Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Recognize http URLs in identifiers with arbitrary keys

Browse Source
This commit is contained in:
Kovid Goyal 2017-05-11 14:01:47 +05:30
parent 496b0ce0f9
commit edfbb3c7bc
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 30 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

45
src/calibre/ebooks/metadata/sources/identify.py
View File

@ -533,6 +533,12 @@ def identify(log, abort, # {{{
def urls_from_identifiers(identifiers): # {{{ def urls_from_identifiers(identifiers): # {{{
identifiers = {k.lower():v for k, v in identifiers.iteritems()} identifiers = {k.lower():v for k, v in identifiers.iteritems()}
ans = [] ans = []
keys_left = set(identifiers)
def add(name, k, val, url):
ans.append((name, k, val, url))
keys_left.discard(k)
rules = msprefs['id_link_rules'] rules = msprefs['id_link_rules']
if rules: if rules:
formatter = EvalFormatter() formatter = EvalFormatter()
@ -546,40 +552,49 @@ def urls_from_identifiers(identifiers): # {{{
import traceback import traceback
traceback.format_exc() traceback.format_exc()
continue continue
ans.append((name, k, val, url)) add(name, k, val, url)
for plugin in all_metadata_plugins(): for plugin in all_metadata_plugins():
try: try:
for id_type, id_val, url in plugin.get_book_urls(identifiers): for id_type, id_val, url in plugin.get_book_urls(identifiers):
ans.append((plugin.get_book_url_name(id_type, id_val, url), id_type, id_val, url)) add(plugin.get_book_url_name(id_type, id_val, url), id_type, id_val, url)
except: except Exception:
pass pass
isbn = identifiers.get('isbn', None) isbn = identifiers.get('isbn', None)
if isbn: if isbn:
ans.append((isbn, 'isbn', isbn, add(isbn, 'isbn', isbn,
'https://www.worldcat.org/isbn/'+isbn)) 'https://www.worldcat.org/isbn/'+isbn)
doi = identifiers.get('doi', None) doi = identifiers.get('doi', None)
if doi: if doi:
ans.append(('DOI', 'doi', doi, add('DOI', 'doi', doi,
'https://dx.doi.org/'+doi)) 'https://dx.doi.org/'+doi)
arxiv = identifiers.get('arxiv', None) arxiv = identifiers.get('arxiv', None)
if arxiv: if arxiv:
ans.append(('arXiv', 'arxiv', arxiv, add('arXiv', 'arxiv', arxiv,
'https://arxiv.org/abs/'+arxiv)) 'https://arxiv.org/abs/'+arxiv)
oclc = identifiers.get('oclc', None) oclc = identifiers.get('oclc', None)
if oclc: if oclc:
ans.append(('OCLC', 'oclc', oclc, add('OCLC', 'oclc', oclc,
'https://www.worldcat.org/oclc/'+oclc)) 'https://www.worldcat.org/oclc/'+oclc)
issn = check_issn(identifiers.get('issn', None)) issn = check_issn(identifiers.get('issn', None))
if issn: if issn:
ans.append((issn, 'issn', issn, add(issn, 'issn', issn,
'https://www.worldcat.org/issn/'+issn)) 'https://www.worldcat.org/issn/'+issn)
q = {'http', 'https', 'file'}
for k, url in identifiers.iteritems(): for k, url in identifiers.iteritems():
if url and re.match(r'ur[il]\d*$', k) is not None: if url and re.match(r'ur[il]\d*$', k) is not None:
url = url[:8].replace('|', ':') + url[8:].replace('|', ',') url = url[:8].replace('|', ':') + url[8:].replace('|', ',')
if url.partition(':')[0].lower() in {'http', 'file', 'https'}: if url.partition(':')[0].lower() in q:
parts = urlparse(url) parts = urlparse(url)
name = parts.netloc or parts.path name = parts.netloc or parts.path
ans.append((name, k, url, url)) add(name, k, url, url)
for k in tuple(keys_left):
val = identifiers.get(k)
if val:
url = val[:8].replace('|', ':') + val[8:].replace('|', ',')
if url.partition(':')[0].lower() in q:
parts = urlparse(url)
name = parts.netloc or parts.path
add(name, k, url, url)
return ans return ans
# }}} # }}}