{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Common import and setup\n"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": "'/Users/francoishuet/Code/camelot/camelot/__init__.py'"
},
"metadata": {},
"execution_count": 1
}
],
"source": [
"import os, sys, time, pytest\n",
"\n",
"import matplotlib.pyplot as plt\n",
"from matplotlib import patches, lines\n",
"import numpy as np\n",
"import pandas as pd\n",
"from pandas.testing import assert_frame_equal\n",
"\n",
"import pdfminer\n",
"\n",
"from IPython.display import display\n",
"\n",
"# Make sure we use the local version of camelot if it is here\n",
"sys.path.insert(0, os.path.abspath(''))\n",
"\n",
"import camelot\n",
"from camelot.core import Table, TableList, TextEdges\n",
"from camelot.__version__ import generate_version\n",
"from camelot.utils import get_text_objects, text_in_bbox\n",
"from camelot.parsers.stream import Stream\n",
"from camelot.parsers.network import Network\n",
"from camelot.handlers import PDFHandler\n",
"from camelot.plotting import draw_pdf\n",
"from tests.data import *\n",
"\n",
"testdir = os.path.dirname(os.path.abspath('.'))\n",
"testdir = os.path.join(testdir, \"camelot/tests/files\")\n",
"\n",
"# Set up plots to be large enough for visualization\n",
"\n",
"# To check which library we're using\n",
"camelot.__file__\n"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"kwargs = {}\n",
"data = None\n",
"# pdf_file = \"vertical_header.pdf\" # test_network_vertical_header\n",
"# pdf_file, kwargs = \"background_lines_1.pdf\", {} # {\"process_background\": True} # test_lattice_process_background\n",
"\n",
"# pdf_file, kwargs, data = \"superscript.pdf\", {\"flag_size\": True}, data_stream_flag_size # test_network_flag_size\n",
"# pdf_file = \"health.pdf\" # test_network\n",
"# pdf_file = \"clockwise_table_2.pdf\"\n",
"# pdf_file = \"tabula/12s0324.pdf\" # interesting because contains two separate tables\n",
"# pdf_file, kwargs = \"tabula/us-007.pdf\", {\"table_regions\": [\"320,335,573,505\"]} # test_network_table_regions\n",
"# pdf_file, kwargs = \"tabula/us-007.pdf\", {\"table_areas\": [\"320,500,573,335\"]} # test_network_table_areas\n",
"# pdf_file, kwargs = \"detect_vertical_false.pdf\", {\"strip_text\": \" ,\\n\"} # data_stream_strip_text\n",
"# pdf_file, kwargs, data = \"tabula/m27.pdf\", {\"columns\": [\"72,95,209,327,442,529,566,606,683\"], \"split_text\": True, }, data_stream_split_text # data_stream_split_text\n",
"# pdf_file = \"clockwise_table_2.pdf\" # test_network_table_rotated / test_stream_table_rotated\n",
"# pdf_file = \"vertical_header.pdf\"\n",
"\n",
"# pdf_file = \"twotables_2.pdf\"\n",
"pdf_file = \"camelot-issue-132-multiple-tables.pdf\"\n",
"# pdf_file, kwargs, data = \"edge_tol.pdf\", {\"edge_tol\": 500}, data_stream_edge_tol\n",
"# pdf_file, kwargs, data = \"edge_tol.pdf\", {}, data_stream_edge_tol\n",
"\n",
"filename = os.path.join(testdir, pdf_file)"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": "Found 2 tables (7x4, 3x3) in 0.18s\n"
},
{
"output_type": "display_data",
"data": {
"text/plain": " 0 1 2 3\n0 1 Ghfhbdhj 1 \n1 Vgvhgh Hj Hj Hj\n2 Hj Hj Hj Hj\n3 Hj Hj J Hj\n4 V C D Gfhj\n5 Hjb B Jhbh Hj\n6 Hjdhshj Hjhjhh Ddnj dsxv",
"text/html": "\n\n
\n \n \n | \n 0 | \n 1 | \n 2 | \n 3 | \n
\n \n \n \n | 0 | \n 1 | \n Ghfhbdhj | \n 1 | \n | \n
\n \n | 1 | \n Vgvhgh | \n Hj | \n Hj | \n Hj | \n
\n \n | 2 | \n Hj | \n Hj | \n Hj | \n Hj | \n
\n \n | 3 | \n Hj | \n Hj | \n J | \n Hj | \n
\n \n | 4 | \n V | \n C | \n D | \n Gfhj | \n
\n \n | 5 | \n Hjb | \n B | \n Jhbh | \n Hj | \n
\n \n | 6 | \n Hjdhshj | \n Hjhjhh | \n Ddnj | \n dsxv | \n
\n \n
\n
\n\n
\n \n \n | \n 0 | \n 1 | \n 2 | \n
\n \n \n \n | 0 | \n Trtrt | \n H | \n Gh | \n
\n \n | 1 | \n Gh | \n V | \n Hv | \n
\n \n | 2 | \n Hv | \n Bhjb | \n hg | \n
\n \n
\n