Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 10:14:46 -04:00
Code Issues Packages Projects Releases Wiki Activity

Amazon metadata download: Add support for Amazon Australia (can be

Browse Source 
configured via Preferences->Metadata download->customize the amazon
metadata source)
This commit is contained in:
Kovid Goyal 2018-09-06 08:19:24 +05:30
parent d07f070a66
commit 77bd4f4544
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 13 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
src/calibre/ebooks/metadata/sources/amazon.py
View File

@ -598,7 +598,7 @@ class Worker(Thread): # Get details {{{
else: else:
# Idiot chickens from amazon strike again. This data is now stored # Idiot chickens from amazon strike again. This data is now stored
# in a JS variable inside a script tag URL encoded. # in a JS variable inside a script tag URL encoded.
m = re.search(b'var\s+iframeContent\s*=\s*"([^"]+)"', raw) m = re.search(br'var\s+iframeContent\s*=\s*"([^"]+)"', raw)
if m is not None: if m is not None:
try: try:
text = unquote(m.group(1)).decode('utf-8') text = unquote(m.group(1)).decode('utf-8')
@ -624,7 +624,7 @@ class Worker(Thread): # Get details {{{
if spans: if spans:
raw = self.tostring( raw = self.tostring(
spans[0], encoding=unicode, method='text', with_tail=False).strip() spans[0], encoding=unicode, method='text', with_tail=False).strip()
m = re.search('\s+([0-9.]+)$', raw.strip()) m = re.search(r'\s+([0-9.]+)$', raw.strip())
if m is not None: if m is not None:
series_index = float(m.group(1)) series_index = float(m.group(1))
s = series.xpath('./a[@id="series-page-link"]') s = series.xpath('./a[@id="series-page-link"]')
@ -637,7 +637,7 @@ class Worker(Thread): # Get details {{{
if ans == (None, None): if ans == (None, None):
for span in root.xpath('//div[@id="aboutEbooksSection"]//li/span'): for span in root.xpath('//div[@id="aboutEbooksSection"]//li/span'):
text = (span.text or '').strip() text = (span.text or '').strip()
m = re.match('Book\s+([0-9.]+)', text) m = re.match(r'Book\s+([0-9.]+)', text)
if m is not None: if m is not None:
series_index = float(m.group(1)) series_index = float(m.group(1))
a = span.xpath('./a[@href]') a = span.xpath('./a[@href]')
@ -650,7 +650,7 @@ class Worker(Thread): # Get details {{{
if ans == (None, None): if ans == (None, None):
for b in root.xpath('//div[@id="reviewFeatureGroup"]/span/b'): for b in root.xpath('//div[@id="reviewFeatureGroup"]/span/b'):
text = (b.text or '').strip() text = (b.text or '').strip()
m = re.match('Book\s+([0-9.]+)', text) m = re.match(r'Book\s+([0-9.]+)', text)
if m is not None: if m is not None:
series_index = float(m.group(1)) series_index = float(m.group(1))
a = b.getparent().xpath('./a[@href]') a = b.getparent().xpath('./a[@href]')
@ -839,7 +839,7 @@ class Worker(Thread): # Get details {{{
class Amazon(Source): class Amazon(Source):
name = 'Amazon.com' name = 'Amazon.com'
version = (1, 2, 2) version = (1, 2, 3)
minimum_calibre_version = (2, 82, 0) minimum_calibre_version = (2, 82, 0)
description = _('Downloads metadata and covers from Amazon') description = _('Downloads metadata and covers from Amazon')
@ -856,6 +856,7 @@ class Amazon(Source):
'fr': _('France'), 'fr': _('France'),
'de': _('Germany'), 'de': _('Germany'),
'uk': _('UK'), 'uk': _('UK'),
'au': _('Australia'),
'it': _('Italy'), 'it': _('Italy'),
'jp': _('Japan'), 'jp': _('Japan'),
'es': _('Spain'), 'es': _('Spain'),
@ -957,13 +958,11 @@ class Amazon(Source):
def referrer_for_domain(self, domain=None): def referrer_for_domain(self, domain=None):
domain = domain or self.domain domain = domain or self.domain
if domain == 'uk': return {
return 'https://www.amazon.co.uk/' 'uk': 'https://www.amazon.co.uk/',
if domain == 'br': 'au': 'https://www.amazon.com.au/',
return 'https://www.amazon.com.br/' 'br': 'https://www.amazon.com.br/',
if domain == 'au': }.get(domain, 'https://www.amazon.%s/' % domain)
return 'https://www.amazon.com.au/'
return 'https://www.amazon.%s/' % domain
def _get_book_url(self, identifiers): # {{{ def _get_book_url(self, identifiers): # {{{
domain, asin = self.get_domain_and_asin( domain, asin = self.get_domain_and_asin(
@ -1016,7 +1015,7 @@ class Amazon(Source):
def clean_downloaded_metadata(self, mi): def clean_downloaded_metadata(self, mi):
docase = ( docase = (
mi.language == 'eng' or mi.language == 'eng' or
(mi.is_null('language') and self.domain in {'com', 'uk'}) (mi.is_null('language') and self.domain in {'com', 'uk', 'au'})
) )
if mi.title and docase: if mi.title and docase:
# Remove series information from title # Remove series information from title
@ -1039,14 +1038,7 @@ class Amazon(Source):
break break
def get_website_domain(self, domain): def get_website_domain(self, domain):
udomain = domain return {'uk': 'co.uk', 'jp': 'co.jp', 'br': 'com.br', 'au': 'com.au'}.get(domain, domain)
if domain == 'uk':
udomain = 'co.uk'
elif domain == 'jp':
udomain = 'co.jp'
elif domain == 'br':
udomain = 'com.br'
return udomain
def create_query(self, log, title=None, authors=None, identifiers={}, # {{{ def create_query(self, log, title=None, authors=None, identifiers={}, # {{{
domain=None, for_amazon=True): domain=None, for_amazon=True):