From 2c014ae36eafcf7728c9e2ae8b1d4a8c9dc027ce Mon Sep 17 00:00:00 2001
From: shirshasa <katerinagorbac@gmail.com>
Date: Thu, 16 Jul 2020 15:31:02 +0300
Subject: [PATCH] LAW-3262

- extra digits in footnotes from documents downloaded from livecarta
---
 src/book.py | 15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

diff --git a/src/book.py b/src/book.py
index e72f97c..ccc7b55 100644
--- a/src/book.py
+++ b/src/book.py
@@ -564,7 +564,7 @@ class Book:
         footnotes = []
         for i, (anc_tag, cont_tag) in enumerate(zip(footnote_anchors, footnote_content)):
             assert anc_tag['name'] == cont_tag.find('a')['href'][1:], \
-                'Some ting went wrong with footnotes after libra conversion'
+                'Something went wrong with footnotes after libra conversion'
 
             new_tag = BeautifulSoup(features='lxml').new_tag('sup')
             new_tag['class'] = 'footnote-element'
@@ -573,7 +573,13 @@ class Book:
             new_tag.string = '*'
             anc_tag.replace_with(new_tag)
 
+            # extra digits in footnotes from documents downloaded from livecarta
+            a_text = cont_tag.a.text
+            sup = cont_tag.find_all('p')[0].find('sup')
+            if sup and sup.text == a_text:
+                sup.decompose()
             cont_tag.a.decompose()
+
             unicode_string = ''
             for child in cont_tag.children:
                 if type(child) is NavigableString:
@@ -586,15 +592,8 @@ class Book:
             content = self._clean_footnote_content(unicode_string)
             cont_tag.decompose()
 
-            # new_tag = BeautifulSoup(features="lxml").new_tag('div')
-            # new_tag['class'] = 'footnote-element'
-            # new_tag['data-id'] = f'"{i}"'
-            # new_tag['id'] = f'footnote-{i}'
-            # new_tag.string = content
-            # footnotes.append(str(new_tag))
             footnotes.append(content)
 
-            # i += 1
 
         self.footnotes = footnotes