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

Improve downloading of covers from the google books metadata source

Browse Source
This commit is contained in:
Kovid Goyal 2017-02-28 14:19:19 +05:30
parent b5010e7060
commit c525f5587f
1 changed files with 19 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

33
src/calibre/ebooks/metadata/sources/google.py
View File

@ -59,6 +59,7 @@ def to_metadata(browser, log, entry_, timeout): # {{{
description = XPath('descendant::dc:description') description = XPath('descendant::dc:description')
language = XPath('descendant::dc:language') language = XPath('descendant::dc:language')
rating = XPath('descendant::gd:rating[@average]') rating = XPath('descendant::gd:rating[@average]')
# print(etree.tostring(entry_, pretty_print=True))
def get_text(extra, x): def get_text(extra, x):
try: try:
@ -170,14 +171,14 @@ class GoogleBooks(Source):
capabilities = frozenset({'identify', 'cover'}) capabilities = frozenset({'identify', 'cover'})
touched_fields = frozenset({ touched_fields = frozenset({
'title', 'authors', 'tags', 'pubdate', 'comments', 'publisher', 'title', 'authors', 'tags', 'pubdate', 'comments', 'publisher',
'identifier:isbn', 'rating', 'identifier:google', 'languages' 'identifier:isbn', 'identifier:google', 'languages'
}) })
supports_gzip_transfer_encoding = True supports_gzip_transfer_encoding = True
cached_cover_url_is_reliable = False cached_cover_url_is_reliable = False
GOOGLE_COVER = 'https://books.google.com/books?id=%s&printsec=frontcover&img=1' GOOGLE_COVER = 'https://books.google.com/books?id=%s&printsec=frontcover&img=1'
DUMMY_IMAGE_MD5 = frozenset({'0de4383ebad0adad5eeb8975cd796657'}) DUMMY_IMAGE_MD5 = frozenset({'0de4383ebad0adad5eeb8975cd796657', 'a64fa89d7ebc97075c1d363fc5fea71f'})
def get_book_url(self, identifiers): # {{{ def get_book_url(self, identifiers): # {{{
goog = identifiers.get('google', None) goog = identifiers.get('google', None)
@ -262,19 +263,22 @@ class GoogleBooks(Source):
log.info('No cover found') log.info('No cover found')
return return
if abort.is_set():
return
br = self.browser br = self.browser
log('Downloading cover from:', cached_url) for candidate in (0, 1):
try: if abort.is_set():
cdata = br.open_novisit(cached_url, timeout=timeout).read() return
if cdata: url = cached_url + '&zoom={}'.format(candidate)
if hashlib.md5(cdata).hexdigest() in self.DUMMY_IMAGE_MD5: log('Downloading cover from:', cached_url)
log.warning('Google returned a dummy image, ignoring') try:
else: cdata = br.open_novisit(url, timeout=timeout).read()
result_queue.put((self, cdata)) if cdata:
except: if hashlib.md5(cdata).hexdigest() in self.DUMMY_IMAGE_MD5:
log.exception('Failed to download cover from:', cached_url) log.warning('Google returned a dummy image, ignoring')
else:
result_queue.put((self, cdata))
break
except Exception:
log.exception('Failed to download cover from:', cached_url)
# }}} # }}}
@ -406,4 +410,5 @@ if __name__ == '__main__': # tests {{{
}, [title_test('Flatland', exact=False)]), }, [title_test('Flatland', exact=False)]),
] ]
) )
# }}} # }}}