Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-08 18:54:09 -04:00
Code Issues Packages Projects Releases Wiki Activity

Amazon metadata download plugin: Use the xisbn service to search for all related ISBNs on Amazon

Browse Source
This commit is contained in:
Kovid Goyal 2010-10-27 17:12:21 -06:00
parent 620102102e
commit 3065cbbe91
1 changed files with 33 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

43
src/calibre/ebooks/metadata/amazon.py
View File

@ -26,15 +26,7 @@ def find_asin(br, isbn):
if revs: if revs:
return revs[0] return revs[0]
def to_asin(br, isbn):
def get_social_metadata(title, authors, publisher, isbn):
mi = Metadata(title, authors)
if not isbn:
return mi
isbn = check_isbn(isbn)
if not isbn:
return mi
br = browser()
if len(isbn) == 13: if len(isbn) == 13:
try: try:
asin = find_asin(br, isbn) asin = find_asin(br, isbn)
@ -44,15 +36,36 @@ def get_social_metadata(title, authors, publisher, isbn):
asin = None asin = None
else: else:
asin = isbn asin = isbn
return asin
def get_social_metadata(title, authors, publisher, isbn):
mi = Metadata(title, authors)
if not isbn:
return mi
isbn = check_isbn(isbn)
if not isbn:
return mi
br = browser()
asin = to_asin(br, isbn)
if asin: if asin:
if get_metadata(br, asin, mi): if get_metadata(br, asin, mi):
return mi return mi
# TODO: Use xisbn to search over all isbns from calibre.ebooks.metadata.xisbn import xisbn
for i in xisbn.get_associated_isbns(isbn):
asin = to_asin(br, i)
if get_metadata(br, asin, mi):
return mi
return mi return mi
def get_metadata(br, asin, mi): def get_metadata(br, asin, mi):
q = 'http://amzn.com/'+asin q = 'http://amzn.com/'+asin
try:
raw = br.open_novisit(q).read() raw = br.open_novisit(q).read()
except Exception, e:
if callable(getattr(e, 'getcode', None)) and \
e.getcode() == 404:
return False
raise
if '<title>404 - ' in raw: if '<title>404 - ' in raw:
return False return False
raw = xml_to_unicode(raw, strip_encoding_pats=True, raw = xml_to_unicode(raw, strip_encoding_pats=True,
@ -86,11 +99,19 @@ def get_metadata(br, asin, mi):
desc = re.sub(r'(?s)<!--.*?-->', '', desc) desc = re.sub(r'(?s)<!--.*?-->', '', desc)
mi.comments = desc mi.comments = desc
return True
def main(args=sys.argv): def main(args=sys.argv):
# Test xisbn
print get_social_metadata('Learning Python', None, None, '8324616489')
print
# Test sophisticated comment formatting
print get_social_metadata('Swan Thieves', None, None, '9780316065795') print get_social_metadata('Swan Thieves', None, None, '9780316065795')
print print
return 0
# Random tests
print get_social_metadata('Star Trek: Destiny: Mere Mortals', None, None, '9781416551720') print get_social_metadata('Star Trek: Destiny: Mere Mortals', None, None, '9781416551720')
print print
print get_social_metadata('The Great Gatsby', None, None, '0743273567') print get_social_metadata('The Great Gatsby', None, None, '0743273567')