mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-08 10:44:09 -04:00
"Close" Amazon.FR and Amazon.DE. Amazon forcibly closed these two affiliate accounts, demanding that "all links toward Amazon content be removed".
This commit is contained in:
Charles Haley
parent
26cff461eb
commit
80b3a8ae41
@ -1288,6 +1288,8 @@ class StoreAmazonCAKindleStore(StoreBase):
|
||||
formats = ['KINDLE']
|
||||
# affiliate = True
|
||||
|
||||
# Remove this plugin definition in Jan 2016 because of Amazon demand. We leave
|
||||
# it here until then so users have a chance to see wny the store is gone.
|
||||
class StoreAmazonDEKindleStore(StoreBase):
|
||||
name = 'Amazon DE Kindle'
|
||||
author = 'Charles Haley'
|
||||
@ -1298,6 +1300,8 @@ class StoreAmazonDEKindleStore(StoreBase):
|
||||
formats = ['KINDLE']
|
||||
affiliate = True
|
||||
|
||||
# Remove this plugin definition in Jan 2016 because of Amazon demand. We leave
|
||||
# it here until then so users have a chance to see wny the store is gone.
|
||||
class StoreAmazonFRKindleStore(StoreBase):
|
||||
name = 'Amazon FR Kindle'
|
||||
author = 'Charles Haley'
|
||||
|
||||
@ -1,171 +1,35 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
from __future__ import (unicode_literals, division, absolute_import, print_function)
|
||||
store_version = 8 # Needed for dynamic plugin loading
|
||||
store_version = 9 # Needed for dynamic plugin loading
|
||||
|
||||
__license__ = 'GPL 3'
|
||||
__copyright__ = '2011, John Schember <john@nachtimwald.com>'
|
||||
__docformat__ = 'restructuredtext en'
|
||||
|
||||
import re
|
||||
from contextlib import closing
|
||||
from lxml import html
|
||||
|
||||
from PyQt5.Qt import QUrl
|
||||
|
||||
from calibre.gui2.store import StorePlugin
|
||||
from calibre import browser
|
||||
from calibre.gui2 import open_url
|
||||
from calibre.gui2.store.search_result import SearchResult
|
||||
|
||||
class AmazonDEKindleStore(StorePlugin):
|
||||
'''
|
||||
For comments on the implementation, please see amazon_plugin.py
|
||||
Amazon forcibly closed the affiliate account, requesting that "all links
|
||||
toward Amazon content be removed".
|
||||
'''
|
||||
|
||||
aff_id = {'tag': 'charhale0a-21'}
|
||||
store_link = ('http://www.amazon.de/gp/redirect.html?ie=UTF8&site-redirect=de'
|
||||
'&tag=%(tag)s&linkCode=ur2&camp=1638&creative=19454'
|
||||
'&location=http://www.amazon.de/ebooks-kindle/b?node=530886031')
|
||||
store_link_details = ('http://www.amazon.de/gp/redirect.html?ie=UTF8'
|
||||
'&location=http://www.amazon.de/dp/%(asin)s&site-redirect=de'
|
||||
'&tag=%(tag)s&linkCode=ur2&camp=1638&creative=6742')
|
||||
search_url = 'http://www.amazon.de/s/?url=search-alias%3Ddigital-text&field-keywords='
|
||||
|
||||
author_article = 'von '
|
||||
|
||||
and_word = ' und '
|
||||
|
||||
# ---- Copy from here to end
|
||||
|
||||
'''
|
||||
For comments on the implementation, please see amazon_plugin.py
|
||||
'''
|
||||
def genesis(self):
|
||||
StorePlugin.genesis(self)
|
||||
from calibre.customize.ui import find_plugin
|
||||
pi = find_plugin('Amazon DE Kindle')
|
||||
pi.affiliate = False
|
||||
|
||||
def open(self, parent=None, detail_item=None, external=False):
|
||||
|
||||
store_link = self.store_link % self.aff_id
|
||||
if detail_item:
|
||||
self.aff_id['asin'] = detail_item
|
||||
store_link = self.store_link_details % self.aff_id
|
||||
open_url(QUrl(store_link))
|
||||
pass
|
||||
|
||||
def search(self, query, max_results=10, timeout=60):
|
||||
url = self.search_url + query.encode('ascii', 'backslashreplace').replace('%', '%25').replace('\\x', '%').replace(' ', '+')
|
||||
br = browser()
|
||||
|
||||
counter = max_results
|
||||
with closing(br.open(url, timeout=timeout)) as f:
|
||||
allText = f.read()
|
||||
doc = html.fromstring(allText)#.decode('latin-1', 'replace'))
|
||||
|
||||
format_xpath2 = ''
|
||||
if doc.xpath('//div[@id = "atfResults" and contains(@class, "grid")]'):
|
||||
#print('grid form')
|
||||
data_xpath = '//div[contains(@class, "prod")]'
|
||||
format_xpath = (
|
||||
'.//ul[contains(@class, "rsltGridList")]'
|
||||
'//span[contains(@class, "lrg") and not(contains(@class, "bld"))]/text()')
|
||||
asin_xpath = '@name'
|
||||
cover_xpath = './/img[contains(@class, "productImage")]/@src'
|
||||
title_xpath = './/h3[@class="newaps"]/a//text()'
|
||||
author_xpath = './/h3[@class="newaps"]//span[contains(@class, "reg")]//text()'
|
||||
price_xpath = (
|
||||
'.//ul[contains(@class, "rsltGridList")]'
|
||||
'//span[contains(@class, "lrg") and contains(@class, "bld")]/text()')
|
||||
elif doc.xpath('//div[@id = "atfResults" and contains(@class, "ilresults")]'):
|
||||
#print('ilo form')
|
||||
data_xpath = '//li[(@class="ilo")]'
|
||||
format_xpath = (
|
||||
'.//ul[contains(@class, "rsltGridList")]'
|
||||
'//span[contains(@class, "lrg") and not(contains(@class, "bld"))]/text()')
|
||||
asin_xpath = '@name'
|
||||
cover_xpath = './div[@class = "ilf"]/a/img[contains(@class, "ilo")]/@src'
|
||||
title_xpath = './/h3[@class="newaps"]/a//text()'
|
||||
author_xpath = './/h3[@class="newaps"]//span[contains(@class, "reg")]//text()'
|
||||
# Results can be in a grid (table) or a column
|
||||
price_xpath = (
|
||||
'.//ul[contains(@class, "rsltL") or contains(@class, "rsltGridList")]'
|
||||
'//span[contains(@class, "lrg") and contains(@class, "bld")]/text()')
|
||||
elif doc.xpath('//div[@id = "atfResults" and contains(@class, "s-result-list-parent-container")]'):
|
||||
#print('new list form')
|
||||
data_xpath = '//li[contains(@class, "s-result-item")]'
|
||||
format_xpath = './/a[contains(@class, "a-size-small")]/text()'
|
||||
format_xpath2 = './/h3[contains(@class, "s-inline")]/text()'
|
||||
asin_xpath = '@data-asin'
|
||||
cover_xpath = './/img[contains(@class, "cfMarker")]/@src'
|
||||
title_xpath = './/h2[contains(@class, "s-access-title")]/text()'
|
||||
author_xpath = ('.//div[contains(@class, "a-fixed-left-grid-col")]'
|
||||
'/div/div/span//text()')
|
||||
price_xpath = ('.//div[contains(@class, "a-spacing-none")]/a/span[contains(@class, "s-price")]/text()')
|
||||
elif doc.xpath('//div[@id = "atfResults" and contains(@class, "list")]'):
|
||||
#print('list form')
|
||||
data_xpath = '//li[@class="s-result-item"]'
|
||||
format_xpath = './/a[contains(@class, "a-size-small")]/text()'
|
||||
format_xpath2 = './/h3[contains(@class, "s-inline")]/text()'
|
||||
asin_xpath = '@data-asin'
|
||||
cover_xpath = './/img[contains(@class, "cfMarker")]/@src'
|
||||
title_xpath = './/h2[contains(@class, "s-access-title")]/text()'
|
||||
author_xpath = ('.//div[contains(@class, "a-fixed-left-grid-col")]'
|
||||
'/div/div/span//text()')
|
||||
price_xpath = ('.//span[contains(@class, "s-price")]/text()')
|
||||
else:
|
||||
# URK -- whats this?
|
||||
print('unknown result table form for Amazon EU search')
|
||||
#with open("c:/amazon_search_results.html", "w") as out:
|
||||
# out.write(allText)
|
||||
return
|
||||
|
||||
|
||||
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 (authors 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():
|
||||
if format_xpath2:
|
||||
format_ = ''.join(data.xpath(format_xpath2))
|
||||
if 'kindle' not in format_.lower():
|
||||
# print(etree.tostring(data, pretty_print=True))
|
||||
continue
|
||||
|
||||
# We must have an asin otherwise we can't easily reference the
|
||||
# book later.
|
||||
asin = data.xpath(asin_xpath)
|
||||
if asin:
|
||||
asin = asin[0]
|
||||
else:
|
||||
continue
|
||||
|
||||
cover_url = ''.join(data.xpath(cover_xpath))
|
||||
|
||||
title = ''.join(data.xpath(title_xpath))
|
||||
|
||||
authors = ''.join(data.xpath(author_xpath))
|
||||
authors = re.sub('^' + self.author_article, '', authors)
|
||||
authors = re.sub(self.and_word, ' & ', authors)
|
||||
mo = re.match(r'(.*)(\(\d.*)$', authors)
|
||||
if mo:
|
||||
authors = mo.group(1).strip()
|
||||
|
||||
price = ''.join(data.xpath(price_xpath)[-1])
|
||||
|
||||
counter -= 1
|
||||
|
||||
s = SearchResult()
|
||||
s.cover_url = cover_url.strip()
|
||||
s.title = title.strip()
|
||||
s.author = authors.strip()
|
||||
s.price = price.strip()
|
||||
s.detail_item = asin.strip()
|
||||
s.drm = SearchResult.DRM_UNKNOWN
|
||||
s.formats = 'Kindle'
|
||||
|
||||
yield s
|
||||
s = SearchResult()
|
||||
s.title = 'Amazon demanded that this<br>store be permanently closed.'
|
||||
s.author = None
|
||||
yield s
|
||||
|
||||
def get_details(self, search_result, timeout):
|
||||
pass
|
||||
pass
|
||||
@ -1,167 +1,35 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
from __future__ import (unicode_literals, division, absolute_import, print_function)
|
||||
store_version = 8 # Needed for dynamic plugin loading
|
||||
store_version = 9 # Needed for dynamic plugin loading
|
||||
|
||||
__license__ = 'GPL 3'
|
||||
__copyright__ = '2011, John Schember <john@nachtimwald.com>'
|
||||
__docformat__ = 'restructuredtext en'
|
||||
|
||||
import re
|
||||
from contextlib import closing
|
||||
from lxml import html
|
||||
|
||||
from PyQt5.Qt import QUrl
|
||||
|
||||
from calibre.gui2.store import StorePlugin
|
||||
from calibre import browser
|
||||
from calibre.gui2 import open_url
|
||||
from calibre.gui2.store.search_result import SearchResult
|
||||
|
||||
class AmazonFRKindleStore(StorePlugin):
|
||||
'''
|
||||
For comments on the implementation, please see amazon_plugin.py
|
||||
Amazon forcibly closed the affiliate account, requesting that "all links
|
||||
toward Amazon content be removed".
|
||||
'''
|
||||
|
||||
aff_id = {'tag': 'charhale-21'}
|
||||
store_link = 'http://www.amazon.fr/livres-kindle/b?ie=UTF8&node=695398031&ref_=sa_menu_kbo1&_encoding=UTF8&tag=%(tag)s&linkCode=ur2&camp=1642&creative=19458' % aff_id
|
||||
store_link_details = 'http://www.amazon.fr/gp/redirect.html?ie=UTF8&location=http://www.amazon.fr/dp/%(asin)s&tag=%(tag)s&linkCode=ur2&camp=1634&creative=6738'
|
||||
search_url = 'http://www.amazon.fr/s/?url=search-alias%3Ddigital-text&field-keywords='
|
||||
|
||||
author_article = 'de '
|
||||
|
||||
and_word = ' et '
|
||||
|
||||
# ---- Copy from here to end
|
||||
|
||||
'''
|
||||
For comments on the implementation, please see amazon_plugin.py
|
||||
'''
|
||||
def genesis(self):
|
||||
StorePlugin.genesis(self)
|
||||
from calibre.customize.ui import find_plugin
|
||||
pi = find_plugin('Amazon FR Kindle')
|
||||
pi.affiliate = False
|
||||
|
||||
def open(self, parent=None, detail_item=None, external=False):
|
||||
|
||||
store_link = self.store_link % self.aff_id
|
||||
if detail_item:
|
||||
self.aff_id['asin'] = detail_item
|
||||
store_link = self.store_link_details % self.aff_id
|
||||
open_url(QUrl(store_link))
|
||||
pass
|
||||
|
||||
def search(self, query, max_results=10, timeout=60):
|
||||
url = self.search_url + query.encode('ascii', 'backslashreplace').replace('%', '%25').replace('\\x', '%').replace(' ', '+')
|
||||
br = browser()
|
||||
|
||||
counter = max_results
|
||||
with closing(br.open(url, timeout=timeout)) as f:
|
||||
allText = f.read()
|
||||
doc = html.fromstring(allText)#.decode('latin-1', 'replace'))
|
||||
|
||||
format_xpath2 = ''
|
||||
if doc.xpath('//div[@id = "atfResults" and contains(@class, "grid")]'):
|
||||
#print('grid form')
|
||||
data_xpath = '//div[contains(@class, "prod")]'
|
||||
format_xpath = (
|
||||
'.//ul[contains(@class, "rsltGridList")]'
|
||||
'//span[contains(@class, "lrg") and not(contains(@class, "bld"))]/text()')
|
||||
asin_xpath = '@name'
|
||||
cover_xpath = './/img[contains(@class, "productImage")]/@src'
|
||||
title_xpath = './/h3[@class="newaps"]/a//text()'
|
||||
author_xpath = './/h3[@class="newaps"]//span[contains(@class, "reg")]//text()'
|
||||
price_xpath = (
|
||||
'.//ul[contains(@class, "rsltGridList")]'
|
||||
'//span[contains(@class, "lrg") and contains(@class, "bld")]/text()')
|
||||
elif doc.xpath('//div[@id = "atfResults" and contains(@class, "ilresults")]'):
|
||||
#print('ilo form')
|
||||
data_xpath = '//li[(@class="ilo")]'
|
||||
format_xpath = (
|
||||
'.//ul[contains(@class, "rsltGridList")]'
|
||||
'//span[contains(@class, "lrg") and not(contains(@class, "bld"))]/text()')
|
||||
asin_xpath = '@name'
|
||||
cover_xpath = './div[@class = "ilf"]/a/img[contains(@class, "ilo")]/@src'
|
||||
title_xpath = './/h3[@class="newaps"]/a//text()'
|
||||
author_xpath = './/h3[@class="newaps"]//span[contains(@class, "reg")]//text()'
|
||||
# Results can be in a grid (table) or a column
|
||||
price_xpath = (
|
||||
'.//ul[contains(@class, "rsltL") or contains(@class, "rsltGridList")]'
|
||||
'//span[contains(@class, "lrg") and contains(@class, "bld")]/text()')
|
||||
elif doc.xpath('//div[@id = "atfResults" and contains(@class, "s-result-list-parent-container")]'):
|
||||
#print('new list form')
|
||||
data_xpath = '//li[contains(@class, "s-result-item")]'
|
||||
format_xpath = './/a[contains(@class, "a-size-small")]/text()'
|
||||
format_xpath2 = './/h3[contains(@class, "s-inline")]/text()'
|
||||
asin_xpath = '@data-asin'
|
||||
cover_xpath = './/img[contains(@class, "cfMarker")]/@src'
|
||||
title_xpath = './/h2[contains(@class, "s-access-title")]/text()'
|
||||
author_xpath = ('.//div[contains(@class, "a-fixed-left-grid-col")]'
|
||||
'/div/div/span//text()')
|
||||
price_xpath = ('.//div[contains(@class, "a-spacing-none")]/a/span[contains(@class, "s-price")]/text()')
|
||||
elif doc.xpath('//div[@id = "atfResults" and contains(@class, "list")]'):
|
||||
#print('list form')
|
||||
data_xpath = '//li[@class="s-result-item"]'
|
||||
format_xpath = './/a[contains(@class, "a-size-small")]/text()'
|
||||
format_xpath2 = './/h3[contains(@class, "s-inline")]/text()'
|
||||
asin_xpath = '@data-asin'
|
||||
cover_xpath = './/img[contains(@class, "cfMarker")]/@src'
|
||||
title_xpath = './/h2[contains(@class, "s-access-title")]/text()'
|
||||
author_xpath = ('.//div[contains(@class, "a-fixed-left-grid-col")]'
|
||||
'/div/div/span//text()')
|
||||
price_xpath = ('.//span[contains(@class, "s-price")]/text()')
|
||||
else:
|
||||
# URK -- whats this?
|
||||
print('unknown result table form for Amazon EU search')
|
||||
#with open("c:/amazon_search_results.html", "w") as out:
|
||||
# out.write(allText)
|
||||
return
|
||||
|
||||
|
||||
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 (authors 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():
|
||||
if format_xpath2:
|
||||
format_ = ''.join(data.xpath(format_xpath2))
|
||||
if 'kindle' not in format_.lower():
|
||||
# print(etree.tostring(data, pretty_print=True))
|
||||
continue
|
||||
|
||||
# We must have an asin otherwise we can't easily reference the
|
||||
# book later.
|
||||
asin = data.xpath(asin_xpath)
|
||||
if asin:
|
||||
asin = asin[0]
|
||||
else:
|
||||
continue
|
||||
|
||||
cover_url = ''.join(data.xpath(cover_xpath))
|
||||
|
||||
title = ''.join(data.xpath(title_xpath))
|
||||
|
||||
authors = ''.join(data.xpath(author_xpath))
|
||||
authors = re.sub('^' + self.author_article, '', authors)
|
||||
authors = re.sub(self.and_word, ' & ', authors)
|
||||
mo = re.match(r'(.*)(\(\d.*)$', authors)
|
||||
if mo:
|
||||
authors = mo.group(1).strip()
|
||||
|
||||
price = ''.join(data.xpath(price_xpath)[-1])
|
||||
|
||||
counter -= 1
|
||||
|
||||
s = SearchResult()
|
||||
s.cover_url = cover_url.strip()
|
||||
s.title = title.strip()
|
||||
s.author = authors.strip()
|
||||
s.price = price.strip()
|
||||
s.detail_item = asin.strip()
|
||||
s.drm = SearchResult.DRM_UNKNOWN
|
||||
s.formats = 'Kindle'
|
||||
|
||||
yield s
|
||||
s = SearchResult()
|
||||
s.title = 'Amazon demanded that this<br>store be permanently closed.'
|
||||
s.author = None
|
||||
yield s
|
||||
|
||||
def get_details(self, search_result, timeout):
|
||||
pass
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user