Spaces:
Runtime error
Runtime error
Update app.py
Browse files
app.py
CHANGED
@@ -28,18 +28,11 @@ st.caption("Created by Bayhaqy")
|
|
28 |
st.markdown("This is tools for join and split file PDF")
|
29 |
|
30 |
# Make folder for storing user uploads
|
31 |
-
destination_folder = Path(
|
32 |
destination_folder.mkdir(exist_ok=True, parents=True)
|
33 |
|
34 |
# Defines what options are in the form
|
35 |
class PDFMergeRequest(BaseModel):
|
36 |
-
"""
|
37 |
-
This code snippet defines a class called PDFMergeRequest that inherits from BaseModel.
|
38 |
-
It has a property called pdf_uploads which is an optional list of FileContent objects.
|
39 |
-
The Field function is used to specify additional information about this property, such as its default value,
|
40 |
-
alias, and description. In this case, the alias is set to "PDF File to Split" and the description is set
|
41 |
-
to "PDF that needs to be split".
|
42 |
-
"""
|
43 |
pdf_uploads: Optional[List[FileContent]] = Field(
|
44 |
None,
|
45 |
alias="PDF File to Split",
|
@@ -47,12 +40,6 @@ class PDFMergeRequest(BaseModel):
|
|
47 |
)
|
48 |
|
49 |
class PDFSplitRequest(BaseModel):
|
50 |
-
"""
|
51 |
-
This code snippet defines a PDFSplitRequest class that inherits from BaseModel.
|
52 |
-
It has two attributes: pages_per_pdf and pdf_upload. pages_per_pdf is an integer field with a default value of 1.
|
53 |
-
pdf_upload is an optional field that can accept a FileContent object or None as its value.
|
54 |
-
Both attributes have aliases and descriptions that provide additional information about their purpose.
|
55 |
-
"""
|
56 |
pages_per_pdf: int = Field(
|
57 |
1,
|
58 |
alias="Pages per Split",
|
@@ -65,17 +52,9 @@ class PDFSplitRequest(BaseModel):
|
|
65 |
)
|
66 |
|
67 |
def stack_images(images):
|
68 |
-
|
69 |
-
Generate a stacked image by vertically stacking a list of input images.
|
70 |
-
|
71 |
-
Parameters:
|
72 |
-
- images (List[Image]): A list of input images to stack vertically.
|
73 |
-
|
74 |
-
Returns:
|
75 |
-
- output_image (Image): The output stacked image, with each input image vertically stacked on top of each other.
|
76 |
-
"""
|
77 |
first_image = images[0]
|
78 |
-
output_image = Image.new(
|
79 |
output_image.paste(first_image, (0, 0))
|
80 |
starting_y_value = first_image.height
|
81 |
for image in images[1:]:
|
@@ -84,23 +63,23 @@ def stack_images(images):
|
|
84 |
return output_image
|
85 |
|
86 |
# Radio buttons for selecting the file type
|
87 |
-
pdf_output =
|
88 |
-
jpg_output =
|
89 |
-
png_output =
|
90 |
-
#output_suffix = st.radio(
|
91 |
output_suffix = (pdf_output)
|
92 |
|
93 |
# Add a heading
|
94 |
st.markdown("### PDF Manipulation Options")
|
95 |
|
96 |
# Radio buttons for selecting the function
|
97 |
-
view_choice = st.radio(
|
98 |
|
99 |
# Display relevant instructions
|
100 |
-
if view_choice ==
|
101 |
st.markdown("**Upload multiple PDFs**")
|
102 |
|
103 |
-
# Get the data from the form, stop running if user hasn
|
104 |
data = sp.pydantic_form(key="pdf_merge_form", model=PDFMergeRequest)
|
105 |
if data is None or data.pdf_uploads is None or len(data.pdf_uploads) < 2:
|
106 |
st.warning("Upload at least 2 PDFs and press Submit")
|
@@ -109,7 +88,7 @@ if view_choice == "Merge Multiple PDFs into One":
|
|
109 |
# Save Uploaded PDFs
|
110 |
uploaded_paths = []
|
111 |
for pdf_data in data.pdf_uploads:
|
112 |
-
input_pdf_path = destination_folder / f"input_{datetime.now().strftime(
|
113 |
input_pdf_path.write_bytes(pdf_data.as_bytes())
|
114 |
uploaded_paths.append(input_pdf_path)
|
115 |
|
@@ -117,13 +96,12 @@ if view_choice == "Merge Multiple PDFs into One":
|
|
117 |
for path in uploaded_paths:
|
118 |
pdf_reader = PdfFileReader(str(path))
|
119 |
for page in range(pdf_reader.getNumPages()):
|
120 |
-
|
121 |
# Add each page to the writer object
|
122 |
pdf_writer.addPage(pdf_reader.getPage(page))
|
123 |
|
124 |
# Write out the merged PDF
|
125 |
-
output_pdf_path = destination_folder / f"output_{datetime.now().strftime(
|
126 |
-
with open(str(output_pdf_path),
|
127 |
pdf_writer.write(out)
|
128 |
output_path = output_pdf_path
|
129 |
|
@@ -131,19 +109,20 @@ if view_choice == "Merge Multiple PDFs into One":
|
|
131 |
if output_suffix in (png_output, jpg_output):
|
132 |
images = convert_from_path(output_pdf_path)
|
133 |
stacked_image = stack_images(images)
|
134 |
-
output_path = destination_folder / f"output_{datetime.now().strftime(
|
135 |
stacked_image.save(output_path) # format inferred
|
136 |
|
137 |
# Allow download
|
138 |
if output_suffix == pdf_output:
|
139 |
-
output_mime =
|
140 |
elif output_suffix == jpg_output:
|
141 |
-
output_mime =
|
142 |
elif output_suffix == png_output:
|
143 |
-
output_mime =
|
144 |
|
145 |
# Create a download button with a custom label
|
146 |
-
st.
|
|
|
147 |
|
148 |
# Delete temporary files
|
149 |
for path in uploaded_paths:
|
@@ -154,17 +133,17 @@ if view_choice == "Merge Multiple PDFs into One":
|
|
154 |
# Delete the output file after download
|
155 |
os.remove(output_path)
|
156 |
|
157 |
-
elif view_choice ==
|
158 |
st.markdown("**Upload a single PDF to split**")
|
159 |
|
160 |
-
# Get the data from the form, stop running if user hasn
|
161 |
data = sp.pydantic_form(key="pdf_split_form", model=PDFSplitRequest)
|
162 |
if data is None or data.pdf_upload is None:
|
163 |
st.warning("Upload a PDF and press Submit")
|
164 |
st.stop()
|
165 |
|
166 |
# Save Uploaded PDF
|
167 |
-
input_pdf_path = destination_folder / f"input_{datetime.now().strftime(
|
168 |
input_pdf_path.write_bytes(data.pdf_upload.as_bytes())
|
169 |
|
170 |
# Get PDF Reader
|
@@ -178,7 +157,7 @@ elif view_choice == "Split One PDF into Multiple":
|
|
178 |
downloads = []
|
179 |
for letter_start in range(0, pdf.numPages, data.pages_per_pdf):
|
180 |
output = PdfFileWriter()
|
181 |
-
output_path = input_pdf_path.with_name(f"output_{datetime.now().strftime(
|
182 |
for letter_page in range(data.pages_per_pdf):
|
183 |
output.addPage(pdf.getPage(letter_start + letter_page))
|
184 |
|
@@ -189,21 +168,21 @@ elif view_choice == "Split One PDF into Multiple":
|
|
189 |
if output_suffix in (png_output, jpg_output):
|
190 |
images = convert_from_path(output_path)
|
191 |
stacked_image = stack_images(images)
|
192 |
-
output_path = destination_folder / f"output_{datetime.now().strftime(
|
193 |
stacked_image.save(output_path) # format inferred
|
194 |
|
195 |
downloads.append(output_path)
|
196 |
st.success(f"Saved file {str(output_path)} (original start page {letter_start + 1 } / {pdf.numPages})")
|
197 |
|
198 |
# Make zip file of all split pdfs
|
199 |
-
zip_path = destination_folder / f"output_{datetime.now().strftime(
|
200 |
output_zip = ZipFile(str(zip_path), "w")
|
201 |
for download_path in downloads:
|
202 |
output_zip.write(str(download_path), arcname=download_path.name)
|
203 |
output_zip.close()
|
204 |
|
205 |
# Provide download button of the zip of split pdfs
|
206 |
-
st.download_button(f"Download {str(zip_path)}", zip_path.read_bytes(), str(zip_path), mime=
|
207 |
|
208 |
# Delete temporary files
|
209 |
for download_path in downloads:
|
|
|
28 |
st.markdown("This is tools for join and split file PDF")
|
29 |
|
30 |
# Make folder for storing user uploads
|
31 |
+
destination_folder = Path('downloads')
|
32 |
destination_folder.mkdir(exist_ok=True, parents=True)
|
33 |
|
34 |
# Defines what options are in the form
|
35 |
class PDFMergeRequest(BaseModel):
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
36 |
pdf_uploads: Optional[List[FileContent]] = Field(
|
37 |
None,
|
38 |
alias="PDF File to Split",
|
|
|
40 |
)
|
41 |
|
42 |
class PDFSplitRequest(BaseModel):
|
|
|
|
|
|
|
|
|
|
|
|
|
43 |
pages_per_pdf: int = Field(
|
44 |
1,
|
45 |
alias="Pages per Split",
|
|
|
52 |
)
|
53 |
|
54 |
def stack_images(images):
|
55 |
+
"""adapted from: https://note.nkmk.me/en/python-pillow-concat-images/"""
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
56 |
first_image = images[0]
|
57 |
+
output_image = Image.new('RGB', (first_image.width, sum((image.height for image in images))))
|
58 |
output_image.paste(first_image, (0, 0))
|
59 |
starting_y_value = first_image.height
|
60 |
for image in images[1:]:
|
|
|
63 |
return output_image
|
64 |
|
65 |
# Radio buttons for selecting the file type
|
66 |
+
pdf_output = '.pdf'
|
67 |
+
jpg_output = '.jpg'
|
68 |
+
png_output = '.png'
|
69 |
+
#output_suffix = st.radio('Output File Type', [pdf_output, jpg_output, png_output], key='output_format')
|
70 |
output_suffix = (pdf_output)
|
71 |
|
72 |
# Add a heading
|
73 |
st.markdown("### PDF Manipulation Options")
|
74 |
|
75 |
# Radio buttons for selecting the function
|
76 |
+
view_choice = st.radio('Select a PDF Function', ('Merge Multiple PDFs into One', 'Split One PDF into Multiple'))
|
77 |
|
78 |
# Display relevant instructions
|
79 |
+
if view_choice == 'Merge Multiple PDFs into One':
|
80 |
st.markdown("**Upload multiple PDFs**")
|
81 |
|
82 |
+
# Get the data from the form, stop running if user hasn't submitted pdfs yet
|
83 |
data = sp.pydantic_form(key="pdf_merge_form", model=PDFMergeRequest)
|
84 |
if data is None or data.pdf_uploads is None or len(data.pdf_uploads) < 2:
|
85 |
st.warning("Upload at least 2 PDFs and press Submit")
|
|
|
88 |
# Save Uploaded PDFs
|
89 |
uploaded_paths = []
|
90 |
for pdf_data in data.pdf_uploads:
|
91 |
+
input_pdf_path = destination_folder / f"input_{datetime.now().strftime('%Y_%m_%d_%H_%M_%S_%f')}.pdf"
|
92 |
input_pdf_path.write_bytes(pdf_data.as_bytes())
|
93 |
uploaded_paths.append(input_pdf_path)
|
94 |
|
|
|
96 |
for path in uploaded_paths:
|
97 |
pdf_reader = PdfFileReader(str(path))
|
98 |
for page in range(pdf_reader.getNumPages()):
|
|
|
99 |
# Add each page to the writer object
|
100 |
pdf_writer.addPage(pdf_reader.getPage(page))
|
101 |
|
102 |
# Write out the merged PDF
|
103 |
+
output_pdf_path = destination_folder / f"output_{datetime.now().strftime('%Y_%m_%d_%H_%M_%S_%f')}.pdf"
|
104 |
+
with open(str(output_pdf_path), 'wb') as out:
|
105 |
pdf_writer.write(out)
|
106 |
output_path = output_pdf_path
|
107 |
|
|
|
109 |
if output_suffix in (png_output, jpg_output):
|
110 |
images = convert_from_path(output_pdf_path)
|
111 |
stacked_image = stack_images(images)
|
112 |
+
output_path = destination_folder / f"output_{datetime.now().strftime('%Y_%m_%d_%H_%M_%S_%f')}{output_suffix}"
|
113 |
stacked_image.save(output_path) # format inferred
|
114 |
|
115 |
# Allow download
|
116 |
if output_suffix == pdf_output:
|
117 |
+
output_mime = 'application/pdf'
|
118 |
elif output_suffix == jpg_output:
|
119 |
+
output_mime = 'image/jpeg'
|
120 |
elif output_suffix == png_output:
|
121 |
+
output_mime = 'image/png'
|
122 |
|
123 |
# Create a download button with a custom label
|
124 |
+
# if st.button("Download Merged PDF"):
|
125 |
+
st.download_button('Download Merged Document', output_path.read_bytes(), f"output_{datetime.now().strftime('%Y_%m_%d_%H_%M_%S_%f')}{output_suffix}", mime=output_mime)
|
126 |
|
127 |
# Delete temporary files
|
128 |
for path in uploaded_paths:
|
|
|
133 |
# Delete the output file after download
|
134 |
os.remove(output_path)
|
135 |
|
136 |
+
elif view_choice == 'Split One PDF into Multiple':
|
137 |
st.markdown("**Upload a single PDF to split**")
|
138 |
|
139 |
+
# Get the data from the form, stop running if user hasn't submitted pdf yet
|
140 |
data = sp.pydantic_form(key="pdf_split_form", model=PDFSplitRequest)
|
141 |
if data is None or data.pdf_upload is None:
|
142 |
st.warning("Upload a PDF and press Submit")
|
143 |
st.stop()
|
144 |
|
145 |
# Save Uploaded PDF
|
146 |
+
input_pdf_path = destination_folder / f"input_{datetime.now().strftime('%Y_%m_%d_%H_%M_%S_%f')}.pdf"
|
147 |
input_pdf_path.write_bytes(data.pdf_upload.as_bytes())
|
148 |
|
149 |
# Get PDF Reader
|
|
|
157 |
downloads = []
|
158 |
for letter_start in range(0, pdf.numPages, data.pages_per_pdf):
|
159 |
output = PdfFileWriter()
|
160 |
+
output_path = input_pdf_path.with_name(f"output_{datetime.now().strftime('%Y_%m_%d_%H_%M_%S_%f')}.pdf")
|
161 |
for letter_page in range(data.pages_per_pdf):
|
162 |
output.addPage(pdf.getPage(letter_start + letter_page))
|
163 |
|
|
|
168 |
if output_suffix in (png_output, jpg_output):
|
169 |
images = convert_from_path(output_path)
|
170 |
stacked_image = stack_images(images)
|
171 |
+
output_path = destination_folder / f"output_{datetime.now().strftime('%Y_%m_%d_%H_%M_%S_%f')}{output_suffix}"
|
172 |
stacked_image.save(output_path) # format inferred
|
173 |
|
174 |
downloads.append(output_path)
|
175 |
st.success(f"Saved file {str(output_path)} (original start page {letter_start + 1 } / {pdf.numPages})")
|
176 |
|
177 |
# Make zip file of all split pdfs
|
178 |
+
zip_path = destination_folder / f"output_{datetime.now().strftime('%Y_%m_%d_%H_%M_%S_%f')}.zip"
|
179 |
output_zip = ZipFile(str(zip_path), "w")
|
180 |
for download_path in downloads:
|
181 |
output_zip.write(str(download_path), arcname=download_path.name)
|
182 |
output_zip.close()
|
183 |
|
184 |
# Provide download button of the zip of split pdfs
|
185 |
+
st.download_button(f"Download {str(zip_path)}", zip_path.read_bytes(), str(zip_path), mime='application/zip', key=str(zip_path))
|
186 |
|
187 |
# Delete temporary files
|
188 |
for download_path in downloads:
|