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: Fix detection of series not working for some books due to changes in the amazon website

Browse Source
This commit is contained in:
Kovid Goyal 2017-01-04 11:11:40 +05:30
parent 392217d41d
commit 066fbef6f6
1 changed files with 13 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
src/calibre/ebooks/metadata/sources/amazon.py
View File

@ -591,6 +591,19 @@ class Worker(Thread): # Get details {{{
series = self.tostring(a[0], encoding=unicode, method='text', with_tail=False).strip() series = self.tostring(a[0], encoding=unicode, method='text', with_tail=False).strip()
if series: if series:
ans = (series, series_index) ans = (series, series_index)
# This is found on newer Kindle edition pages on amazon.com
if ans == (None, None):
for b in root.xpath('//div[@id="reviewFeatureGroup"]/span/b'):
text = (b.text or '').strip()
m = re.match('Book\s+([0-9.]+)', text)
if m is not None:
series_index = float(m.group(1))
a = b.getparent().xpath('./a[@href]')
if a:
series = self.tostring(a[0], encoding=unicode, method='text', with_tail=False).partition('(')[0].strip()
if series:
ans = series, series_index
if ans == (None, None): if ans == (None, None):
desc = root.xpath('//div[@id="ps-content"]/div[@class="buying"]') desc = root.xpath('//div[@id="ps-content"]/div[@class="buying"]')
if desc: if desc: