def extend_atom(self, entry):
'''Add additional fields to an RSS item.
:param feed: The RSS item XML element to use.
'''
groups = {None: entry}
for media_content in self.__media_content:
# Define current media:group
group = groups.get(media_content.get('group'))
if group is None:
group = xml_elem('{%s}group' % MEDIA_NS, entry)
groups[media_content.get('group')] = group
# Add content
content = xml_elem('{%s}content' % MEDIA_NS, group)
for attr in ('url', 'fileSize', 'type', 'medium', 'isDefault',
'expression', 'bitrate', 'framerate', 'samplingrate',
'channels', 'duration', 'height', 'width', 'lang'):
if media_content.get(attr):
content.set(attr, media_content[attr])
for media_thumbnail in self.__media_thumbnail:
# Define current media:group
group = groups.get(media_thumbnail.get('group'))
if group is None:
group = xml_elem('{%s}group' % MEDIA_NS, entry)
groups[media_thumbnail.get('group')] = group
# Add thumbnails
thumbnail = xml_elem('{%s}thumbnail' % MEDIA_NS, group)
for attr in ('url', 'height', 'width', 'time'):
if media_thumbnail.get(attr):
thumbnail.set(attr, media_thumbnail[attr])
return entry
def extend_file(self, entry):
'''Add additional fields to an RSS item.
:param feed: The RSS item XML element to use.
'''
GEO_NS = 'http://www.georss.org/georss'
if self.__point:
point = xml_elem('{%s}point' % GEO_NS, entry)
point.text = self.__point
if self.__line:
line = xml_elem('{%s}line' % GEO_NS, entry)
line.text = self.__line
if self.__polygon:
polygon = xml_elem('{%s}polygon' % GEO_NS, entry)
polygon.text = self.__polygon
if self.__box:
box = xml_elem('{%s}box' % GEO_NS, entry)
box.text = self.__box
if self.__featuretypetag:
featuretypetag = xml_elem('{%s}featuretypetag' % GEO_NS, entry)
featuretypetag.text = self.__featuretypetag
if self.__relationshiptag:
relationshiptag = xml_elem('{%s}relationshiptag' % GEO_NS, entry)
relationshiptag.text = self.__relationshiptag
if self.__featurename:
featurename = xml_elem('{%s}featurename' % GEO_NS, entry)
featurename.text = self.__featurename
if self.__elev:
elevation = xml_elem('{%s}elev' % GEO_NS, entry)
elevation.text = str(self.__elev)
if self.__floor:
floor = xml_elem('{%s}floor' % GEO_NS, entry)
floor.text = str(self.__floor)
if self.__radius:
radius = xml_elem('{%s}radius' % GEO_NS, entry)
radius.text = str(self.__radius)
return entry
def _add_text_elm(entry, data, name):
"""Add a text subelement to an entry"""
if not data:
return
elm = xml_elem(name, entry)
type_ = data.get('type')
if data.get('src'):
if name != 'content':
raise ValueError("Only the 'content' element of an entry can "
"contain a 'src' attribute")
elm.attrib['src'] = data['src']
elif data.get(name):
# Surround xhtml with a div tag, parse it and embed it
if type_ == 'xhtml':
xhtml = '<div xmlns="http://www.w3.org/1999/xhtml">' \
+ data.get(name) + '</div>'
elm.append(xml_fromstring(xhtml))
elif type_ == 'CDATA':
elm.text = CDATA(data.get(name))
# Parse XML and embed it
elif type_ and (type_.endswith('/xml') or type_.endswith('+xml')):
elm.append(xml_fromstring(data[name]))
# Embed the text in escaped form
elif not type_ or type_.startswith('text') or type_ == 'html':
elm.text = data.get(name)
# Everything else should be included base64 encoded
else:
raise NotImplementedError(
'base64 encoded {} is not supported at the moment. '
'Pull requests adding support are welcome.'.format(name)
)
# Add type description of the content
if type_:
elm.attrib['type'] = type_
def extend_rss(self, entry):
'''Add additional fields to an RSS item.
:param feed: The RSS item XML element to use.
'''
if self.__torrent_filename:
filename = xml_elem('{%s}filename' % TORRENT_NS, entry)
filename.text = self.__torrent_filename
if self.__torrent_contentlength:
contentlength = xml_elem('{%s}contentlength' % TORRENT_NS, entry)
contentlength.text = self.__torrent_contentlength
if self.__torrent_infohash:
infohash = xml_elem('{%s}infohash' % TORRENT_NS, entry)
infohash.text = self.__torrent_infohash
magnet = xml_elem('{%s}magneturi' % TORRENT_NS, entry)
magnet.text = 'magnet:?xt=urn:btih:' + self.__torrent_infohash
if self.__torrent_seeds:
seeds = xml_elem('{%s}seed' % TORRENT_NS, entry)
seeds.text = self.__torrent_seeds
if self.__torrent_peers:
peers = xml_elem('{%s}peers' % TORRENT_NS, entry)
peers.text = self.__torrent_peers
if self.__torrent_verified:
verified = xml_elem('{%s}verified' % TORRENT_NS, entry)
verified.text = self.__torrent_verified
def extend_rss(self, entry):
'''Add additional fields to an RSS item.
:param feed: The RSS item XML element to use.
'''
ITUNES_NS = 'http://www.itunes.com/dtds/podcast-1.0.dtd'
if self.__itunes_author:
author = xml_elem('{%s}author' % ITUNES_NS, entry)
author.text = self.__itunes_author
if self.__itunes_block is not None:
block = xml_elem('{%s}block' % ITUNES_NS, entry)
block.text = 'yes' if self.__itunes_block else 'no'
if self.__itunes_image:
image = xml_elem('{%s}image' % ITUNES_NS, entry)
image.attrib['href'] = self.__itunes_image
if self.__itunes_duration:
duration = xml_elem('{%s}duration' % ITUNES_NS, entry)
duration.text = self.__itunes_duration
if self.__itunes_explicit in ('yes', 'no', 'clean'):
explicit = xml_elem('{%s}explicit' % ITUNES_NS, entry)
explicit.text = self.__itunes_explicit
if self.__itunes_is_closed_captioned is not None:
is_closed_captioned = xml_elem('{%s}isClosedCaptioned' % ITUNES_NS,
entry)
if self.__itunes_is_closed_captioned:
is_closed_captioned.text = 'yes'
else:
is_closed_captioned.text = 'no'
if self.__itunes_order is not None and self.__itunes_order >= 0:
order = xml_elem('{%s}order' % ITUNES_NS, entry)
order.text = str(self.__itunes_order)
if self.__itunes_subtitle:
subtitle = xml_elem('{%s}subtitle' % ITUNES_NS, entry)
subtitle.text = self.__itunes_subtitle
if self.__itunes_summary:
summary = xml_elem('{%s}summary' % ITUNES_NS, entry)
summary.text = self.__itunes_summary
return entry
def _extend_xml(self, xml_element):
'''Extend xml_element with set DC fields.
:param xml_element: etree element
'''
DCELEMENTS_NS = 'http://purl.org/dc/elements/1.1/'
for elem in ['contributor', 'coverage', 'creator', 'date',
'description', 'language', 'publisher', 'relation',
'rights', 'source', 'subject', 'title', 'type', 'format',
'identifier']:
if hasattr(self, '_dcelem_%s' % elem):
for val in getattr(self, '_dcelem_%s' % elem) or []:
node = xml_elem('{%s}%s' % (DCELEMENTS_NS, elem),
xml_element)
node.text = val
def _set_value(channel, name, value):
if value:
newelem = xml_elem('{%s}' % SYNDICATION_NS + name, channel)
newelem.text = value
def _create_atom(self, extensions=True):
'''Create a ATOM feed xml structure containing all previously set
fields.
:returns: Tuple containing the feed root element and the element tree.
'''
nsmap = dict()
if extensions:
for ext in self.__extensions.values() or []:
if ext.get('atom'):
nsmap.update(ext['inst'].extend_ns())
feed = xml_elem('feed',
xmlns='http://www.w3.org/2005/Atom',
nsmap=nsmap)
if self.__atom_feed_xml_lang:
feed.attrib['{http://www.w3.org/XML/1998/namespace}lang'] = \
self.__atom_feed_xml_lang
if not (self.__atom_id and self.__atom_title and self.__atom_updated):
missing = ([] if self.__atom_title else ['title']) + \
([] if self.__atom_id else ['id']) + \
([] if self.__atom_updated else ['updated'])
missing = ', '.join(missing)
raise ValueError('Required fields not set (%s)' % missing)
id = xml_elem('id', feed)
id.text = self.__atom_id
title = xml_elem('title', feed)
title.text = self.__atom_title
updated = xml_elem('updated', feed)
updated.text = self.__atom_updated.isoformat()
# Add author elements
for a in self.__atom_author or []:
# Atom requires a name. Skip elements without.
if not a.get('name'):
continue
author = xml_elem('author', feed)
name = xml_elem('name', author)
name.text = a.get('name')
if a.get('email'):
email = xml_elem('email', author)
email.text = a.get('email')
if a.get('uri'):
uri = xml_elem('uri', author)
uri.text = a.get('uri')
for l in self.__atom_link or []:
link = xml_elem('link', feed, href=l['href'])
if l.get('rel'):
link.attrib['rel'] = l['rel']
if l.get('type'):
link.attrib['type'] = l['type']
if l.get('hreflang'):
link.attrib['hreflang'] = l['hreflang']
if l.get('title'):
link.attrib['title'] = l['title']
if l.get('length'):
link.attrib['length'] = l['length']
for c in self.__atom_category or []:
cat = xml_elem('category', feed, term=c['term'])
if c.get('scheme'):
cat.attrib['scheme'] = c['scheme']
if c.get('label'):
cat.attrib['label'] = c['label']
# Add author elements
for c in self.__atom_contributor or []:
# Atom requires a name. Skip elements without.
if not c.get('name'):
continue
contrib = xml_elem('contributor', feed)
name = xml_elem('name', contrib)
name.text = c.get('name')
if c.get('email'):
email = xml_elem('email', contrib)
email.text = c.get('email')
if c.get('uri'):
uri = xml_elem('uri', contrib)
uri.text = c.get('uri')
if self.__atom_generator and self.__atom_generator.get('value'):
generator = xml_elem('generator', feed)
generator.text = self.__atom_generator['value']
if self.__atom_generator.get('uri'):
generator.attrib['uri'] = self.__atom_generator['uri']
if self.__atom_generator.get('version'):
generator.attrib['version'] = self.__atom_generator['version']
if self.__atom_icon:
icon = xml_elem('icon', feed)
icon.text = self.__atom_icon
if self.__atom_logo:
logo = xml_elem('logo', feed)
logo.text = self.__atom_logo
if self.__atom_rights:
rights = xml_elem('rights', feed)
rights.text = self.__atom_rights
if self.__atom_subtitle:
subtitle = xml_elem('subtitle', feed)
subtitle.text = self.__atom_subtitle
if extensions:
for ext in self.__extensions.values() or []:
if ext.get('atom'):
ext['inst'].extend_atom(feed)
for entry in self.__feed_entries:
entry = entry.atom_entry()
feed.append(entry)
doc = etree.ElementTree(feed)
return feed, doc
def _create_rss(self, extensions=True):
'''Create an RSS feed xml structure containing all previously set
fields.
:returns: Tuple containing the feed root element and the element tree.
'''
nsmap = dict()
if extensions:
for ext in self.__extensions.values() or []:
if ext.get('rss'):
nsmap.update(ext['inst'].extend_ns())
nsmap.update({
'atom': 'http://www.w3.org/2005/Atom',
'content': 'http://purl.org/rss/1.0/modules/content/'
})
feed = xml_elem('rss', version='2.0', nsmap=nsmap)
channel = xml_elem('channel', feed)
if not (self.__rss_title and self.__rss_link
and self.__rss_description):
missing = ([] if self.__rss_title else ['title']) + \
([] if self.__rss_link else ['link']) + \
([] if self.__rss_description else ['description'])
missing = ', '.join(missing)
raise ValueError('Required fields not set (%s)' % missing)
title = xml_elem('title', channel)
title.text = self.__rss_title
link = xml_elem('link', channel)
link.text = self.__rss_link
desc = xml_elem('description', channel)
desc.text = self.__rss_description
for ln in self.__atom_link or []:
# It is recommended to include a atom self link in rss documents…
if ln.get('rel') == 'self':
selflink = xml_elem('{http://www.w3.org/2005/Atom}link',
channel,
href=ln['href'],
rel='self')
if ln.get('type'):
selflink.attrib['type'] = ln['type']
if ln.get('hreflang'):
selflink.attrib['hreflang'] = ln['hreflang']
if ln.get('title'):
selflink.attrib['title'] = ln['title']
if ln.get('length'):
selflink.attrib['length'] = ln['length']
break
if self.__rss_category:
for cat in self.__rss_category:
category = xml_elem('category', channel)
category.text = cat['value']
if cat.get('domain'):
category.attrib['domain'] = cat['domain']
if self.__rss_cloud:
cloud = xml_elem('cloud', channel)
cloud.attrib['domain'] = self.__rss_cloud.get('domain')
cloud.attrib['port'] = self.__rss_cloud.get('port')
cloud.attrib['path'] = self.__rss_cloud.get('path')
cloud.attrib['registerProcedure'] = self.__rss_cloud.get(
'registerProcedure')
cloud.attrib['protocol'] = self.__rss_cloud.get('protocol')
if self.__rss_copyright:
copyright = xml_elem('copyright', channel)
copyright.text = self.__rss_copyright
if self.__rss_docs:
docs = xml_elem('docs', channel)
docs.text = self.__rss_docs
if self.__rss_generator:
generator = xml_elem('generator', channel)
generator.text = self.__rss_generator
if self.__rss_image:
image = xml_elem('image', channel)
url = xml_elem('url', image)
url.text = self.__rss_image.get('url')
title = xml_elem('title', image)
title.text = self.__rss_image.get('title', self.__rss_title)
link = xml_elem('link', image)
link.text = self.__rss_image.get('link', self.__rss_link)
if self.__rss_image.get('width'):
width = xml_elem('width', image)
width.text = self.__rss_image.get('width')
if self.__rss_image.get('height'):
height = xml_elem('height', image)
height.text = self.__rss_image.get('height')
if self.__rss_image.get('description'):
description = xml_elem('description', image)
description.text = self.__rss_image.get('description')
if self.__rss_language:
language = xml_elem('language', channel)
language.text = self.__rss_language
if self.__rss_lastBuildDate:
lastBuildDate = xml_elem('lastBuildDate', channel)
lastBuildDate.text = formatRFC2822(self.__rss_lastBuildDate)
if self.__rss_managingEditor:
managingEditor = xml_elem('managingEditor', channel)
managingEditor.text = self.__rss_managingEditor
if self.__rss_pubDate:
pubDate = xml_elem('pubDate', channel)
pubDate.text = formatRFC2822(self.__rss_pubDate)
if self.__rss_rating:
rating = xml_elem('rating', channel)
rating.text = self.__rss_rating
if self.__rss_skipHours:
skipHours = xml_elem('skipHours', channel)
for h in self.__rss_skipHours:
hour = xml_elem('hour', skipHours)
hour.text = str(h)
if self.__rss_skipDays:
skipDays = xml_elem('skipDays', channel)
for d in self.__rss_skipDays:
day = xml_elem('day', skipDays)
day.text = d
if self.__rss_textInput:
textInput = xml_elem('textInput', channel)
textInput.attrib['title'] = self.__rss_textInput.get('title')
textInput.attrib['description'] = \
self.__rss_textInput.get('description')
textInput.attrib['name'] = self.__rss_textInput.get('name')
textInput.attrib['link'] = self.__rss_textInput.get('link')
if self.__rss_ttl:
ttl = xml_elem('ttl', channel)
ttl.text = str(self.__rss_ttl)
if self.__rss_webMaster:
webMaster = xml_elem('webMaster', channel)
webMaster.text = self.__rss_webMaster
if extensions:
for ext in self.__extensions.values() or []:
if ext.get('rss'):
ext['inst'].extend_rss(feed)
for entry in self.__feed_entries:
item = entry.rss_entry()
channel.append(item)
doc = etree.ElementTree(feed)
return feed, doc
def extend_rss(self, rss_feed):
'''Extend an RSS feed root with set itunes fields.
:returns: The feed root element.
'''
ITUNES_NS = 'http://www.itunes.com/dtds/podcast-1.0.dtd'
channel = rss_feed[0]
if self.__itunes_author:
author = xml_elem('{%s}author' % ITUNES_NS, channel)
author.text = self.__itunes_author
if self.__itunes_block is not None:
block = xml_elem('{%s}block' % ITUNES_NS, channel)
block.text = 'yes' if self.__itunes_block else 'no'
for c in self.__itunes_category or []:
if not c.get('cat'):
continue
category = channel.find(
'{%s}category[@text="%s"]' % (ITUNES_NS, c.get('cat')))
if category is None:
category = xml_elem('{%s}category' % ITUNES_NS, channel)
category.attrib['text'] = c.get('cat')
if c.get('sub'):
subcategory = xml_elem('{%s}category' % ITUNES_NS, category)
subcategory.attrib['text'] = c.get('sub')
if self.__itunes_image:
image = xml_elem('{%s}image' % ITUNES_NS, channel)
image.attrib['href'] = self.__itunes_image
if self.__itunes_explicit in ('yes', 'no', 'clean'):
explicit = xml_elem('{%s}explicit' % ITUNES_NS, channel)
explicit.text = self.__itunes_explicit
if self.__itunes_complete in ('yes', 'no'):
complete = xml_elem('{%s}complete' % ITUNES_NS, channel)
complete.text = self.__itunes_complete
if self.__itunes_new_feed_url:
new_feed_url = xml_elem('{%s}new-feed-url' % ITUNES_NS, channel)
new_feed_url.text = self.__itunes_new_feed_url
if self.__itunes_owner:
owner = xml_elem('{%s}owner' % ITUNES_NS, channel)
owner_name = xml_elem('{%s}name' % ITUNES_NS, owner)
owner_name.text = self.__itunes_owner.get('name')
owner_email = xml_elem('{%s}email' % ITUNES_NS, owner)
owner_email.text = self.__itunes_owner.get('email')
if self.__itunes_subtitle:
subtitle = xml_elem('{%s}subtitle' % ITUNES_NS, channel)
subtitle.text = self.__itunes_subtitle
if self.__itunes_summary:
summary = xml_elem('{%s}summary' % ITUNES_NS, channel)
summary.text = self.__itunes_summary
if self.__itunes_type in ('episodic', 'serial'):
type = xml_elem('{%s}type' % ITUNES_NS, channel)
type.text = self.__itunes_type
return rss_feed
def rss_entry(self, extensions=True):
'''Create a RSS item and return it.'''
entry = xml_elem('item')
if not (self.__rss_title or
self.__rss_description or
self.__rss_content):
raise ValueError('Required fields not set')
if self.__rss_title:
title = xml_elem('title', entry)
title.text = self.__rss_title
if self.__rss_link:
link = xml_elem('link', entry)
link.text = self.__rss_link
if self.__rss_description and self.__rss_content:
description = xml_elem('description', entry)
description.text = self.__rss_description
XMLNS_CONTENT = 'http://purl.org/rss/1.0/modules/content/'
content = xml_elem('{%s}encoded' % XMLNS_CONTENT, entry)
content.text = CDATA(self.__rss_content['content']) \
if self.__rss_content.get('type', '') == 'CDATA' \
else self.__rss_content['content']
elif self.__rss_description:
description = xml_elem('description', entry)
description.text = self.__rss_description
elif self.__rss_content:
description = xml_elem('description', entry)
description.text = CDATA(self.__rss_content['content']) \
if self.__rss_content.get('type', '') == 'CDATA' \
else self.__rss_content['content']
for a in self.__rss_author or []:
author = xml_elem('author', entry)
author.text = a
if self.__rss_guid.get('guid'):
guid = xml_elem('guid', entry)
guid.text = self.__rss_guid['guid']
permaLink = str(self.__rss_guid.get('permalink', False)).lower()
guid.attrib['isPermaLink'] = permaLink
for cat in self.__rss_category or []:
category = xml_elem('category', entry)
category.text = cat['value']
if cat.get('domain'):
category.attrib['domain'] = cat['domain']
if self.__rss_comments:
comments = xml_elem('comments', entry)
comments.text = self.__rss_comments
if self.__rss_enclosure:
enclosure = xml_elem('enclosure', entry)
enclosure.attrib['url'] = self.__rss_enclosure['url']
enclosure.attrib['length'] = self.__rss_enclosure['length']
enclosure.attrib['type'] = self.__rss_enclosure['type']
if self.__rss_pubDate:
pubDate = xml_elem('pubDate', entry)
pubDate.text = formatRFC2822(self.__rss_pubDate)
if self.__rss_source:
source = xml_elem('source', entry, url=self.__rss_source['url'])
source.text = self.__rss_source['title']
if extensions:
for ext in self.__extensions.values() or []:
if ext.get('rss'):
ext['inst'].extend_rss(entry)
return entry
def atom_entry(self, extensions=True):
'''Create an ATOM entry and return it.'''
entry = xml_elem('entry')
if not (self.__atom_id and self.__atom_title and self.__atom_updated):
raise ValueError('Required fields not set')
id = xml_elem('id', entry)
id.text = self.__atom_id
title = xml_elem('title', entry)
title.text = self.__atom_title
updated = xml_elem('updated', entry)
updated.text = self.__atom_updated.isoformat()
# An entry must contain an alternate link if there is no content
# element.
if not self.__atom_content:
links = self.__atom_link or []
if not [l for l in links if l.get('rel') == 'alternate']:
raise ValueError('Entry must contain an alternate link or ' +
'a content element.')
# Add author elements
for a in self.__atom_author or []:
# Atom requires a name. Skip elements without.
if not a.get('name'):
continue
author = xml_elem('author', entry)
name = xml_elem('name', author)
name.text = a.get('name')
if a.get('email'):
email = xml_elem('email', author)
email.text = a.get('email')
if a.get('uri'):
uri = xml_elem('uri', author)
uri.text = a.get('uri')
_add_text_elm(entry, self.__atom_content, 'content')
for l in self.__atom_link or []:
link = xml_elem('link', entry, href=l['href'])
if l.get('rel'):
link.attrib['rel'] = l['rel']
if l.get('type'):
link.attrib['type'] = l['type']
if l.get('hreflang'):
link.attrib['hreflang'] = l['hreflang']
if l.get('title'):
link.attrib['title'] = l['title']
if l.get('length'):
link.attrib['length'] = l['length']
_add_text_elm(entry, self.__atom_summary, 'summary')
for c in self.__atom_category or []:
cat = xml_elem('category', entry, term=c['term'])
if c.get('scheme'):
cat.attrib['scheme'] = c['scheme']
if c.get('label'):
cat.attrib['label'] = c['label']
# Add author elements
for c in self.__atom_contributor or []:
# Atom requires a name. Skip elements without.
if not c.get('name'):
continue
contrib = xml_elem('contributor', entry)
name = xml_elem('name', contrib)
name.text = c.get('name')
if c.get('email'):
email = xml_elem('email', contrib)
email.text = c.get('email')
if c.get('uri'):
uri = xml_elem('uri', contrib)
uri.text = c.get('uri')
if self.__atom_published:
published = xml_elem('published', entry)
published.text = self.__atom_published.isoformat()
if self.__atom_rights:
rights = xml_elem('rights', entry)
rights.text = self.__atom_rights
if self.__atom_source:
source = xml_elem('source', entry)
if self.__atom_source.get('title'):
source_title = xml_elem('title', source)
source_title.text = self.__atom_source['title']
if self.__atom_source.get('link'):
xml_elem('link', source, href=self.__atom_source['link'])
if extensions:
for ext in self.__extensions.values() or []:
if ext.get('atom'):
ext['inst'].extend_atom(entry)
return entry