fix bookloader when a bookdata is empty

core/bookloader.py

@@ -1113,13 +1113,14 @@ def add_from_bookdatas(bookdatas):
     editions = []
     for bookdata in bookdatas:
         edition = work = None
-        loader = BasePandataLoader(bookdata.base)
+        if bookdata and bookdata.metadata:
-        pandata = Pandata()
+            loader = BasePandataLoader(bookdata.base)
-        pandata.metadata = bookdata.metadata
+            pandata = Pandata()
-        for metadata in pandata.get_edition_list():
+            pandata.metadata = bookdata.metadata
-            edition = loader.load_from_pandata(metadata, work)
+            for metadata in pandata.get_edition_list():
-            work = edition.work
+                edition = loader.load_from_pandata(metadata, work)
-        loader.load_ebooks(pandata, edition)
+                work = edition.work
-        if edition:
+            loader.load_ebooks(pandata, edition)
-            editions.append(edition)
+            if edition:
+                editions.append(edition)
     return editions

core/loaders/scrape.py

@@ -65,13 +65,16 @@ class BaseScraper(object):
                 for review in self.doc.find_all(itemtype="http://schema.org/Review"):
                     review.clear()
                 self.get_all()
-            if not self.metadata.get('title', None):
+                if not self.metadata.get('title', None):
-                self.set('title', '!!! missing title !!!')
+                    self.set('title', '!!! missing title !!!')
-            if not self.metadata.get('language', None):
+                if not self.metadata.get('language', None):
-                self.set('language', 'en')
+                    self.set('language', 'en')
+                self.metadata['identifiers'] = self.identifiers
+            else:
+                self.metadata = None
         else:
-            self.metadata = {}
+            self.metadata = None
-        self.metadata['identifiers'] = self.identifiers
+        
 
     #
     # utilities

core/loaders/springer.py

@@ -146,9 +146,9 @@ class SpringerScraper(BaseScraper):
             self.set('rights_url', lic_url)
 
     def get_pubdate(self):
-        pubinfo = self.doc.select_one('#copyright-info')
+        pubinfo = self.doc.find(attrs={"data-test": "electronic_isbn_publication_date"})
         if not pubinfo:
-            pubinfo = self.doc.select_one('header .c-article-identifiers')
+            pubinfo = self.doc.find(attrs={"data-test": "softcover_isbn_publication_date"})
         if pubinfo:
             for yearstring in pubinfo.stripped_strings:
                 yearmatch = HAS_YEAR.search(yearstring)