Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-11-03 19:17:02 -05:00
Code Issues Packages Projects Releases Wiki Activity

Support Dublin Core id tags when importing HTML

Browse Source 
All of the below formats are supported and would be interpreted as "foo:bar"
<meta name="DC.identifier" scheme="foo" content="bar" />
<meta name="dc:identifier.foo" content="bar/>
<meta name="DCTERMS:identifier" scheme="foo" content="bar" />
<meta name="dcterms.identifier.foo" content="bar" />
This commit is contained in:
Christopher Szucko 2019-08-09 08:54:26 -05:00
parent c1663d3cc8
commit 9c846f3b51
1 changed files with 27 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
src/calibre/ebooks/metadata/html.py
View File

@ -10,6 +10,8 @@ Try to read metadata from an HTML file.
import re import re
from HTMLParser import HTMLParser
from calibre.ebooks.metadata import string_to_authors from calibre.ebooks.metadata import string_to_authors
from calibre.ebooks.metadata.book.base import Metadata from calibre.ebooks.metadata.book.base import Metadata
from calibre.ebooks.chardet import xml_to_unicode from calibre.ebooks.chardet import xml_to_unicode
@ -87,6 +89,26 @@ def parse_meta_tags(src):
return ans return ans
return ans return ans
def parse_meta_tag_identifiers(src):
meta_identifiers = {}
class MetadataParser(HTMLParser):
def handle_starttag(self, tag, attrs):
attr_dict = dict(attrs)
if tag == 'meta' and re.match(r'(?:dc|dcterms)[\.:]identifier', attr_dict.get('name', ''), flags=re.IGNORECASE):
content = attr_dict.get('content', '').strip()
scheme = attr_dict.get('scheme', '').strip()
if not scheme:
elements = re.split(r'[\.:]', attr_dict['name'])
if len(elements) == 3:
scheme = elements[2]
if content and scheme:
meta_identifiers[scheme.lower()] = replace_entities(content)
MetadataParser().feed(src)
return meta_identifiers
def parse_comment_tags(src): def parse_comment_tags(src):
all_names = '|'.join(itervalues(COMMENT_NAMES)) all_names = '|'.join(itervalues(COMMENT_NAMES))
@ -113,6 +135,7 @@ def get_metadata_(src, encoding=None):
src = src[:150000] # Searching shouldn't take too long src = src[:150000] # Searching shouldn't take too long
comment_tags = parse_comment_tags(src) comment_tags = parse_comment_tags(src)
meta_tags = parse_meta_tags(src) meta_tags = parse_meta_tags(src)
meta_tag_ids = parse_meta_tag_identifiers(src)
def get(field): def get(field):
ans = comment_tags.get(field, meta_tags.get(field, None)) ans = comment_tags.get(field, meta_tags.get(field, None))
@ -193,4 +216,8 @@ def get_metadata_(src, encoding=None):
if tags: if tags:
mi.tags = tags mi.tags = tags
# IDENTIFIERS
for (k,v) in meta_tag_ids.iteritems():
mi.set_identifier(k, v)
return mi return mi