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

Amazon metadata download plugin: Fix links being stripped from comments. Also fix ratings/isbn not being parsed from kindle edition pages. Fixes #782012 (amazon metadata errors)

Browse Source
This commit is contained in:
Kovid Goyal 2011-05-13 10:48:32 -06:00
parent a070127d1d
commit 1dd0706eae
1 changed files with 25 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
src/calibre/ebooks/metadata/sources/amazon.py
View File

@ -202,6 +202,8 @@ class Worker(Thread): # Get details {{{
def parse_rating(self, root): def parse_rating(self, root):
ratings = root.xpath('//div[@class="jumpBar"]/descendant::span[@class="asinReviewsSummary"]') ratings = root.xpath('//div[@class="jumpBar"]/descendant::span[@class="asinReviewsSummary"]')
if not ratings:
ratings = root.xpath('//div[@class="buying"]/descendant::span[@class="asinReviewsSummary"]')
pat = re.compile(r'([0-9.]+) out of (\d+) stars') pat = re.compile(r'([0-9.]+) out of (\d+) stars')
if ratings: if ratings:
for elem in ratings[0].xpath('descendant::*[@title]'): for elem in ratings[0].xpath('descendant::*[@title]'):
@ -215,9 +217,13 @@ class Worker(Thread): # Get details {{{
if desc: if desc:
desc = desc[0] desc = desc[0]
for c in desc.xpath('descendant::*[@class="seeAll" or' for c in desc.xpath('descendant::*[@class="seeAll" or'
' @class="emptyClear" or @href]'): ' @class="emptyClear"]'):
c.getparent().remove(c) c.getparent().remove(c)
for a in desc.xpath('descendant::a[@href]'):
del a.attrib['href']
a.tag = 'span'
desc = tostring(desc, method='html', encoding=unicode).strip() desc = tostring(desc, method='html', encoding=unicode).strip()
# Encoding bug in Amazon data U+fffd (replacement char) # Encoding bug in Amazon data U+fffd (replacement char)
# in some examples it is present in place of ' # in some examples it is present in place of '
desc = desc.replace('\ufffd', "'") desc = desc.replace('\ufffd', "'")
@ -246,8 +252,12 @@ class Worker(Thread): # Get details {{{
return ('/'.join(parts[:-1]))+'/'+bn return ('/'.join(parts[:-1]))+'/'+bn
def parse_isbn(self, pd): def parse_isbn(self, pd):
for x in reversed(pd.xpath( items = pd.xpath(
'descendant::*[starts-with(text(), "ISBN")]')): 'descendant::*[starts-with(text(), "ISBN")]')
if not items:
items = pd.xpath(
'descendant::b[contains(text(), "ISBN:")]')
for x in reversed(items):
if x.tail: if x.tail:
ans = check_isbn(x.tail.strip()) ans = check_isbn(x.tail.strip())
if ans: if ans:
@ -519,8 +529,17 @@ if __name__ == '__main__': # tests {{{
test_identify_plugin(Amazon.name, test_identify_plugin(Amazon.name,
[ [
( # An e-book ISBN not on Amazon, one of the authors is ( # Description has links
# unknown to Amazon, so no popup wrapper {'identifiers':{'isbn': '9780671578275'}},
[title_test('A Civil Campaign: A Comedy of Biology and Manners',
exact=True), authors_test(['Lois McMaster Bujold'])
]
),
( # An e-book ISBN not on Amazon, the title/author search matches
# the Kindle edition, which has different markup for ratings and
# isbn
{'identifiers':{'isbn': '9780307459671'}, {'identifiers':{'isbn': '9780307459671'},
'title':'Invisible Gorilla', 'authors':['Christopher Chabris']}, 'title':'Invisible Gorilla', 'authors':['Christopher Chabris']},
[title_test('The Invisible Gorilla: And Other Ways Our Intuitions Deceive Us', [title_test('The Invisible Gorilla: And Other Ways Our Intuitions Deceive Us',