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

remove Gandalf store - new web page makes harvesting data almost imposible

Browse Source
This commit is contained in:
Tomasz Długosz 2012-11-21 22:31:30 +01:00
parent b9599df708
commit 3ee7612a7d
2 changed files with 0 additions and 92 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
src/calibre/customize/builtins.py
View File

@ -1433,15 +1433,6 @@ class StoreFoylesUKStore(StoreBase):
formats = ['EPUB', 'PDF']
affiliate = True
class StoreGandalfStore(StoreBase):
name = 'Gandalf'
author = u'Tomasz Długosz'
description = u'Księgarnia internetowa Gandalf.'
actual_plugin = 'calibre.gui2.store.stores.gandalf_plugin:GandalfStore'
headquarters = 'PL'
formats = ['EPUB', 'PDF']
class StoreGoogleBooksStore(StoreBase):
name = 'Google Books'
description = u'Google Books'
@ -1684,7 +1675,6 @@ plugins += [
StoreEscapeMagazineStore,
StoreFeedbooksStore,
StoreFoylesUKStore,
StoreGandalfStore,
StoreGoogleBooksStore,
StoreGutenbergStore,
StoreKoboStore,

82
src/calibre/gui2/store/stores/gandalf_plugin.py
View File

@ -1,82 +0,0 @@
# -*- coding: utf-8 -*-
from __future__ import (unicode_literals, division, absolute_import, print_function)
__license__ = 'GPL 3'
__copyright__ = '2011-2012, Tomasz Długosz <tomek3d@gmail.com>'
__docformat__ = 'restructuredtext en'
import re
import urllib
from contextlib import closing
from lxml import html
from PyQt4.Qt import QUrl
from calibre import browser, url_slash_cleaner
from calibre.gui2 import open_url
from calibre.gui2.store import StorePlugin
from calibre.gui2.store.basic_config import BasicStoreConfig
from calibre.gui2.store.search_result import SearchResult
from calibre.gui2.store.web_store_dialog import WebStoreDialog
class GandalfStore(BasicStoreConfig, StorePlugin):
def open(self, parent=None, detail_item=None, external=False):
url = 'http://www.gandalf.com.pl/ebooks/'
if external or self.config.get('open_external', False):
open_url(QUrl(url_slash_cleaner(detail_item if detail_item else url)))
else:
d = WebStoreDialog(self.gui, url, parent, detail_item)
d.setWindowTitle(self.name)
d.set_tags(self.config.get('tags', ''))
d.exec_()
def search(self, query, max_results=10, timeout=60):
counter = max_results
page = 1
url = 'http://www.gandalf.com.pl/we/' + urllib.quote_plus(query.decode('utf-8').encode('iso8859_2')) + '/bdb'
br = browser()
while counter:
with closing(br.open((url + str(page-1) + '/#s') if (page-1) else (url + '/#s'), timeout=timeout)) as f:
doc = html.fromstring(f.read())
for data in doc.xpath('//div[@class="box"]'):
if counter <= 0:
break
id = ''.join(data.xpath('.//div[@class="info"]/h3/a/@href'))
if not id:
continue
cover_url = ''.join(data.xpath('.//div[@class="info"]/h3/a/@id'))
title = ''.join(data.xpath('.//div[@class="info"]/h3/a/@title'))
formats = ''.join(data.xpath('.//div[@class="info"]/p[1]/text()'))
formats = re.findall(r'\((.*?)\)',formats)[0]
author = ''.join(data.xpath('.//div[@class="info"]/h4/text() | .//div[@class="info"]/h4/span/text()'))
price = ''.join(data.xpath('.//div[@class="options"]/h3/text()'))
price = re.sub('PLN', 'zł', price)
price = re.sub('\.', ',', price)
drm = data.xpath('boolean(.//div[@class="info" and contains(., "Zabezpieczenie: DRM")])')
counter -= 1
s = SearchResult()
s.cover_url = 'http://imguser.gandalf.com.pl/' + re.sub('p', 'p_', cover_url) + '.jpg'
s.title = title.strip()
s.author = author.strip()
s.price = price
s.detail_item = id.strip()
if drm:
s.drm = SearchResult.DRM_LOCKED
else:
s.drm = SearchResult.DRM_UNLOCKED
s.formats = formats.upper().strip()
yield s
if not doc.xpath('boolean(//div[@class="wyszukiwanie_podstawowe_header"]//div[@class="box"])'):
break
page+=1