Duplicate from pierreguillou/pdf-firstpage-to-img

Co-authored-by: Pierre Guillou <[email protected]>

.gitattributes

@@ -0,0 +1,27 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: First page of a PDF >> image
+emoji: 💻
+colorFrom: pink
+colorTo: indigo
+sdk: gradio
+sdk_version: 3.0.2
+app_file: app.py
+pinned: false
+duplicated_from: pierreguillou/pdf-firstpage-to-img
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces#reference

app.py

@@ -0,0 +1,48 @@
+import gradio as gr
+import pdf2image
+import numpy as np
+
+# Convert a PDF to images
+def pdf_to_imgs(pdf):
+  """
+  pdf: pdf file
+  first_page: convert to image only the first page
+  return numpy array of the first page and number of images
+  """
+
+  # get path to pdf
+  path_to_pdf = pdf.name
+  
+  # convert PDF to PIL images (one image by page)
+  first_page=True # we want here only the first page as image
+  if first_page: last_page = 1
+  else: last_page = None
+
+  imgs = pdf2image.convert_from_path(path_to_pdf, last_page=last_page)
+  #num_pages = len(imgs)
+
+  return np.array(imgs[0])
+  #return np.array(imgs[0]), num_pages
+
+title = "First page of a PDF >> image"
+description = "Drop a PDF (WARNING: only the first page will be converted into an image)."
+examples = [["example.pdf"]]
+css = ".output-image, .input-image, .image-preview {height: 600px !important}"
+allow_flagging = "never"
+live = False
+
+iface = gr.Interface(fn=pdf_to_imgs, 
+                     #inputs=[gr.File(label="PDF"), gr.Checkbox(label="Only first page?", value=True)],
+                     inputs=gr.File(label="PDF"), # sdk_version: 3.0.2
+                     #inputs=gr.inputs.File(type="file", label="PDF"), # sdk_version: 2.9.4 needed to use gr.Interface.load("spaces/pierreguillou/pdf2imgs") in other Spaces
+                     #outputs=[gr.Image(type="numpy", label="page image"), gr.Textbox(label="number of pages")], # sdk_version: 3.0.2
+                     outputs=gr.Image(type="numpy", label="image of the first page"), # sdk_version: 3.0.2 
+                     title=title,
+                     description=description,
+                     examples=examples,
+                     #article=article,
+                     css=css,
+                     allow_flagging=allow_flagging,
+                     live=live
+                     )
+iface.launch(debug=True, enable_queue=True)

packages.txt

@@ -0,0 +1 @@
+poppler-utils 

requirements.txt

@@ -0,0 +1,2 @@
+pdf2image
+numpy