Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-06-23 15:30:45 -04:00
Code Issues Packages Projects Releases Wiki Activity

Get Books: Add the amazon.fr store. Remove leading 'by' from author names. Fix encoding issues with non English titles/names

Browse Source
This commit is contained in:
Kovid Goyal 2011-10-11 04:23:56 +05:30
commit c579764ce7
5 changed files with 103 additions and 39 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
src/calibre/customize/builtins.py
View File

@ -1144,6 +1144,16 @@ class StoreAmazonDEKindleStore(StoreBase):
formats = ['KINDLE']
affiliate = True
class StoreAmazonFRKindleStore(StoreBase):
name = 'Amazon FR Kindle'
author = 'Charles Haley'
description = u'Tous les ebooks Kindle'
actual_plugin = 'calibre.gui2.store.stores.amazon_fr_plugin:AmazonFRKindleStore'
headquarters = 'DE'
formats = ['KINDLE']
affiliate = True
class StoreAmazonUKKindleStore(StoreBase):
name = 'Amazon UK Kindle'
author = 'Charles Haley'
@ -1521,6 +1531,7 @@ plugins += [
StoreArchiveOrgStore,
StoreAmazonKindleStore,
StoreAmazonDEKindleStore,
StoreAmazonFRKindleStore,
StoreAmazonUKKindleStore,
StoreBaenWebScriptionStore,
StoreBNStore,

22
src/calibre/gui2/store/stores/amazon_de_plugin.py
View File

@ -6,7 +6,6 @@ __license__ = 'GPL 3'
__copyright__ = '2011, John Schember <john@nachtimwald.com>'
__docformat__ = 'restructuredtext en'
import urllib
from contextlib import closing
from lxml import html
@ -37,27 +36,16 @@ class AmazonDEKindleStore(StorePlugin):
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)
url = 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:
doc = html.fromstring(f.read())
doc = html.fromstring(f.read().decode('latin-1', 'replace'))
# Amazon has two results pages.
# 20110725: seems that is_shot is gone.
# 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[contains(@class, "result") and contains(@class, "product")]'
format_xpath = './/span[@class="format"]/text()'
cover_xpath = './/img[@class="productImage"]/@src'
# end is_shot else
for data in doc.xpath(data_xpath):
if counter <= 0:
@ -80,11 +68,9 @@ class AmazonDEKindleStore(StorePlugin):
title = ''.join(data.xpath('.//div[@class="title"]/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="title"]/span[@class="ptBrand"]/text()'))
author = author.split('von ')[-1]
if author.startswith('von '):
author = author[4:]
counter -= 1

82
src/calibre/gui2/store/stores/amazon_fr_plugin.py Normal file
View File

@ -0,0 +1,82 @@
# -*- coding: utf-8 -*-
from __future__ import (unicode_literals, division, absolute_import, print_function)
__license__ = 'GPL 3'
__copyright__ = '2011, John Schember <john@nachtimwald.com>'
__docformat__ = 'restructuredtext en'
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 import StorePlugin
from calibre.gui2.store.search_result import SearchResult
class AmazonFRKindleStore(StorePlugin):
'''
For comments on the implementation, please see amazon_plugin.py
'''
def open(self, parent=None, detail_item=None, external=False):
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
if detail_item:
aff_id['asin'] = detail_item
store_link = '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' % aff_id
open_url(QUrl(store_link))
def search(self, query, max_results=10, timeout=60):
search_url = 'http://www.amazon.fr/s/?url=search-alias%3Ddigital-text&field-keywords='
url = 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:
doc = html.fromstring(f.read().decode('latin-1', 'replace'))
data_xpath = '//div[contains(@class, "result") and contains(@class, "product")]'
format_xpath = './/span[@class="format"]/text()'
cover_xpath = './/img[@class="productImage"]/@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). So 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 = ''.join(data.xpath("@name"))
cover_url = ''.join(data.xpath(cover_xpath))
title = ''.join(data.xpath('.//div[@class="title"]/a/text()'))
price = ''.join(data.xpath('.//div[@class="newPrice"]/span/text()'))
author = unicode(''.join(data.xpath('.//div[@class="title"]/span[@class="ptBrand"]/text()')))
if author.startswith('de '):
author = author[3:]
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'
s.drm = SearchResult.DRM_UNKNOWN
yield s

5
src/calibre/gui2/store/stores/amazon_plugin.py
View File

@ -8,7 +8,6 @@ __docformat__ = 'restructuredtext en'
import random
import re
import urllib
from contextlib import closing
from lxml import html
@ -122,12 +121,12 @@ class AmazonKindleStore(StorePlugin):
open_url(QUrl(store_link))
def search(self, query, max_results=10, timeout=60):
url = self.search_url + urllib.quote_plus(query)
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:
doc = html.fromstring(f.read())
doc = html.fromstring(f.read().decode('latin-1', 'replace'))
# Amazon has two results pages.
is_shot = doc.xpath('boolean(//div[@id="shotgunMainResults"])')

22
src/calibre/gui2/store/stores/amazon_uk_plugin.py
View File

@ -6,7 +6,6 @@ __license__ = 'GPL 3'
__copyright__ = '2011, John Schember <john@nachtimwald.com>'
__docformat__ = 'restructuredtext en'
import urllib
from contextlib import closing
from lxml import html
@ -34,27 +33,16 @@ class AmazonUKKindleStore(StorePlugin):
def search(self, query, max_results=10, timeout=60):
search_url = 'http://www.amazon.co.uk/s/?url=search-alias%3Ddigital-text&field-keywords='
url = search_url + urllib.quote_plus(query)
url = 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:
doc = html.fromstring(f.read())
doc = html.fromstring(f.read().decode('latin-1', 'replace'))
# Amazon has two results pages.
# 20110725: seems that is_shot is gone.
# 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[contains(@class, "result") and contains(@class, "product")]'
format_xpath = './/span[@class="format"]/text()'
cover_xpath = './/img[@class="productImage"]/@src'
# end is_shot else
for data in doc.xpath(data_xpath):
if counter <= 0:
@ -77,11 +65,9 @@ class AmazonUKKindleStore(StorePlugin):
title = ''.join(data.xpath('.//div[@class="title"]/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="title"]/span[@class="ptBrand"]/text()'))
author = author.split('by ')[-1]
if author.startswith('by '):
author = author[3:]
counter -= 1