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

Download tags from Amazon

Browse Source 
When downloading metadata from Amazon, convert the amazon categories into
tags. You can turn this off by going to Preferences->Metadata download
and configuring the Amazon source. Fixes #1206763 [[Enhancement] Get tags from Amazon](https://bugs.launchpad.net/calibre/+bug/1206763)
This commit is contained in:
Kovid Goyal 2013-08-01 10:35:31 +05:30
parent fda8ce7abb
commit d38dffa86d
1 changed files with 35 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
src/calibre/ebooks/metadata/sources/amazon.py
View File

@ -162,6 +162,18 @@ class Worker(Thread): # Get details {{{
'''
self.language_names = {'Language', 'Sprache', 'Lingua', 'Idioma', 'Langue', '言語'}
self.tags_xpath = '''
descendant::h2[
text() = "Look for Similar Items by Category" or
text() = "Ähnliche Artikel finden" or
text() = "Buscar productos similares por categoría" or
text() = "Ricerca articoli simili per categoria" or
text() = "Rechercher des articles similaires par rubrique" or
text() = "Procure por itens similares por categoria" or
text() = "関連商品を探す"
]/../descendant::ul/li
'''
self.ratings_pat = re.compile(
r'([0-9.]+) ?(out of|von|su|étoiles sur|つ星のうち|de un máximo de|de) ([\d\.]+)( (stars|Sternen|stelle|estrellas|estrelas)){0,1}')
@ -312,6 +324,11 @@ class Worker(Thread): # Get details {{{
except:
self.log.exception('Error parsing series for url: %r'%self.url)
try:
mi.tags = self.parse_tags(root)
except:
self.log.exception('Error parsing tags for url: %r'%self.url)
try:
self.cover_url = self.parse_cover(root, raw)
except:
@ -490,6 +507,23 @@ class Worker(Thread): # Get details {{{
ans = (s, i)
return ans
def parse_tags(self, root):
ans = []
exclude_tokens = {'kindle', 'a-z'}
exclude = {'special features', 'by authors', 'authors & illustrators', 'books', 'new; used & rental textbooks'}
seen = set()
for li in root.xpath(self.tags_xpath):
for i, a in enumerate(li.iterdescendants('a')):
if i > 0:
# we ignore the first category since it is almost always too broad
raw = (a.text or '').strip().replace(',', ';')
lraw = icu_lower(raw)
tokens = frozenset(lraw.split())
if raw and lraw not in exclude and not tokens.intersection(exclude_tokens) and lraw not in seen:
ans.append(raw)
seen.add(lraw)
return ans
def parse_cover(self, root, raw=b""):
imgs = root.xpath('//img[(@id="prodImage" or @id="original-main-image" or @id="main-image") and @src]')
if not imgs:
@ -588,7 +622,7 @@ class Amazon(Source):
capabilities = frozenset(['identify', 'cover'])
touched_fields = frozenset(['title', 'authors', 'identifier:amazon',
'identifier:isbn', 'rating', 'comments', 'publisher', 'pubdate',
'languages', 'series'])
'languages', 'series', 'tags'])
has_html_comments = True
supports_gzip_transfer_encoding = True