Prototype for datasheet data extraction

.gitignore

@@ -0,0 +1 @@
+venv

README.md

@@ -1,3 +1,21 @@
 # jukebox-software
 
 This repository is for all of the software used in the Jukebox project.
+
+To setup and run:
+
+run `install-deps.sh` to prepare the python venv and install packages:
+
+    chmod +x ./install-deps.sh && ./install-deps.sh
+
+then, you need to source the venv. Run 
+
+    source venv/bin/activate
+
+or 
+
+    source venv/bin/activate.fish
+
+if you use fish shell.
+
+Then you are good to go to execute any python file.

install-deps.sh

@@ -0,0 +1,9 @@
+#!/bin/sh
+
+if ! [ -d "venv" ]; then
+    ./venv-setup.sh
+fi
+
+source ./venv/bin/activate
+
+pip3 install -r requirements.txt

read-datasheet.py

@@ -0,0 +1,28 @@
+#!/usr/bin/env python3
+
+# Parse Belden catalog techdata datasheets 
+
+import camelot
+import numpy as np
+
+def parse(filename):
+    tables = camelot.read_pdf(filename, pages="1-end", flavor='lattice', backend="poppler", split_text=False, line_scale=100, process_background=True, resolution=600, interations=1, layout_kwargs={'detect_vertical': False, 'char_margin': 0.5}, shift_text=['r', 't'])
+    print("Total tables extracted:", tables.n)
+    n = 0
+    
+    for table in tables:
+        table.df.replace('', np.nan, inplace=True)
+        table.df.dropna(inplace=True, how="all")
+        table.df.dropna(inplace=True, axis="columns", how="all")
+        table.df.replace(np.nan, '', inplace=True)
+        if not table.df.empty:
+            table.to_html("table" + str(n) + ".html")
+            print("\nTable " + str(n))
+            print(table.df)
+            #camelot.plot(table, kind='grid').savefig("test" + str(n) + ".png")
+            n=n+1
+    camelot.plot(tables[0], kind='contour').savefig("test.png")
+    #tables.export('foo.csv', f='csv')
+
+if __name__ == "__main__":
+    parse("test.pdf")

requirements.txt

@@ -0,0 +1,5 @@
+camelot-py[base]
+opencv-python
+pypdf2==2.12.1
+matplotlib
+#PyQt5

venv-setup.sh

@@ -0,0 +1,6 @@
+#!/bin/sh
+
+python -m venv ./venv
+source ./venv/bin/activate
+
+pip install --upgrade pip