Get Books: Update Baen store plugin for website changes

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

@@ -1,21 +1,21 @@
 # -*- coding: utf-8 -*-
 
 from __future__ import (unicode_literals, division, absolute_import, print_function)
-store_version = 1  # Needed for dynamic plugin loading
+store_version = 2  # Needed for dynamic plugin loading
 
 __license__ = 'GPL 3'
 __copyright__ = '2011, John Schember <john@nachtimwald.com>'
 __docformat__ = 'restructuredtext en'
 
-import re
+from urllib import urlencode
-import urllib2
 from contextlib import closing
 
 from lxml import html
 
 from PyQt5.Qt import QUrl
 
-from calibre import browser, url_slash_cleaner
+from calibre import browser
+from calibre.ebooks.metadata import authors_to_string
 from calibre.gui2 import open_url
 from calibre.gui2.store import StorePlugin
 from calibre.gui2.store.basic_config import BasicStoreConfig
@@ -23,70 +23,73 @@ from calibre.gui2.store.search_result import SearchResult
 from calibre.gui2.store.web_store_dialog import WebStoreDialog
 
 
+def search(query, max_results=10, timeout=60):
+    url = 'http://www.baen.com/catalogsearch/result/?' + urlencode(
+        {'q':query.lower(), 'dir':'desc', 'order':'relevance'})
+
+    br = browser()
+
+    counter = max_results
+    with closing(br.open_novisit(url, timeout=timeout)) as f:
+        raw = f.read()
+        root = html.fromstring(raw)
+        for data in root.xpath('//div[@id="productMatches"]//table[@id="authorTable"]//tr[contains(@class, "IDCell")]'):
+            if counter <= 0:
+                break
+
+            try:
+                book_url = data.xpath('./td[1]/a/@href[1]')[0]
+            except IndexError:
+                continue
+
+            try:
+                title = data.xpath('./td[2]/a[1]/text()')[0].strip()
+            except IndexError:
+                continue
+            try:
+                cover_url = data.xpath('./td[1]//img[1]/@src')[0]
+            except IndexError:
+                cover_url = ''
+
+            tails = [(b.tail or '').strip() for b in data.xpath('./td[2]/br')]
+            authors = [x[2:].strip() for x in tails if x.startswith('by ')]
+            author = authors_to_string(authors)
+            price = ''.join(data.xpath('.//span[@class="variantprice"]/text()'))
+            a, b, price = price.partition('$')
+            price = b + price
+
+            counter -= 1
+
+            s = SearchResult()
+            s.cover_url = cover_url
+            s.title = title.strip()
+            s.author = author.strip()
+            s.price = price
+            s.detail_item = book_url.strip()
+            s.drm = SearchResult.DRM_UNLOCKED
+            s.formats = 'RB, MOBI, EPUB, LIT, LRF, RTF, HTML'
+
+            yield s
+
+
 class BaenWebScriptionStore(BasicStoreConfig, StorePlugin):
 
     def open(self, parent=None, detail_item=None, external=False):
         url = 'http://www.baenebooks.com/'
-
         if external or self.config.get('open_external', False):
-            if detail_item:
+            open_url(QUrl(detail_item or url))
-                url = url + detail_item
-            open_url(QUrl(url_slash_cleaner(url)))
         else:
-            detail_url = None
+            d = WebStoreDialog(self.gui, url, parent, detail_item or url)
-            if detail_item:
-                detail_url = url + detail_item
-            d = WebStoreDialog(self.gui, url, parent, detail_url)
             d.setWindowTitle(self.name)
             d.set_tags(self.config.get('tags', ''))
             d.exec_()
 
     def search(self, query, max_results=10, timeout=60):
-        url = 'http://www.baenebooks.com/searchadv.aspx?IsSubmit=true&SearchTerm=' + urllib2.quote(query)
+        for result in search(query, max_results, timeout):
+            yield result
 
-        br = browser()
 
-        counter = max_results
+if __name__ == '__main__':
-        with closing(br.open(url, timeout=timeout)) as f:
+    import sys
-            doc = html.fromstring(f.read())
+    for result in search(' '.join(sys.argv[1:])):
-            for data in doc.xpath('//table//table//table//table//tr'):
+        print(result)
-                if counter <= 0:
-                    break
-
-                id = ''.join(data.xpath('./td[1]/a/@href'))
-                if not id or not id.startswith('p-'):
-                    continue
-
-                title = ''.join(data.xpath('./td[1]/a/text()'))
-
-                author = ''
-                cover_url = ''
-                price = ''
-
-                with closing(br.open('http://www.baenebooks.com/' + id.strip(), timeout=timeout/4)) as nf:
-                    idata = html.fromstring(nf.read())
-                    author = ''.join(idata.xpath('//span[@class="ProductNameText"]/../b/text()'))
-                    author = author.split('by ')[-1]
-                    price = ''.join(idata.xpath('//span[@class="variantprice"]/text()'))
-                    a, b, price = price.partition('$')
-                    price = b + price
-
-                    pnum = ''
-                    mo = re.search(r'p-(?P<num>\d+)-', id.strip())
-                    if mo:
-                        pnum = mo.group('num')
-                    if pnum:
-                        cover_url = 'http://www.baenebooks.com/' + ''.join(idata.xpath('//img[@id="ProductPic%s"]/@src' % pnum))
-
-                counter -= 1
-
-                s = SearchResult()
-                s.cover_url = cover_url
-                s.title = title.strip()
-                s.author = author.strip()
-                s.price = price
-                s.detail_item = id.strip()
-                s.drm = SearchResult.DRM_UNLOCKED
-                s.formats = 'RB, MOBI, EPUB, LIT, LRF, RTF, HTML'
-
-                yield s