Merge branch 'release/1.0.7'

OpenBookPublishers · Mar 6, 2023 · f4271c4 · f4271c4
2 parents c6c8968 + 66a03d9
commit f4271c4
Show file tree

Hide file tree

Showing 2 changed files with 15 additions and 23 deletions.
diff --git a/src/epublius/metadata.py b/src/epublius/metadata.py
@@ -106,32 +106,22 @@ def get_file_soup(self):
 
     def get_chapter_title(self):
         '''
-        Retrieve chapter title based on the text of <h1> or
+        Retrieve chapter title based on the text of <title> or
         taking a guess from the file name
         (i.e. front-cover.xhtml -> "Front Cover")
 
         Special characters in the title are escaped before
         the ch_title varible is returned.
         '''
 
-        h1 = self.soup.find_all('h1')
-
-        if len(h1) == 1:
-            ch_title = self.soup.h1.get_text()
-
-        elif len(h1) > 1:
-            print("[WARNING] {} has multiple h1 tags"
-                  .format(self.contents[self.index]))
-            ch_title = h1.pop(0).get_text()
+        title_node = self.soup.title
 
+        if (title_node is not None) and \
+           (title_node.string is not None):
+            ch_title = title_node.string
         else:
-            # Strip extension from file name
-            basename = self.contents[self.index].split('.')[0]
-
-            # Replace hypens with spaces (if any)
+            basename = os.path.splitext(self.contents[self.index])[0]
             title_words = basename.replace('-', ' ')
-
-            # Create a titlecased version of title words
             ch_title = title_words.title()
 
         return html.escape(ch_title)

diff --git a/src/thoth_wrapper.py b/src/thoth_wrapper.py
@@ -19,17 +19,19 @@ def get_title(thoth_data):
 def get_html_pub_url(thoth_data):
     for publication in thoth_data["publications"]:
         if publication['publicationType'] == 'HTML':
-            try:
-                url = publication['locations'][0]['fullTextUrl']
-            except IndexError:
-                raise IndexError('HTML edition defined in Thoth but '
-                                 'location URL not specified. Please, '
-                                 'add it and re-run the process.')
+            locations = publication.get('locations', [])
             break
     else:
-        raise SystemExit('HTML edition data not found in Thoth.',
+        raise ValueError('HTML edition data not found in Thoth.',
                          'Please add it and re-run the process.')
 
+    try:
+        url = locations[0]['fullTextUrl']
+    except IndexError:
+        raise IndexError('HTML edition defined in Thoth but '
+                         'location URL not specified. Please, '
+                         'add it and re-run the process.')
+
     return url
 
 def run():