDR";s:14:"127.0.0.1";s:11:"REMOTE_PORT";s:5:"52826";s:11:"SERVER_ADDR";s:13:"127.0.0.1";s:11:"SERVER_PORT";s:2:"80";s:11:"SERVER_NAME";s:12:"thisisa.test";s:15:"REDIRECT_STATUS";s:3:"200";s:15:"SCRIPT_FILENAME";s:35:"/home/blog/wp-comments-post.php";s:9:"HTTP_HOST";s:12:"thisisa.test";s:15:"HTTP_USER_AGENT";s:74:"Mozilla/5.0 (X11; Ubuntu; Linux i686; rv:12.0) Gecko/20100101 Firefox/12.0";s:11:"HTTP_ACCEPT";s:63:"text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8";s:20:"HTTP_ACCEPT_LANGUAGE";s:35:"fr,fr-fr;q=0.8,en-us;q=0.5,en;q=0.3";s:20:"HTTP_ACCEPT_ENCODING";s:13:"gzip, deflate";s:8:"HTTP_DNT";s:1:"1";s:15:"HTTP_CONNECTION";s:10:"keep-alive";s:11:"HTTP_COOKIE";s:0:"";s:17:"HTTP_CONTENT_TYPE";s:33:"application/x-www-form-urlencoded";s:19:"HTTP_CONTENT_LENGTH";s:3:"277";s:8:"PHP_SELF";s:21:"/wp-comments-post.php";s:12:"REQUEST_TIME";s:10:"1336337164";}]]></wp:meta_value>
</wp:commentmeta>
</wp:comment>
<wp:comment>
<wp:comment_id>117</wp:comment_id>
<wp:comment_author><![CDATA[Bob]]></wp:comment_author>
<wp:comment_author_email>bob@thisisa.test</wp:comment_author_email>
<wp:comment_author_url></wp:comment_author_url>
<wp:comment_author_IP>127.0.0.1</wp:comment_author_IP>
<wp:comment_date>2012-05-06 17:44:06</wp:comment_date>
<wp:comment_date_gmt>2012-05-06 22:44:06</wp:comment_date_gmt>
<wp:comment_content><![CDATA[Comment content.]]></wp:comment_content>
<wp:comment_approved>1</wp:comment_approved>
<wp:comment_type></wp:comment_type>
<wp:comment_parent>116</wp:comment_parent>
<wp:comment_user_id>3</wp:comment_user_id>
<wp:commentmeta>
<wp:meta_key>akismet_result</wp:meta_key>
<wp:meta_value><![CDATA[false]]></wp:meta_value>
</wp:commentmeta>
<wp:commentmeta>
<wp:meta_key>akismet_history</wp:meta_key>
<wp:meta_value><![CDATA[a:4:{s:4:"time";s:15:"1336344263.8658";s:7:"message";s:28:"Akismet cleared this comment";s:5:"event";s:9:"check-ham";s:4:"user";s:3:"bob";}]]></wp:meta_value>
</wp:commentmeta>
<wp:commentmeta>
<wp:meta_key>akismet_as_submitted</wp:meta_key>
<wp:meta_value><![CDATA[a:74:{s:15:"comment_post_ID";s:3:"422";s:14:"comment_author";s:3:"bob";s:20:"comment_author_email";s:25:"bob@thisisa.test";s:18:"comment_author_url";s:0:"";s:15:"comment_content";s:26:"Merci de l'avoir signalé.";s:14:"comment_parent";s:3:"116";s:7:"user_ID";s:1:"3";s:7:"user_ip";s:14:"127.0.0.1";s:10:"user_agent";s:139:"Mozilla/5.0 (X11; Linux i686) AppleWebKit/535.19 (KHTML, like Gecko) Ubuntu/12.04 Chromium/127.0.0.1 Chrome/127.0.0.1 Safari/535.19";s:8:"referrer";s:29:"http://thisisa.test/wp-admin/";s:4:"blog";s:19:"http://thisisa.test";s:9:"blog_lang";s:5:"en_US";s:12:"blog_charset";s:5:"UTF-8";s:9:"permalink";s:62:"http://thisisa.test/htop-un-visualiseur-interactif-de-process/";s:9:"user_role";s:13:"administrator";s:21:"akismet_comment_nonce";s:6:"passed";s:22:"POST_newcomment_author";s:0:"";s:28:"POST_newcomment_author_email";s:0:"";s:26:"POST_newcomment_author_url";s:0:"";s:12:"POST_user_ID";s:1:"3";s:11:"POST_action";s:15:"replyto-comment";s:15:"POST_comment_ID";s:3:"116";s:20:"POST_comment_post_ID";s:3:"422";s:11:"POST_status";s:0:"";s:13:"POST_position";s:2:"-1";s:13:"POST_checkbox";s:1:"0";s:9:"POST_mode";s:9:"dashboard";s:32:"POST__ajax_nonce-replyto-comment";s:10:"d1ad3bd917";s:32:"POST__wp_unfiltered_html_comment";s:10:"fc11aee860";s:12:"POST_content";s:26:"Merci de l'avoir signalé.";s:7:"POST_id";s:3:"422";s:21:"POST_comments_listing";s:0:"";s:15:"SERVER_SOFTWARE";s:12:"nginx/0.8.55";s:11:"REQUEST_URI";s:24:"/wp-admin/admin-ajax.php";s:4:"TERM";s:5:"xterm";s:17:"PHP_FCGI_CHILDREN";s:1:"4";s:4:"PATH";s:29:"/sbin:/usr/sbin:/bin:/usr/bin";s:1:"_";s:25:"/usr/local/bin/spawn-fcgi";s:3:"PWD";s:1:"/";s:4:"LANG";s:11:"en_US.UTF-8";s:5:"SHLVL";s:1:"2";s:21:"PHP_FCGI_MAX_REQUESTS";s:4:"1000";s:9:"FCGI_ROLE";s:9:"RESPONDER";s:12:"QUERY_STRING";s:0:"";s:14:"REQUEST_METHOD";s:4:"POST";s:12:"CONTENT_TYPE";s:33:"application/x-www-form-urlencoded";s:14:"CONTENT_LENGTH";s:3:"322";s:11:"SCRIPT_NAME";s:24:"/wp-admin/admin-ajax.php";s:12:"DOCUMENT_URI";s:24:"/wp-admin/admin-ajax.php";s:13:"DOCUMENT_ROOT";s:14:"/home/blog";s:15:"SERVER_PROTOCOL";s:8:"HTTP/1.1";s:17:"GATEWAY_INTERFACE";s:7:"CGI/1.1";s:11:"REMOTE_ADDR";s:14:"127.0.0.1";s:11:"REMOTE_PORT";s:5:"10252";s:11:"SERVER_ADDR";s:13:"127.0.0.1";s:11:"SERVER_PORT";s:2:"80";s:11:"SERVER_NAME";s:12:"thisisa.test";s:15:"REDIRECT_STATUS";s:3:"200";s:15:"SCRIPT_FILENAME";s:38:"/home/blog/wp-admin/admin-ajax.php";s:9:"HTTP_HOST";s:12:"thisisa.test";s:15:"HTTP_CONNECTION";s:10:"keep-alive";s:19:"HTTP_CONTENT_LENGTH";s:3:"322";s:11:"HTTP_ORIGIN";s:19:"http://thisisa.test";s:21:"HTTP_X_REQUESTED_WITH";s:14:"XMLHttpRequest";s:15:"HTTP_USER_AGENT";s:139:"Mozilla/5.0 (X11; Linux i686) AppleWebKit/535.19 (KHTML, like Gecko) Ubuntu/12.04 Chromium/127.0.0.1 Chrome/127.0.0.1 Safari/535.19";s:17:"HTTP_CONTENT_TYPE";s:33:"application/x-www-form-urlencoded";s:11:"HTTP_ACCEPT";s:3:"*/*";s:12:"HTTP_REFERER";s:29:"http://thisisa.test/wp-admin/";s:20:"HTTP_ACCEPT_ENCODING";s:17:"gzip,deflate,sdch";s:20:"HTTP_ACCEPT_LANGUAGE";s:35:"fr-FR,fr;q=0.8,en-US;q=0.6,en;q=0.4";s:19:"HTTP_ACCEPT_CHARSET";s:30:"ISO-8859-1,utf-8;q=0.7,*;q=0.3";s:11:"HTTP_COOKIE";s:0:"";s:8:"PHP_SELF";s:24:"/wp-admin/admin-ajax.php";s:12:"REQUEST_TIME";s:10:"1336344246";}]]></wp:meta_value>
</wp:commentmeta>
</wp:comment>
<wp:comment>
<wp:comment_id>156</wp:comment_id>
<wp:comment_author><![CDATA[Ping back comment author]]></wp:comment_author>
<wp:comment_author_email></wp:comment_author_email>
<wp:comment_author_url>http://thisisa.test/to-article-you-ping-back/</wp:comment_author_url>
<wp:comment_author_IP>127.0.0.1</wp:comment_author_IP>
<wp:comment_date>2012-05-09 19:30:19</wp:comment_date>
<wp:comment_date_gmt>2012-05-10 00:30:19</wp:comment_date_gmt>
<wp:comment_content><![CDATA[[...]this is a ping pack [...] ]]></wp:comment_content>
<wp:comment_approved>trash</wp:comment_approved>
<wp:comment_type>pingback</wp:comment_type>
<wp:comment_parent>0</wp:comment_parent>
<wp:comment_user_id>0</wp:comment_user_id>
<wp:commentmeta>
<wp:meta_key>akismet_history</wp:meta_key>
<wp:meta_value><![CDATA[a:4:{s:4:"time";s:15:"1336610793.7343";s:7:"message";s:39:"bob changed the comment status to trash";s:5:"event";s:12:"status-trash";s:4:"user";s:3:"bob";}]]></wp:meta_value>
</wp:commentmeta>
<wp:commentmeta>
<wp:meta_key>_wp_trash_meta_status</wp:meta_key>
<wp:meta_value><![CDATA[0]]></wp:meta_value>
</wp:commentmeta>
<wp:commentmeta>
<wp:meta_key>_wp_trash_meta_time</wp:meta_key>
<wp:meta_value><![CDATA[1336610793]]></wp:meta_value>
</wp:commentmeta>
</wp:comment>
<wp:comment>
<wp:comment_id>122</wp:comment_id>
<wp:comment_author><![CDATA[bob]]></wp:comment_author>
<wp:comment_author_email>bob@thisisa.test</wp:comment_author_email>
<wp:comment_author_url></wp:comment_author_url>
<wp:comment_author_IP>127.0.0.1</wp:comment_author_IP>
<wp:comment_date>2012-05-07 14:11:34</wp:comment_date>
<wp:comment_date_gmt>2012-05-07 19:11:34</wp:comment_date_gmt>
<wp:comment_content><![CDATA[Comment content.]]></wp:comment_content>
<wp:comment_approved>1</wp:comment_approved>
<wp:comment_type></wp:comment_type>
<wp:comment_parent>121</wp:comment_parent>
<wp:comment_user_id>3</wp:comment_user_id>
<wp:commentmeta>
<wp:meta_key>akismet_result</wp:meta_key>
<wp:meta_value><![CDATA[false]]></wp:meta_value>
</wp:commentmeta>
<wp:commentmeta>
<wp:meta_key>akismet_history</wp:meta_key>
<wp:meta_value><![CDATA[a:4:{s:4:"time";s:15:"1336417895.1821";s:7:"message";s:28:"Akismet cleared this comment";s:5:"event";s:9:"check-ham";s:4:"user";s:3:"bob";}]]></wp:meta_value>
</wp:commentmeta>
<wp:commentmeta>
<wp:meta_key>akismet_as_submitted</wp:meta_key>
<wp:meta_value><![CDATA[a:65:{s:15:"comment_post_ID";s:3:"422";s:14:"comment_author";s:3:"bob";s:20:"comment_author_email";s:25:"bob@thisisa.test";s:18:"comment_author_url";s:0:"";s:15:"comment_content";s:832:"Comment content";s:12:"comment_type";s:0:"";s:14:"comment_parent";s:3:"121";s:7:"user_ID";s:1:"3";s:7:"user_ip";s:14:"127.0.0.1";s:10:"user_agent";s:139:"Mozilla/5.0 (X11; Linux i686) AppleWebKit/535.19 (KHTML, like Gecko) Ubuntu/12.04 Chromium/127.0.0.1 Chrome/127.0.0.1 Safari/535.19";s:8:"referrer";s:62:"http://thisisa.test/htop-un-visualiseur-interactif-de-process/";s:4:"blog";s:19:"http://thisisa.test";s:9:"blog_lang";s:5:"en_US";s:12:"blog_charset";s:5:"UTF-8";s:9:"permalink";s:62:"http://thisisa.test/htop-un-visualiseur-interactif-de-process/";s:9:"user_role";s:13:"administrator";s:21:"akismet_comment_nonce";s:6:"passed";s:12:"POST_comment";s:832:"Comment content.";s:11:"POST_submit";s:14:"Submit Comment";s:20:"POST_comment_post_ID";s:3:"422";s:19:"POST_comment_parent";s:3:"121";s:32:"POST__wp_unfiltered_html_comment";s:10:"9dacc22ee8";s:26:"POST_akismet_comment_nonce";s:10:"b9cbdae553";s:15:"SERVER_SOFTWARE";s:12:"nginx/0.8.55";s:11:"REQUEST_URI";s:21:"/wp-comments-post.php";s:4:"TERM";s:5:"xterm";s:17:"PHP_FCGI_CHILDREN";s:1:"4";s:4:"PATH";s:29:"/sbin:/usr/sbin:/bin:/usr/bin";s:1:"_";s:25:"/usr/local/bin/spawn-fcgi";s:3:"PWD";s:1:"/";s:4:"LANG";s:11:"en_US.UTF-8";s:5:"SHLVL";s:1:"2";s:21:"PHP_FCGI_MAX_REQUESTS";s:4:"1000";s:9:"FCGI_ROLE";s:9:"RESPONDER";s:12:"QUERY_STRING";s:0:"";s:14:"REQUEST_METHOD";s:4:"POST";s:12:"CONTENT_TYPE";s:33:"application/x-www-form-urlencoded";s:14:"CONTENT_LENGTH";s:4:"1143";s:11:"SCRIPT_NAME";s:21:"/wp-comments-post.php";s:12:"DOCUMENT_URI";s:21:"/wp-comments-post.php";s:13:"DOCUMENT_ROOT";s:14:"/home/blog";s:15:"SERVER_PROTOCOL";s:8:"HTTP/1.1";s:17:"GATEWAY_INTERFACE";s:7:"CGI/1.1";s:11:"REMOTE_ADDR";s:14:"127.0.0.1";s:11:"REMOTE_PORT";s:5:"10834";s:11:"SERVER_ADDR";s:13:"127.0.0.1";s:11:"SERVER_PORT";s:2:"80";s:11:"SERVER_NAME";s:12:"thisisa.test";s:15:"REDIRECT_STATUS";s:3:"200";s:15:"SCRIPT_FILENAME";s:35:"/home/blog/wp-comments-post.php";s:9:"HTTP_HOST";s:12:"thisisa.test";s:15:"HTTP_CONNECTION";s:10:"keep-alive";s:19:"HTTP_CONTENT_LENGTH";s:4:"1143";s:18:"HTTP_CACHE_CONTROL";s:9:"john-age=0";s:11:"HTTP_ORIGIN";s:19:"http://thisisa.test";s:15:"HTTP_USER_AGENT";s:139:"Mozilla/5.0 (X11; Linux i686) AppleWebKit/535.19 (KHTML, like Gecko) Ubuntu/12.04 Chromium/127.0.0.1 Chrome/127.0.0.1 Safari/535.19";s:17:"HTTP_CONTENT_TYPE";s:33:"application/x-www-form-urlencoded";s:11:"HTTP_ACCEPT";s:63:"text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8";s:12:"HTTP_REFERER";s:62:"http://thisisa.test/htop-un-visualiseur-interactif-de-process/";s:20:"HTTP_ACCEPT_ENCODING";s:17:"gzip,deflate,sdch";s:20:"HTTP_ACCEPT_LANGUAGE";s:35:"fr-FR,fr;q=0.8,en-US;q=0.6,en;q=0.4";s:19:"HTTP_ACCEPT_CHARSET";s:30:"ISO-8859-1,utf-8;q=0.7,*;q=0.3";s:11:"HTTP_COOKIE";s:0:"";s:8:"PHP_SELF";s:21:"/wp-comments-post.php";s:12:"REQUEST_TIME";s:10:"1336417893";}]]></wp:meta_value>
</wp:commentmeta>
</wp:comment>
</item>
<item>
<title>Post with raw data</title>
<link>http://thisisa.test/?p=173</link>
<pubDate>Thu, 01 Jan 1970 00:00:00 +0000</pubDate>
<dc:creator>bob</dc:creator>
<guid isPermaLink="false">http://thisisa.test/?p=173</guid>
<description></description>
<content:encoded><![CDATA[<h1>Pelicans are scary</h1>
Pelicans are supposed to eat fish, damn it!
<iframe width="420" height="315" src="http://www.youtube.com/embed/QNNl_uWmQXE" frameborder="0" allowfullscreen></iframe>
Bottom line: don't mess up with birds]]></content:encoded>
<excerpt:encoded><![CDATA[]]></excerpt:encoded>
<wp:post_id>173</wp:post_id>
<wp:post_date>2012-02-16 15:52:55</wp:post_date>
<wp:post_date_gmt>0000-00-00 00:00:00</wp:post_date_gmt>
<wp:comment_status>open</wp:comment_status>
<wp:ping_status>open</wp:ping_status>
<wp:post_name>post-with-raw-data</wp:post_name>
<wp:status>publish</wp:status>
<wp:post_parent>0</wp:post_parent>
<wp:menu_order>0</wp:menu_order>
<wp:post_type>post</wp:post_type>
<wp:post_password></wp:post_password>
<wp:is_sticky>0</wp:is_sticky>
<category domain="category" nicename="category-2"><![CDATA[Category 2]]></category>
<wp:postmeta>
<wp:meta_key>_edit_last</wp:meta_key>
<wp:meta_value><![CDATA[3]]></wp:meta_value>
</wp:postmeta>
</item>
</channel>
</rss>

88
tests/support.py
View file

@ -6,6 +6,11 @@ __all__ = [
import os
import subprocess
import re
import sys
import cStringIO
from functools import wraps
from contextlib import contextmanager
from tempfile import mkdtemp
from shutil import rmtree
@ -28,8 +33,87 @@ def temporary_folder():
# do whatever you want
"""
tempdir = mkdtemp()
yield tempdir
rmtree(tempdir)
try:
yield tempdir
finally:
rmtree(tempdir)
def isplit(s, sep=None):
"""
Behave like str.split but returns a generator instead of a list.
>>> list(isplit('\tUse the force\n')) == '\tUse the force\n'.split()
True
>>> list(isplit('\tUse the force\n')) == ['Use', 'the', 'force']
True
>>> list(isplit('\tUse the force\n', "e")) == '\tUse the force\n'.split("e")
True
>>> list(isplit('Use the force', "e")) == 'Use the force'.split("e")
True
>>> list(isplit('Use the force', "e")) == ['Us', ' th', ' forc', '']
True
"""
sep, hardsep = r'\s+' if sep is None else re.escape(sep), sep is not None
exp, pos, l = re.compile(sep), 0, len(s)
while True:
m = exp.search(s, pos)
if not m:
if pos < l or hardsep:
# ^ mimic "split()": ''.split() returns []
yield s[pos:]
break
start = m.start()
if pos < start or hardsep:
# ^ mimic "split()": includes trailing empty string
yield s[pos:start]
pos = m.end()
def mute(returns_output=False):
"""
Decorate a function that prints to stdout, intercepting the output.
If "returns_output" is True, the function will return a generator
yielding the printed lines instead of the return values.
The decorator litterally hijack sys.stdout during each function
execution, so be careful with what you apply it to.
>>> def numbers():
print "42"
print "1984"
...
>>> numbers()
42
1984
>>> mute()(numbers)()
>>> list(mute(True)(numbers)())
['42', '1984']
"""
def decorator(func):
@wraps(func)
def wrapper(*args, **kwargs):
saved_stdout = sys.stdout
sys.stdout = cStringIO.StringIO()
try:
out = func(*args, **kwargs)
if returns_output:
out = isplit(sys.stdout.getvalue().strip())
finally:
sys.stdout = saved_stdout
return out
return wrapper
return decorator
def get_article(title, slug, content, lang, extra_metadata=None):

43
tests/test_importer.py Normal file
View file

@ -0,0 +1,43 @@
# -*- coding: utf-8 -*-
import os
from pelican.tools.pelican_import import wp2fields, fields2pelican
from .support import unittest, temporary_folder, mute
CUR_DIR = os.path.dirname(__file__)
WORDPRESS_XML_SAMPLE = os.path.join(CUR_DIR, 'content', 'wordpressexport.xml')
class TestWordpressXmlImporter(unittest.TestCase):
def setUp(self):
self.posts = wp2fields(WORDPRESS_XML_SAMPLE)
def test_ignore_empty_posts(self):
posts = list(self.posts)
self.assertTrue(posts)
for title, content, fname, date, author, categ, tags, format in posts:
self.assertTrue(title.strip())
def test_can_toggle_raw_html_code_parsing(self):
posts = list(self.posts)
r = lambda f: open(f).read()
silent_f2p = mute(True)(fields2pelican)
with temporary_folder() as temp:
rst_files = (r(f) for f in silent_f2p(posts, 'markdown', temp))
self.assertTrue(any('<iframe' in rst for rst in rst_files))
rst_files = (r(f) for f in silent_f2p(posts, 'markdown', temp, strip_raw=True))
self.assertFalse(any('<iframe' in rst for rst in rst_files))
# no effect in rst
rst_files = (r(f) for f in silent_f2p(posts, 'rst', temp))
self.assertFalse(any('<iframe' in rst for rst in rst_files))
rst_files = (r(f) for f in silent_f2p(posts, 'rst', temp, strip_raw=True))
self.assertFalse(any('<iframe' in rst for rst in rst_files))