Get books: Update Barnes and Noble store plugin for website changes. Fixes #2023046 [Get Books unable to find book from ebooks.com](https://bugs.launchpad.net/calibre/+bug/2023046)

src/calibre/gui2/store/stores/bn_plugin.py

@@ -1,13 +1,12 @@
 # -*- coding: utf-8 -*-
 from __future__ import absolute_import, division, print_function, unicode_literals
 
-store_version = 2  # Needed for dynamic plugin loading
+store_version = 3  # Needed for dynamic plugin loading
 
 __license__ = 'GPL 3'
 __copyright__ = '2011, John Schember <john@nachtimwald.com>'
 __docformat__ = 'restructuredtext en'
 
-import re
 from contextlib import closing
 try:
     from urllib.parse import quote_plus
@@ -26,10 +25,70 @@ from calibre.gui2.store.search_result import SearchResult
 from calibre.gui2.store.web_store_dialog import WebStoreDialog
 
 
+
+def search_bn(query, max_results=10, timeout=60, write_html_to=''):
+    url = 'https://www.barnesandnoble.com/s/%s?keyword=%s&store=ebook&view=list' % (query.replace(' ', '-'), quote_plus(query))
+    url = 'file:///t/bn.html'
+
+    br = browser()
+
+    counter = max_results
+    with closing(br.open(url, timeout=timeout)) as f:
+        raw = f.read()
+        if write_html_to:
+            with open(write_html_to, 'wb') as f:
+                f.write(raw)
+        doc = html.fromstring(raw)
+        for data in doc.xpath('//section[@id="gridView"]//div[contains(@class, "product-shelf-tile-book")]'):
+            if counter <= 0:
+                break
+            counter -= 1
+
+            cover_url = ''
+            cover_div = data.xpath('.//div[contains(@class, "product-shelf-image")]')
+            if cover_div:
+                cover_url = 'https:' + ''.join(cover_div[0].xpath('descendant::img/@src'))
+
+            title_div = data.xpath('.//div[contains(@class, "product-shelf-title")]')
+            if not title_div:
+                continue
+            title = ''.join(title_div[0].xpath('descendant::a/text()')).strip()
+            if not title:
+                continue
+            item_url = ''.join(title_div[0].xpath('descendant::a/@href')).strip()
+            if not item_url:
+                continue
+            item_url = 'https://www.barnesandnoble.com' + item_url
+
+            author = ''
+            author_div = data.xpath('.//div[contains(@class, "product-shelf-author")]')
+            if author_div:
+                author = ''.join(author_div[0].xpath('descendant::a/text()')).strip()
+
+            price = ''
+            price_div = data.xpath('.//div[contains(@class, "product-shelf-pricing")]/div[contains(@class, "current")]')
+            if price_div:
+                spans = price_div[0].xpath('descendant::span')
+                if spans:
+                    price = ''.join(spans[-1].xpath('descendant::text()'))
+                    if '\n' in price:
+                        price = price.split('\n')[1].split(',')[0]
+
+            s = SearchResult()
+            s.cover_url = cover_url
+            s.title = title.strip()
+            s.author = author.strip()
+            s.price = price.strip()
+            s.detail_item = item_url.strip()
+            s.drm = SearchResult.DRM_UNKNOWN
+            s.formats = 'Nook'
+            yield s
+
+
 class BNStore(BasicStoreConfig, StorePlugin):
 
     def open(self, parent=None, detail_item=None, external=False):
-        url = "http://bn.com"
+        url = "https://bn.com"
 
         if external or self.config.get('open_external', False):
             open_url(QUrl(url_slash_cleaner(detail_item if detail_item else url)))
@@ -40,44 +99,10 @@ class BNStore(BasicStoreConfig, StorePlugin):
             d.exec()
 
     def search(self, query, max_results=10, timeout=60):
-        url = 'http://www.barnesandnoble.com/s/%s?keyword=%s&store=ebook&view=list' % (query.decode('utf-8').replace(' ', '-'), quote_plus(query))
+        yield from search_bn(query, max_results, timeout)
 
-        br = browser()
 
-        counter = max_results
+if __name__ == '__main__':
-        with closing(br.open(url, timeout=timeout)) as f:
+    import sys
-            raw = f.read()
+    for result in search_bn(' '.join(sys.argv[1:]), write_html_to='/t/bn.html'):
-            doc = html.fromstring(raw)
+        print(result)
-            for data in doc.xpath('//ol[contains(@class, "result-set")]/li[contains(@class, "result")]'):
-                if counter <= 0:
-                    break
-
-                id = ''.join(data.xpath('.//div[contains(@class, "image-block")]/a/@href'))
-                if not id:
-                    continue
-
-                cover_url = ''
-                cover_id = ''.join(data.xpath('.//img[contains(@class, "product-image")]/@id'))
-                m = re.search(r"%s'.*?srcUrl: '(?P<iurl>.*?)'.*?}" % cover_id, raw)
-                if m:
-                    cover_url = m.group('iurl')
-
-                title = ''.join(data.xpath('descendant::p[@class="title"]//span[@class="name"]//text()')).strip()
-                if not title:
-                    continue
-
-                author = ', '.join(data.xpath('.//ul[contains(@class, "contributors")]//a[contains(@class, "subtle")]//text()')).strip()
-                price = ''.join(data.xpath('.//a[contains(@class, "bn-price")]//text()'))
-
-                counter -= 1
-
-                s = SearchResult()
-                s.cover_url = cover_url
-                s.title = title.strip()
-                s.author = author.strip()
-                s.price = price.strip()
-                s.detail_item = id.strip()
-                s.drm = SearchResult.DRM_UNKNOWN
-                s.formats = 'Nook'
-
-                yield s