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

Fix encoding issues when searching and displaying results for Amazon plugins.

Browse Source
This commit is contained in:
John Schember 2011-10-09 10:54:19 -04:00
parent 6e4792a284
commit 7003ae2aa9
4 changed files with 11 additions and 47 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
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
@ -37,12 +36,12 @@ 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.

43
src/calibre/gui2/store/stores/amazon_fr_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
@ -34,12 +33,12 @@ class AmazonFRKindleStore(StorePlugin):
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 + 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'))
data_xpath = '//div[contains(@class, "result") and contains(@class, "product")]'
format_xpath = './/span[@class="format"]/text()'
@ -66,9 +65,7 @@ class AmazonFRKindleStore(StorePlugin):
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()')))
author = author.split('de ')[-1]
# print (author, asin, cover_url, title, price)
author = author.split('et ')[-1]
counter -= 1
@ -79,36 +76,6 @@ class AmazonFRKindleStore(StorePlugin):
s.price = price.strip()
s.detail_item = asin.strip()
s.formats = 'Kindle'
s.DRM = SearchResult.DRM_UNKNOWN
s.drm = SearchResult.DRM_UNKNOWN
yield s
def get_details(self, search_result, timeout):
# We might already have been called.
if search_result.drm:
return
url = 'http://amazon.fr/dp/'
drm_search_text = u'Simultaneous Device Usage'
drm_free_text = u'Unlimited'
br = browser()
with closing(br.open(url + search_result.detail_item, timeout=timeout)) as nf:
idata = html.fromstring(nf.read())
if not search_result.author:
search_result.author = ''.join(idata.xpath('//div[@class="buying" and contains(., "Author")]/a/text()'))
is_kindle = idata.xpath('boolean(//div[@class="buying"]/h1/span/span[contains(text(), "Kindle Edition")])')
if is_kindle:
search_result.formats = 'Kindle'
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

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"])')

5
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
@ -34,12 +33,12 @@ 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.