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

Split amazon UK and DE away from US, making each a separate plugin

Browse Source
This commit is contained in:
Charles Haley 2011-06-06 12:20:05 +01:00
parent 408adb911b
commit ae724b9ef6
2 changed files with 105 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

107
src/calibre/gui2/store/amazon_de_plugin.py
View File

@ -6,21 +6,23 @@ __license__ = 'GPL 3'
__copyright__ = '2011, John Schember <john@nachtimwald.com>'
__docformat__ = 'restructuredtext en'
import re, urllib
from contextlib import closing
from lxml import html
from PyQt4.Qt import QUrl
from calibre import browser
from calibre.gui2 import open_url
from calibre.gui2.store.amazon_plugin import AmazonKindleStore
from calibre.gui2.store import StorePlugin
from calibre.gui2.store.search_result import SearchResult
class AmazonDEKindleStore(AmazonKindleStore):
class AmazonDEKindleStore(StorePlugin):
'''
For comments on the implementation, please see amazon_plugin.py
'''
search_url = 'http://www.amazon.de/s/?url=search-alias%3Ddigital-text&field-keywords='
details_url = 'http://amazon.de/dp/'
drm_search_text = u'Gleichzeitige Verwendung von Geräten'
drm_free_text = u'Keine Einschränkung'
def open(self, parent=None, detail_item=None, external=False):
aff_id = {'tag': 'charhale0a-21'}
store_link = ('http://www.amazon.de/gp/redirect.html?ie=UTF8&site-redirect=de'
@ -32,3 +34,94 @@ class AmazonDEKindleStore(AmazonKindleStore):
'&location=http://www.amazon.de/dp/%(asin)s&site-redirect=de'
'&tag=%(tag)s&linkCode=ur2&camp=1638&creative=6742') % aff_id
open_url(QUrl(store_link))
def search(self, query, max_results=10, timeout=60):
search_url = 'http://www.amazon.de/s/?url=search-alias%3Ddigital-text&field-keywords='
url = search_url + urllib.quote_plus(query)
br = browser()
counter = max_results
with closing(br.open(url, timeout=timeout)) as f:
doc = html.fromstring(f.read())
# Amazon has two results pages.
is_shot = doc.xpath('boolean(//div[@id="shotgunMainResults"])')
# Horizontal grid of books.
if is_shot:
data_xpath = '//div[contains(@class, "result")]'
format_xpath = './/div[@class="productTitle"]/text()'
cover_xpath = './/div[@class="productTitle"]//img/@src'
# Vertical list of books.
else:
data_xpath = '//div[@class="productData"]'
format_xpath = './/span[@class="format"]/text()'
cover_xpath = '../div[@class="productImage"]/a/img/@src'
for data in doc.xpath(data_xpath):
if counter <= 0:
break
# Even though we are searching digital-text only Amazon will still
# put in results for non Kindle books (author pages). Se we need
# to explicitly check if the item is a Kindle book and ignore it
# if it isn't.
format = ''.join(data.xpath(format_xpath))
if 'kindle' not in format.lower():
continue
# We must have an asin otherwise we can't easily reference the
# book later.
asin_href = None
asin_a = data.xpath('.//div[@class="productTitle"]/a[1]')
if asin_a:
asin_href = asin_a[0].get('href', '')
m = re.search(r'/dp/(?P<asin>.+?)(/|$)', asin_href)
if m:
asin = m.group('asin')
else:
continue
else:
continue
cover_url = ''.join(data.xpath(cover_xpath))
title = ''.join(data.xpath('.//div[@class="productTitle"]/a/text()'))
price = ''.join(data.xpath('.//div[@class="newPrice"]/span/text()'))
if is_shot:
author = format.split(' von ')[-1]
else:
author = ''.join(data.xpath('.//div[@class="productTitle"]/span[@class="ptBrand"]/text()'))
author = author.split(' von ')[-1]
counter -= 1
s = SearchResult()
s.cover_url = cover_url.strip()
s.title = title.strip()
s.author = author.strip()
s.price = price.strip()
s.detail_item = asin.strip()
s.formats = 'Kindle'
yield s
def get_details(self, search_result, timeout):
drm_search_text = u'Gleichzeitige Verwendung von Geräten'
drm_free_text = u'Keine Einschränkung'
url = 'http://amazon.de/dp/'
br = browser()
with closing(br.open(url + search_result.detail_item, timeout=timeout)) as nf:
idata = html.fromstring(nf.read())
if idata.xpath('boolean(//div[@class="content"]//li/b[contains(text(), "' +
drm_search_text + '")])'):
if idata.xpath('boolean(//div[@class="content"]//li[contains(., "' +
drm_free_text + '") and contains(b, "' +
drm_search_text + '")])'):
search_result.drm = SearchResult.DRM_UNLOCKED
else:
search_result.drm = SearchResult.DRM_UNKNOWN
else:
search_result.drm = SearchResult.DRM_LOCKED
return True

12
src/calibre/gui2/store/amazon_uk_plugin.py
View File

@ -15,17 +15,14 @@ from PyQt4.Qt import QUrl
from calibre import browser
from calibre.gui2 import open_url
from calibre.gui2.store.amazon_plugin import AmazonKindleStore
from calibre.gui2.store import StorePlugin
from calibre.gui2.store.search_result import SearchResult
class AmazonUKKindleStore(AmazonKindleStore):
class AmazonUKKindleStore(StorePlugin):
'''
For comments on the implementation, please see amazon_plugin.py
'''
search_url = 'http://www.amazon.co.uk/s/?url=search-alias%3Ddigital-text&field-keywords='
details_url = 'http://amazon.co.uk/dp/'
def open(self, parent=None, detail_item=None, external=False):
aff_id = {'tag': 'calcharles-21'}
store_link = 'http://www.amazon.co.uk/gp/redirect.html?ie=UTF8&location=http://www.amazon.co.uk/Kindle-eBooks/b?ie=UTF8&node=341689031&ref_=sa_menu_kbo2&tag=%(tag)s&linkCode=ur2&camp=1634&creative=19450' % aff_id
@ -36,7 +33,8 @@ class AmazonUKKindleStore(AmazonKindleStore):
open_url(QUrl(store_link))
def search(self, query, max_results=10, timeout=60):
url = self.search_url + urllib.quote_plus(query)
search_url = 'http://www.amazon.co.uk/s/?url=search-alias%3Ddigital-text&field-keywords='
url = search_url + urllib.quote_plus(query)
br = browser()
counter = max_results
@ -95,7 +93,7 @@ class AmazonUKKindleStore(AmazonKindleStore):
if search_result.drm:
return
url = self.details_url
url = 'http://amazon.co.uk/dp/'
br = browser()
with closing(br.open(url + search_result.detail_item, timeout=timeout)) as nf: