fix: pdf first page tailor (#1116)

* fix: pdf first page tailor * fix: pdf first page tailor
GaiZhenbiao · Jun 19, 2024 · 588d672 · 588d672
1 parent b9a5bca
commit 588d672
Showing 1 changed file with 3 additions and 2 deletions.
diff --git a/modules/pdf_func.py b/modules/pdf_func.py
@@ -61,7 +61,7 @@ def get_title_with_cropped_page(first_page):
         elif word.text == "Abstract": # 获取页面abstract
             top = word.top
 
-    user_info = [i["text"] for i in extract_words(first_page.within_bbox((x0,title_bottom,x1,top)))]
+    user_info = [i["text"] for i in extract_words(first_page.within_bbox((x0,title_bottom,x1,bottom)))]
     # 裁剪掉上半部分, within_bbox: full_included; crop: partial_included
     return title, user_info, first_page.within_bbox((x0,top,x1,bottom))
 
@@ -150,4 +150,5 @@ def parse_pdf(filename, two_column = True):
     # Test code
     z = parse_pdf("./build/test.pdf")
     print(z["user_info"])
-    print(z["title"])
+    print(z["title"])
+