def _find_feed_items(mf2):
"""Extract feed items from given microformats2 data.
If the top-level h-* item is an h-feed, return its children. Otherwise,
returns the top-level items.
Args:
mf2: dict, parsed mf2 data
Returns: list of dicts, each one representing an mf2 h-* item
"""
feeditems = mf2['items']
hfeeds = mf2util.find_all_entries(mf2, ('h-feed', ))
if hfeeds:
feeditems = list(
itertools.chain.from_iterable(
hfeed.get('children', []) for hfeed in hfeeds))
else:
logger.debug('No h-feed found, fallback to top-level h-entrys.')
if len(feeditems) > MAX_FEED_ENTRIES:
logger.info(
f'Feed has {len(feeditems)} entries! only processing the first {MAX_FEED_ENTRIES}.'
)
feeditems = feeditems[:MAX_FEED_ENTRIES]
return feeditems
def _find_feed_items(feed_url, feed_doc):
"""Extract feed items from a given URL and document. If the top-level
h-* item is an h-feed, return its children. Otherwise, returns the
top-level items.
Args:
feed_url: a string. the URL passed to mf2py parser
feed_doc: a string or BeautifulSoup object. document is passed to
mf2py parser
Returns:
a list of dicts, each one representing an mf2 h-* item
"""
parsed = util.mf2py_parse(feed_doc, feed_url)
feeditems = parsed['items']
hfeeds = mf2util.find_all_entries(parsed, ('h-feed',))
if hfeeds:
feeditems = list(itertools.chain.from_iterable(
hfeed.get('children', []) for hfeed in hfeeds))
else:
logging.debug('No h-feed found, fallback to top-level h-entrys.')
if len(feeditems) > MAX_FEED_ENTRIES:
logging.info('%s has %s entries! only processing the first %s.',
feed_url, len(feeditems), MAX_FEED_ENTRIES)
feeditems = feeditems[:MAX_FEED_ENTRIES]
return feeditems
def _find_feed_items(feed_url, feed_doc):
"""Extract feed items from a given URL and document. If the top-level
h-* item is an h-feed, return its children. Otherwise, returns the
top-level items.
Args:
feed_url: a string. the URL passed to mf2py parser
feed_doc: a string or BeautifulSoup object. document is passed to
mf2py parser
Returns:
a list of dicts, each one representing an mf2 h-* item
"""
parsed = util.mf2py_parse(feed_doc, feed_url)
feeditems = parsed['items']
hfeeds = mf2util.find_all_entries(parsed, ('h-feed', ))
if hfeeds:
feeditems = list(
itertools.chain.from_iterable(
hfeed.get('children', []) for hfeed in hfeeds))
else:
logging.debug('No h-feed found, fallback to top-level h-entrys.')
if len(feeditems) > MAX_FEED_ENTRIES:
logging.info('%s has %s entries! only processing the first %s.',
feed_url, len(feeditems), MAX_FEED_ENTRIES)
feeditems = feeditems[:MAX_FEED_ENTRIES]
return feeditems
def _find_feed_items(feed_url, feed_doc):
"""Extract feed items from a given URL and document. If the top-level
h-* item is an h-feed, return its children. Otherwise, returns the
top-level items.
Args:
feed_url: a string. the URL passed to mf2py parser
feed_doc: a string or BeautifulSoup object. document is passed to
mf2py parser
Returns:
a list of dicts, each one representing an mf2 h-* item
"""
parsed = mf2py.parse(url=feed_url, doc=feed_doc)
feeditems = parsed['items']
hfeeds = mf2util.find_all_entries(parsed, ('h-feed',))
if hfeeds:
feeditems = list(itertools.chain.from_iterable(
hfeed.get('children', []) for hfeed in hfeeds))
else:
logging.debug('No h-feed found, fallback to top-level h-entrys.')
return feeditems
def representative_card(parsed, source_url):
"""
Find the representative card for a URL.
http://microformats.org/wiki/representative-h-card-parsing
:param dict parsed: an mf2 parsed dict
:param str source_url: the source of the parsed document.
:return: the representative h-card if one is found
"""
# FIXME NOTE mf2py needs plain mf2json
parsed = json.loads(JSONEncoder().encode(parsed)) # FIXME
source_url = uri.parse(source_url).minimized
cards = [
h
for h in util.find_all_entries(parsed, ["h-card"], include_properties=True)
if (
h["properties"].get("name", [""])[0]
or h["properties"].get("nickname", [""])[0]
)
]
if match := _check_uid_and_url_match_source_url(source_url, cards):
return match