kris/ForcePilot
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

reformat

Browse Source
This commit is contained in:
Xerrors 2024-08-08 17:13:01 +08:00
parent d15618e12d
commit 32740f9979
1 changed files with 26 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

48
src/plugins/pdf2txt.py
View File

@ -13,26 +13,7 @@ def pdf2txt(pdf_path, return_text=False):
table_engine = PPStructure(recovery=True, lang='ch') table_engine = PPStructure(recovery=True, lang='ch')
imgs = [] imgs = convert_imgs(pdf_path, output_dir)
img_dir = os.path.join(output_dir, 'imgs')
if not os.path.exists(img_dir):
os.makedirs(img_dir)
pdfDoc = fitz.open(pdf_path)
totalPage = pdfDoc.page_count
for pg in tqdm(range(totalPage), desc='to imgs', ncols=100):
page = pdfDoc[pg]
rotate = int(0)
zoom_x = 2
zoom_y = 2
mat = fitz.Matrix(zoom_x, zoom_y).prerotate(rotate)
pix = page.get_pixmap(matrix=mat, alpha=False)
img_filename = os.path.join(img_dir, f'images_{pg+1}.png')
pix.save(img_filename) # os.sep
imgs.append(img_filename)
else:
img_names = sorted(os.listdir(img_dir))
imgs = [os.path.join(img_dir, img_name) for img_name in img_names]
respath = os.path.join(output_dir, 'res.txt') respath = os.path.join(output_dir, 'res.txt')
text = [] text = []
@ -59,7 +40,7 @@ def pdf2txt(pdf_path, return_text=False):
continue # 如果不是字典或者缺少 'text' 键，跳过当前循环 continue # 如果不是字典或者缺少 'text' 键，跳过当前循环
text.append('\n') text.append('\n')
whole_text = '\n'.join(text) whole_text = ''.join(text)
with open(respath, 'w', encoding='utf-8') as f: with open(respath, 'w', encoding='utf-8') as f:
f.write(whole_text) f.write(whole_text)
@ -68,6 +49,29 @@ def pdf2txt(pdf_path, return_text=False):
return respath return respath
def convert_imgs(pdf_path, output_dir):
imgs = []
img_dir = os.path.join(output_dir, 'imgs')
if not os.path.exists(img_dir):
os.makedirs(img_dir)
pdfDoc = fitz.open(pdf_path)
totalPage = pdfDoc.page_count
for pg in tqdm(range(totalPage), desc='to imgs', ncols=100):
page = pdfDoc[pg]
rotate = int(0)
zoom_x = 2
zoom_y = 2
mat = fitz.Matrix(zoom_x, zoom_y).prerotate(rotate)
pix = page.get_pixmap(matrix=mat, alpha=False)
img_filename = os.path.join(img_dir, f'images_{pg+1}.png')
pix.save(img_filename) # os.sep
imgs.append(img_filename)
else:
img_names = sorted(os.listdir(img_dir))
imgs = [os.path.join(img_dir, img_name) for img_name in img_names]
return imgs
if __name__ == "__main__": if __name__ == "__main__":
pdf_path = r'data/file/焙烤食品工艺学.pdf' pdf_path = r'saves/data/uploads/2e04d5_保健食品.pdf'
print(pdf2txt(pdf_path)) print(pdf2txt(pdf_path))