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

Revert "Amazon metadata download: Get tags from amazon best seller rank"

Browse Source 
This reverts commit d0f179da8233fe7e61c1132f7fea31253c3105e2.

There are still many pages where the look for similar items is available
This commit is contained in:
Kovid Goyal 2013-09-23 15:21:32 +05:30
parent de4cddf853
commit 589ef0a5fe
1 changed files with 18 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
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.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( 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}') 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}')
@ -509,15 +521,8 @@ class Worker(Thread): # Get details {{{
exclude_tokens = {'kindle', 'a-z'} exclude_tokens = {'kindle', 'a-z'}
exclude = {'special features', 'by authors', 'authors & illustrators', 'books', 'new; used & rental textbooks'} exclude = {'special features', 'by authors', 'authors & illustrators', 'books', 'new; used & rental textbooks'}
seen = set() seen = set()
tags = root.xpath(''' for li in root.xpath(self.tags_xpath):
//div[@class="kindleAuthorRank"]/div[@class="browseNodeRanks"]/div[@class="nodeRank"] for i, a in enumerate(li.iterdescendants('a')):
''')
if not tags:
tags = root.xpath('''
//li[@id="SalesRank"]/descendant::span[@class="zg_hrsr_ladder"]
''')
for container in tags:
for i, a in enumerate(container.iterdescendants('a')):
if i > 0: if i > 0:
# we ignore the first category since it is almost always too broad # we ignore the first category since it is almost always too broad
raw = (a.text or '').strip().replace(',', ';') raw = (a.text or '').strip().replace(',', ';')
@ -1073,10 +1078,10 @@ if __name__ == '__main__': # tests {{{
authors_test(['F. Scott Fitzgerald'])] authors_test(['F. Scott Fitzgerald'])]
), ),
( # A newer book with tags via amazon best seller rank ( # A newer book
{'identifiers':{'isbn': '0385346824'}}, {'identifiers':{'isbn': '9780316044981'}},
[title_test('Ex-Communication: A Novel', exact=True), [title_test('The Heroes', exact=True),
authors_test(['Peter Clines']), ] authors_test(['Joe Abercrombie'])]
), ),