From 8632be2b8c572e6f139b2eae7b46989b5f0b4da6 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Tomasz=20D=C5=82ugosz?= <tomek3d@gmail.com>
Date: Thu, 8 May 2014 21:50:42 +0200
Subject: [PATCH] Update Woblink - rewrite plugin to use js enabled browser

---
 .../gui2/store/stores/woblink_plugin.py       | 82 +++++++++++--------
 1 file changed, 49 insertions(+), 33 deletions(-)

diff --git a/src/calibre/gui2/store/stores/woblink_plugin.py b/src/calibre/gui2/store/stores/woblink_plugin.py
index 59d7987a62..66ddbc149f 100644
--- a/src/calibre/gui2/store/stores/woblink_plugin.py
+++ b/src/calibre/gui2/store/stores/woblink_plugin.py
@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 
 from __future__ import (unicode_literals, division, absolute_import, print_function)
-store_version = 7  # Needed for dynamic plugin loading
+store_version = 8  # Needed for dynamic plugin loading
 
 __license__ = 'GPL 3'
 __copyright__ = '2011-2014, Tomasz Długosz <tomek3d@gmail.com>'
@@ -16,13 +16,27 @@ from lxml import html
 
 from PyQt4.Qt import QUrl
 
-from calibre import browser, url_slash_cleaner
+from calibre import 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
 
+from calibre.ebooks.chardet import xml_to_unicode
+from calibre.utils.ipc.simple_worker import fork_job, WorkerError
+
+js_browser = '''
+from calibre.web.jsbrowser.browser import Browser, Timeout
+import urllib
+
+def get_results(url, timeout):
+    browser = Browser(default_timeout=timeout)
+    browser.visit(url)
+    browser.wait_for_element('#nw_content_list')
+    return browser.html
+    '''
+
 class WoblinkStore(BasicStoreConfig, StorePlugin):
 
     def open(self, parent=None, detail_item=None, external=False):
@@ -43,6 +57,7 @@ class WoblinkStore(BasicStoreConfig, StorePlugin):
             d.set_tags(self.config.get('tags', ''))
             d.exec_()
 
+
     def search(self, query, max_results=10, timeout=60):
         url = 'http://woblink.com/katalog-ebooki?query=' + urllib.quote_plus(query.encode('utf-8'))
         if max_results > 10:
@@ -51,42 +66,43 @@ class WoblinkStore(BasicStoreConfig, StorePlugin):
             else:
                 url += '&limit=20'
 
-        br = browser()
-
         counter = max_results
-        with closing(br.open(url, timeout=timeout)) as f:
-            doc = html.fromstring(f.read())
-            for data in doc.xpath('//div[@class="nw_katalog_lista_ksiazka "]'):
-                if counter <= 0:
-                    break
 
-                id = ''.join(data.xpath('.//div[@class="nw_katalog_lista_ksiazka_okladka nw_okladka"]/a[1]/@href'))
-                if not id:
-                    continue
+        try:
+          results = fork_job(js_browser,'get_results', (url, timeout,), module_is_source_code=True)
+        except WorkerError as e:
+          raise Exception('Could not get results: %s'%e.orig_tb)
+        doc = html.fromstring(xml_to_unicode(str(results['result']),strip_encoding_pats=True)[0])
+        for data in doc.xpath('//div[@class="nw_katalog_lista_ksiazka"]'):
+            if counter <= 0:
+                break
 
-                cover_url = ''.join(data.xpath('.//div[@class="nw_katalog_lista_ksiazka_okladka nw_okladka"]/a[1]/img/@src'))
-                title = ''.join(data.xpath('.//h2[@class="nw_katalog_lista_ksiazka_detale_tytul"]/a[1]/text()'))
-                author = ', '.join(data.xpath('.//p[@class="nw_katalog_lista_ksiazka_detale_autor"]/a/text()'))
-                price = ''.join(data.xpath('.//div[@class="nw_katalog_lista_ksiazka_opcjezakupu_cena"]/span/text()'))
-                price = re.sub('\.', ',', price)
-                formats = ', '.join(data.xpath('.//p[@class="nw_katalog_lista_ksiazka_detale_formaty"]/span/text()'))
+            id = ''.join(data.xpath('.//div[@class="nw_katalog_lista_ksiazka_okladka nw_okladka"]/a[1]/@href'))
+            if not id:
+                continue
 
-                s = SearchResult()
-                s.cover_url = 'http://woblink.com' + cover_url
-                s.title = title.strip()
-                s.author = author.strip()
-                s.price = price + ' zł'
-                s.detail_item = id.strip()
-                s.formats = formats
+            cover_url = ''.join(data.xpath('.//div[@class="nw_katalog_lista_ksiazka_okladka nw_okladka"]/a[1]/img/@src'))
+            title = ''.join(data.xpath('.//h2[@class="nw_katalog_lista_ksiazka_detale_tytul"]/a[1]/text()'))
+            author = ', '.join(data.xpath('.//p[@class="nw_katalog_lista_ksiazka_detale_autor"]/a/text()'))
+            price = ''.join(data.xpath('.//div[@class="nw_opcjezakupu_cena"]/text()'))
+            formats = ', '.join(data.xpath('.//p[@class="nw_katalog_lista_ksiazka_detale_format"]/span/text()'))
 
-                if 'EPUB DRM' in formats:
-                    s.drm = SearchResult.DRM_LOCKED
+            s = SearchResult()
+            s.cover_url = 'http://woblink.com' + cover_url
+            s.title = title.strip()
+            s.author = author.strip()
+            s.price = price + ' zł'
+            s.detail_item = id.strip()
+            s.formats = formats
 
-                    counter -= 1
-                    yield s
-                else:
-                    s.drm = SearchResult.DRM_UNLOCKED
+            if 'DRM' in formats:
+                s.drm = SearchResult.DRM_LOCKED
 
-                    counter -= 1
-                    yield s
+                counter -= 1
+                yield s
+            else:
+                s.drm = SearchResult.DRM_UNLOCKED
+
+                counter -= 1
+                yield s