pipeline.cfg

[transmogrifier]
include = funnelweb.remote

[crawler]
url=file:build/html
ignore=
        cgi-bin
        javascript:
        _static
        _sources
        genindex\.html
        search\.html
        saesrchindex\.js

[template1]
title = text //div[@class='body']//h1[1]
description = optional //div[contains(@class,'admonition-description')]/p[@class='last']/text()
text = html //div[@class='body']
# Fields with '_' won't be uploaded to Plone so will be effectively removed
_permalink = text //div[@class='body']//a[@class='headerlink']
_label = optional //p[contains(@class,'admonition-title')]
_remove_useless_links = optional //div[@id = 'indices-and-tables']

# Images will get titles from backlink text
[titleguess]
condition = python:True

# Pages linked to content will be moved together
[indexguess]
condition = python:False

# Hide the images folder from navigation
[hideguess]
condition = python:item.get("_path","").startswith('_images') and item.get('_type')=='Folder'

# Upload as PHC instead of Folders and Pages
[changetype]
value=python:{'Folder':'HelpCenterReferenceManualSection','Document':'HelpCenterLeafPage'}.get(item['_type'],item['_type'])

# Save locally for debugging purposes
[localupload]
output=manual

# All folderish content should be checked if they contain
# any items on the remote site which are not presented locally. including base folder
[ploneprune]
condition=python:item.get('_type') in ['HelpCenterReferenceManualSection','HelpCenterReferenceManual'] or item['_path'] == ''