From 7bd6fba0967d6e553776b0d330b80f2a04a20d07 Mon Sep 17 00:00:00 2001
From: eric <eric@hellman.net>
Date: Fri, 22 Nov 2024 14:34:17 -0500
Subject: [PATCH] fix bookloader when a bookdata is empty

---
 core/bookloader.py       | 19 ++++++++++---------
 core/loaders/scrape.py   | 15 +++++++++------
 core/loaders/springer.py |  4 ++--
 3 files changed, 21 insertions(+), 17 deletions(-)

diff --git a/core/bookloader.py b/core/bookloader.py
index 08644fa6..2baabe05 100755
--- a/core/bookloader.py
+++ b/core/bookloader.py
@@ -1113,13 +1113,14 @@ def add_from_bookdatas(bookdatas):
     editions = []
     for bookdata in bookdatas:
         edition = work = None
-        loader = BasePandataLoader(bookdata.base)
-        pandata = Pandata()
-        pandata.metadata = bookdata.metadata
-        for metadata in pandata.get_edition_list():
-            edition = loader.load_from_pandata(metadata, work)
-            work = edition.work
-        loader.load_ebooks(pandata, edition)
-        if edition:
-            editions.append(edition)
+        if bookdata and bookdata.metadata:
+            loader = BasePandataLoader(bookdata.base)
+            pandata = Pandata()
+            pandata.metadata = bookdata.metadata
+            for metadata in pandata.get_edition_list():
+                edition = loader.load_from_pandata(metadata, work)
+                work = edition.work
+            loader.load_ebooks(pandata, edition)
+            if edition:
+                editions.append(edition)
     return editions
diff --git a/core/loaders/scrape.py b/core/loaders/scrape.py
index 20a79bfb..863d9271 100644
--- a/core/loaders/scrape.py
+++ b/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):
-                self.set('title', '!!! missing title !!!')
-            if not self.metadata.get('language', None):
-                self.set('language', 'en')
+                if not self.metadata.get('title', None):
+                    self.set('title', '!!! missing title !!!')
+                if not self.metadata.get('language', None):
+                    self.set('language', 'en')
+                self.metadata['identifiers'] = self.identifiers
+            else:
+                self.metadata = None
         else:
-            self.metadata = {}
-        self.metadata['identifiers'] = self.identifiers
+            self.metadata = None
+        
 
     #
     # utilities
diff --git a/core/loaders/springer.py b/core/loaders/springer.py
index 88918e7f..cf6dc8c5 100644
--- a/core/loaders/springer.py
+++ b/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)