Update get_paper_from_pdf.py

pp2024 · Mar 16, 2023 · 2998637 · 2998637
1 parent 5f4a61c
commit 2998637
Showing 1 changed file with 2 additions and 2 deletions.
diff --git a/get_paper_from_pdf.py b/get_paper_from_pdf.py
@@ -125,7 +125,7 @@ def get_title(self):
         max_font_size = 0 # 初始化最大字体大小为0
         max_string = "" # 初始化最大字体大小对应的字符串为空
         max_font_sizes = [0]
-        for page in doc: # 遍历每一页
+        for page_index, page in enumerate(doc): # 遍历每一页
             text = page.get_text("dict") # 获取页面上的文本信息
             blocks = text["blocks"] # 获取文本块列表
             for block in blocks: # 遍历每个文本块
@@ -139,7 +139,7 @@ def get_title(self):
         max_font_sizes.sort()                
         print("max_font_sizes", max_font_sizes[-10:])
         cur_title = ''
-        for page in doc: # 遍历每一页
+        for page_index, page in enumerate(doc): # 遍历每一页
             text = page.get_text("dict") # 获取页面上的文本信息
             blocks = text["blocks"] # 获取文本块列表
             for block in blocks: # 遍历每个文本块