Extract PDF content (from CHP) with Python

import re

import sys

import urllib.request

import pdfplumber

import pandas as pd

if (len(sys.argv) < 2):

    print("\n\nSyntax: python extract_pdf.py date_string (e.g. 20220124) \n\n")

    exit()

def main():    

    date_string  = sys.argv[1] # e.g. 20220124

    pdf_file_name = f"ctn_{date_string}.pdf" # PDF from CHP: https://www.chp.gov.hk/files/pdf/ctn_20220124.pdf

    #download_pdf( pdf_file_name )

    extract_pdf( pdf_file_name )

def extract_pdf( pdf_file_name ):

    with pdfplumber.open( f"./pdf/{pdf_file_name}" ) as pdf:

        for page in pdf.pages:

            #print(page)

            for table in page.extract_tables():

                df = pd.DataFrame(table[1:], columns=table[0])

                for index, row in df.iterrows():

                    if (isinstance(row[0], str) and len(row[0])>0):

                        rowid = row[0].replace(".","")

                        title = row[1].split("\n")

                        for i in range(0,len(title)):                            

                            if (re.search(u'[\u4e00-\u9fff]', title[i]) is None):

                                title[i] = ""

                        print(rowid, "".join(title))

def download_pdf ( pdf_file_name ) :

    pdfFile = urllib.request.urlopen(f"https://www.chp.gov.hk/files/pdf/{pdf_file_name}")

    file = open(f"./pdf/{pdf_file_name}", "wb")

    file.write(pdfFile.read())

    file.close()

main()

Display cx_oracle error indicating which rows are affected

cursor.executemany("SQL EXEC STATEMENT", data, batcherrors=True)

for error in cursor.getbatcherrors():

    print("Error", error.message, "at row offset", error.offset) 

Calculate the viewing location in Cesium

 Here I summarise two approach for calculating the viewing location in Cesium viewer:

Method 1 (using Camera.computeViewRectangle() method) 

var projection = new Cesium.WebMercatorProjection();

var rect = new Cesium.Rectangle()

viewer.camera.computeViewRectangle(projection.ellipsoid, rect)

let rect_x = (rect.east - rect.west)/2 + rect.west;

let rect_y = (rect.north - rect.south)/2 + rect.south;

var rect_lon = Cesium.Math.toDegrees(rect_y);

var rect_lat = Cesium.Math.toDegrees(rect_x);

console.log(rect_lat, rect_lon)

Note: The computeViewRectangle( ) could be very large when the view pitch is very flat, resulting in a very far point being calculated.

Method 2 (using Camera.computeViewRectangle() method) 

var cc = document.getElementById("cesiumContainer");

var screenCenterPt = new Cesium.Cartesian2(cc.offsetWidth/2, cc.offsetHeight/2);

var pick = viewer.scene.globe.pick(viewer.camera.getPickRay(screenCenterPt), viewer.scene);

if (pick) {

  var geoPt = viewer.scene.globe.ellipsoid.cartesianToCartographic(pick);

  var point = [geoPt.longitude/ Math.PI * 180, geoPt.latitude/ Math.PI * 180];

  

  var rect_lon = point[0];

  var rect_lat = point[1];

  

  console.log(rect_lat, rect_lon);

}

Note: It uses screen center to calculate the point, seems to be more useful.

DOS batch file: Expand * into list of filenames in command line

expand-wildcard.bat

@echo off

setlocal EnableDelayedExpansion

set params=command

for %%a in ("%~1") do (

    set params=!params! %%a

)

echo %params%

%params%

 

Then, running the following command:

C:\>expand-wildcard filename*

Will be executed as following:

C:\>command filename1 filename2 filename3 filename4 ..