Dixhom

import os
from pathlib import Path
from pdf2image import convert_from_path

# For Windows users, download poppler Release-24.08.0-0.zip from here (https://github.com/oschwartz10612/poppler-windows/releases)
# unzip it and add the poppler path to the environmental variable.
poppler_dir = "<path-to-poppler>/poppler-24.08.0/Library/bin"
os.environ["PATH"] += os.pathsep + str(poppler_dir)

pdf_path = Path("<path-to-pdf>/file.pdf")

Dixhom

'''an example of getting a list of unique dicts using named tuple'''

from collections import namedtuple

dict_list = [
    dict(a=1, b=2, c=3), 
    dict(a=10, b=20, c=30), 
    dict(a=100, b=200, c=300), 
    dict(a=1, b=2, c=3), 
    dict(a=10, b=20, c=30), 

Dixhom

def parse_price(price):
    '''Convert a mixture of arabic and Chinese numerics to arabic numerics. For example, price="４，２５６円"や"百三十二円"
    漢数字等が混じった数字文字列を数字に変換する。例えば、price="４，２５６円"や"百三十二円"'''
    price = price.strip()
    # 削除する文字列
    delete_chars = [',', '、', '円', '￥', '\\']
    for char in delete_chars:
        price = price.replace(char, '')

    # 漢数字や全角数字、半角数字

Dixhom

"""
advantages over normal tqdm:

1. progress can be checked more in detail.
   a progress bar comes with a number at the end "########6".
   This means the last portion is done 60%.
2. The total number of iteration can be changed.
   `obj.total_count = new_count`

"""

Dixhom

int base_year = 1970;
// cumulative days of the year for each month
int daysCumsum[] = {0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334, 365};
char* dayOfTheWeek[] = {"Mon", "Tue", "Wed", "Thu", "Fri", "Sat", "Sun"};


int getLeapYear(int year) {
    // get num leap years from the year 1
    int div4 = year / 4;
    int div100 = year / 100;

Dixhom

def getLeapYear(year):
    # get num leap years from the year 1
    div4 = year // 4
    div100 = year // 100
    div400 = year // 400
    # number of leap years until `year`
    return div4 - div100 + div400

def isLeapYear(year):
    # whether `year` is a leap year

Dixhom

import requests
from bs4 import BeautifulSoup

url = "https://mansion-market.com/mansions/categories/brands"
r = requests.get(url)
soup = BeautifulSoup(r.content, "html.parser")
# be careful, select() returns a list.
[a.text for a in soup.select('div.article_list')[0].select('li')]

Dixhom

# About:
# - This code reads import statements from python scripts and creates a requirements_txt.

# Caveats:
# - Sometimes library names in pip and python scripts are different. e.g.) pip install scikit-learn vs import sklearn. The users need to fix the name by themselves.

# Todo:
# - Prepare a conversion table between the library names in pip and python scripts and create the requirements.txt properly.

import pkg_resources

Dixhom

n = 8
div = 10**n
for i in range(10**(n-1), 10**n):
    if (i * i) % div == i:
        print(i)
        
# 2: 25, 76    
# 3: 376, 625
# 4: 9376
# 5: 90625

Dixhom

class Rational:
	"""
	a class to handle rational numbers
	"""
	def __init__(self, num, denom=1):
		self.num = num # numerator
		self.denom = denom # denominator
		
	def __gcd(self,u,v):
		"""