Get Books: Remove Gandalf store, add Publio store. Update the Legimi store plugin for website changes

src/calibre/customize/builtins.py

@@ -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'
@@ -1472,7 +1463,7 @@ class StoreKoboStore(StoreBase):
 class StoreLegimiStore(StoreBase):
     name = 'Legimi'
     author = u'Tomasz Długosz'
-    description = u'Tanie oraz darmowe ebooki, egazety i blogi w formacie EPUB, wprost na Twój e-czytnik, iPhone, iPad, Android i komputer'
+    description = u'Ebooki w formacie EPUB, MOBI i PDF'
     actual_plugin = 'calibre.gui2.store.stores.legimi_plugin:LegimiStore'
 
     headquarters = 'PL'
@@ -1566,6 +1557,15 @@ class StorePragmaticBookshelfStore(StoreBase):
     headquarters = 'US'
     formats = ['EPUB', 'MOBI', 'PDF']
 
+class StorePublioStore(StoreBase):
+    name = 'Publio'
+    description = u'Publio.pl to księgarnia internetowa, w której mogą Państwo nabyć e-booki i audiobooki.'
+    actual_plugin = 'calibre.gui2.store.stores.publio_plugin:PublioStore'
+    author = u'Tomasz Długosz'
+
+    headquarters = 'PL'
+    formats = ['EPUB', 'MOBI', 'PDF']
+
 class StoreRW2010Store(StoreBase):
     name = 'RW2010'
     description = u'Polski serwis self-publishingowy. Pliki PDF, EPUB i MOBI. Maksymalna cena utworu nie przekracza u nas 10 złotych!'
@@ -1675,7 +1675,6 @@ plugins += [
     StoreEscapeMagazineStore,
     StoreFeedbooksStore,
     StoreFoylesUKStore,
-    StoreGandalfStore,
     StoreGoogleBooksStore,
     StoreGutenbergStore,
     StoreKoboStore,
@@ -1689,6 +1688,7 @@ plugins += [
     StoreOpenBooksStore,
     StoreOzonRUStore,
     StorePragmaticBookshelfStore,
+    StorePublioStore,
     StoreRW2010Store,
     StoreSmashwordsStore,
     StoreVirtualoStore,

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

@@ -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

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

@@ -25,7 +25,7 @@ class LegimiStore(BasicStoreConfig, StorePlugin):
 
     def open(self, parent=None, detail_item=None, external=False):
         
-        plain_url = 'http://www.legimi.com/pl/ebooks/?price=any'
+        plain_url = 'http://www.legimi.com/pl/ebooki/'
         url = 'https://ssl.afiliant.com/affskrypt,,2f9de2,,11483,,,?u=(' + plain_url + ')'
         detail_url = None
 
@@ -41,32 +41,36 @@ class LegimiStore(BasicStoreConfig, StorePlugin):
             d.exec_()
 
     def search(self, query, max_results=10, timeout=60):
-        url = 'http://www.legimi.com/pl/ebooks/?price=any&lang=pl&search=' + urllib.quote_plus(query) + '&sort=relevance'
+        url = 'http://www.legimi.com/pl/ebooki/?szukaj=' + urllib.quote_plus(query)
         
         br = browser()
-        drm_pattern = re.compile("(DRM)")
+        drm_pattern = re.compile("zabezpieczona DRM")
         
         counter = max_results
         with closing(br.open(url, timeout=timeout)) as f:
             doc = html.fromstring(f.read())
-            for data in doc.xpath('//div[@class="list"]/ul/li'):
+            for data in doc.xpath('//div[@id="listBooks"]/div'):
                 if counter <= 0:
                     break
                 
-                id = ''.join(data.xpath('.//div[@class="item_cover_container"]/a[1]/@href'))
+                id = ''.join(data.xpath('.//a[@class="plainLink"]/@href'))
                 if not id:
                     continue
 
-                cover_url = ''.join(data.xpath('.//div[@class="item_cover_container"]/a/img/@src'))
+                cover_url = ''.join(data.xpath('.//img[1]/@src'))
-                title = ''.join(data.xpath('.//div[@class="item_entries"]/h2/a/text()'))
+                title = ''.join(data.xpath('.//span[@class="bookListTitle ellipsis"]/text()'))
-                author = ''.join(data.xpath('.//div[@class="item_entries"]/span[1]/a/text()'))
+                author = ''.join(data.xpath('.//span[@class="bookListAuthor ellipsis"]/text()'))
                 author = re.sub(',','',author)
                 author = re.sub(';',',',author)
-                price = ''.join(data.xpath('.//span[@class="ebook_price"]/text()'))
+                price = ''.join(data.xpath('.//div[@class="bookListPrice"]/span/text()'))
-                formats = ''.join(data.xpath('.//div[@class="item_entries"]/span[3]/text()'))
+                formats = []
-                formats = re.sub('Format:','',formats)
+                with closing(br.open(id.strip(), timeout=timeout/4)) as nf:
-                drm = drm_pattern.search(formats)
+                    idata = html.fromstring(nf.read())
-                formats = re.sub('\(DRM\)','',formats)
+                    formatlist = idata.xpath('.//div[@id="fullBookFormats"]//span[@class="bookFormat"]/text()')
+                    for x in formatlist:
+                        if x.strip() not in formats:
+                            formats.append(x.strip())
+                    drm = drm_pattern.search(''.join(idata.xpath('.//div[@id="fullBookFormats"]/p/text()')))
 
                 counter -= 1
                 
@@ -76,7 +80,7 @@ class LegimiStore(BasicStoreConfig, StorePlugin):
                 s.author = author.strip()
                 s.price = price
                 s.detail_item = 'http://www.legimi.com/' + id.strip()
+                s.formats = ', '.join(formats)
                 s.drm = SearchResult.DRM_LOCKED if drm else SearchResult.DRM_UNLOCKED
-                s.formats = formats.strip()
                 
                 yield s

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

@@ -0,0 +1,80 @@
+# -*- coding: utf-8 -*-
+
+from __future__ import (unicode_literals, division, absolute_import, print_function)
+
+__license__ = 'GPL 3'
+__copyright__ = '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 PublioStore(BasicStoreConfig, StorePlugin):
+
+    def open(self, parent=None, detail_item=None, external=False):
+        google_analytics = '?utm_source=tdcalibre&utm_medium=calibre'
+        url = 'http://www.publio.pl/e-booki.html' + google_analytics
+
+        if external or self.config.get('open_external', False):
+            open_url(QUrl(url_slash_cleaner((detail_item + google_analytics) 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=20, timeout=60):
+
+        br = browser()
+
+        counter = max_results
+        page = 1
+        while counter:
+            with closing(br.open('http://www.publio.pl/e-booki,strona' + str(page) + '.html?q=' + urllib.quote(query), timeout=timeout)) as f:
+                doc = html.fromstring(f.read())
+                for data in doc.xpath('//div[@class="item"]'):
+                    if counter <= 0:
+                        break
+
+                    id = ''.join(data.xpath('.//div[@class="img"]/a/@href'))
+                    if not id:
+                        continue
+
+                    cover_url = ''.join(data.xpath('.//div[@class="img"]/a/img/@data-original'))
+                    title = ''.join(data.xpath('.//div[@class="desc"]/h4/a/text()'))
+                    title2 = ''.join(data.xpath('.//div[@class="desc"]/h5/a/text()'))
+                    if title2:
+                        title = title + '. ' + title2
+                    author = ', '.join(data.xpath('./div[@class="desc"]/div[@class="detailShortList"]/div[@class="row"]/a/text()'))
+                    price = ''.join(data.xpath('.//div[@class="priceBoxContener "]/div/ins/text()'))
+                    if not price:
+                        price = ''.join(data.xpath('.//div[@class="priceBoxContener "]/div/text()'))
+                    formats = ', '.join(data.xpath('.//div[@class="formats"]/a/img/@alt'))
+
+                    counter -= 1
+
+                    s = SearchResult()
+                    s.cover_url = 'http://www.publio.pl' + cover_url 
+                    s.title = title.strip()
+                    s.author = author.strip()
+                    s.price = price.strip()
+                    s.detail_item = 'http://www.publio.pl' + id.strip()
+                    s.drm = SearchResult.DRM_LOCKED if 'DRM' in formats else SearchResult.DRM_UNLOCKED
+                    s.formats = formats.replace(' DRM','').strip()
+
+                    yield s
+                if not doc.xpath('boolean(//a[@class="next"])'):
+                    break
+                page+=1