From 4fc67c81a4858d490d88a26e2c84f43b8a3983c8 Mon Sep 17 00:00:00 2001
From: josdion <josdion@users.noreply.github.com>
Date: Sun, 21 Feb 2021 12:55:40 +0200
Subject: [PATCH] Fix biblio store

Update html parser to be consistent with the current version of the site.
---
 .../gui2/store/stores/biblio_plugin.py        | 100 +++++++++++++-----
 1 file changed, 72 insertions(+), 28 deletions(-)

diff --git a/src/calibre/gui2/store/stores/biblio_plugin.py b/src/calibre/gui2/store/stores/biblio_plugin.py
index e43f64376e..fa2f874065 100644
--- a/src/calibre/gui2/store/stores/biblio_plugin.py
+++ b/src/calibre/gui2/store/stores/biblio_plugin.py
@@ -1,58 +1,102 @@
 # -*- coding: utf-8 -*-
 from __future__ import absolute_import, division, print_function, unicode_literals
 
-store_version = 1  # Needed for dynamic plugin loading
+store_version = 2  # Needed for dynamic plugin loading
 
 __license__ = 'GPL 3'
 __copyright__ = '2012, Alex Stanev <alex@stanev.org>'
 __docformat__ = 'restructuredtext en'
 
-import re
+try:
+    from urllib.parse import quote_plus
+except ImportError:
+    from urllib import quote_plus
 
+from calibre import browser
+from calibre.gui2 import open_url
 from calibre.gui2.store.basic_config import BasicStoreConfig
-from calibre.gui2.store.opensearch_store import OpenSearchOPDSStore
+from calibre.gui2.store import StorePlugin
 from calibre.gui2.store.search_result import SearchResult
+from calibre.gui2.store.web_store_dialog import WebStoreDialog
+from contextlib import closing
+from lxml import html
 
 
-class BiblioStore(BasicStoreConfig, OpenSearchOPDSStore):
+class BiblioStore(BasicStoreConfig, StorePlugin):
 
-    open_search_url = 'http://biblio.bg/feed.opds.php'
-    web_url = 'http://biblio.bg/'
+    web_url = 'https://biblio.bg'
+
+    def open(self, parent=None, detail_item=None, external=False):
+        if external or self.config.get('open_external', False):
+            open_url(detail_item)
+        else:
+            d = WebStoreDialog(self.gui, self.web_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):
-        # check for cyrillic symbols before performing search
         if isinstance(query, bytes):
             query = query.decode('utf-8')
-        uquery = query.strip()
-        reObj = re.search(u'^[а-яА-Я\\d\\s]{3,}$', uquery)
-        if not reObj:
+
+        if len(query) < 3:
             return
 
-        for s in OpenSearchOPDSStore.search(self, query, max_results, timeout):
-            yield s
+        # do keyword search
+        url = '{}/книги?query={}&search_by=0'.format(self.web_url, quote_plus(query))
+        yield from self._do_search(url, max_results, timeout)
+
 
     def get_details(self, search_result, timeout):
-        # get format and DRM status
-        from calibre import browser
-        from contextlib import closing
-        from lxml import html
-
         br = browser()
         with closing(br.open(search_result.detail_item, timeout=timeout)) as nf:
             idata = html.fromstring(nf.read())
             search_result.formats = ''
-            if idata.xpath('.//span[@class="format epub"]'):
-                search_result.formats = 'EPUB'
+            search_result.drm = SearchResult.DRM_LOCKED
 
-            if idata.xpath('.//span[@class="format pdf"]'):
-                if search_result.formats == '':
-                    search_result.formats = 'PDF'
-                else:
-                    search_result.formats.join(', PDF')
+            for option in idata.xpath('//ul[@class="order_product_options"]/li'):
+                option_type = option.text.strip() if option.text else ''
+                if option_type.startswith('Формат:'):
+                    search_result.formats = ''.join(option.xpath('.//b/text()')).strip()
+                if option_type.startswith('Защита:'):
+                    if ''.join(option.xpath('.//b/text()')).strip() == 'няма':
+                        search_result.drm = SearchResult.DRM_UNLOCKED
 
-            if idata.xpath('.//span[@class="format nodrm-icon"]'):
-                search_result.drm = SearchResult.DRM_UNLOCKED
-            else:
-                search_result.drm = SearchResult.DRM_LOCKED
+            if not search_result.author:
+                search_result.author = ', '.join(idata.xpath('//div[@class="row product_info"]/div/div/div[@class="item-author"]/a/text()')).strip(', ')
 
         return True
+
+
+    def _do_search(self, url, max_results, timeout):
+        br = browser()
+        with closing(br.open(url, timeout=timeout)) as f:
+            page = f.read().decode('utf-8')
+            doc = html.fromstring(page)
+
+            for data in doc.xpath('//ul[contains(@class,"book_list")]/li'):
+                if max_results <= 0:
+                    break
+
+                s = SearchResult()
+                s.detail_item = ''.join(data.xpath('.//a[@class="th"]/@href')).strip()
+                if not id:
+                    continue
+
+                s.cover_url = ''.join(data.xpath('.//a[@class="th"]/img/@data-original')).strip()
+                s.title = ''.join(data.xpath('.//div[@class="item-title"]/a/text()')).strip()
+                s.author = ', '.join(data.xpath('.//div[@class="item-author"]/a/text()')).strip(', ')
+
+                price_list = data.xpath('.//div[@class="item-price"]')
+                for price_item in price_list:
+                    if price_item.text.startswith('е-книга:'):
+                        s.price = ''.join(price_item.xpath('.//span/text()'))
+                        break
+
+                s.price = '0.00 лв.' if not s.price and not price_list else s.price
+                if not s.price:
+                    # no e-book available
+                    continue
+
+                max_results -= 1
+                yield s