راهنمای استان گیلان

import pandas as pd
import openpyxl

# Read the excel file
excel_file = "Irangaah links.xlsx"
xls = pd.ExcelFile(excel_file)
print("Sheet names:", xls.sheet_names)

df = pd.read_excel(excel_file, sheet_name=xls.sheet_names[0])
print("DataFrame head:")
print(df.head(20))
print("DataFrame info:")
print(df.info())

Sheet names: ['Sheet1']
DataFrame head:
                                       cities     شهرستان‌ها  Unnamed: 2                                                provinces             استان‌ها  Unnamed: 5                                                    urls صفحات اصلی ایران
0                    https://irangaah.ir/arak           اراک         NaN                     https://irangaah.ir/province/markazi                مرکزی         NaN                                https://irangaah.ir/iran            ایران
1                 https://irangaah.ir/delijan         دلیجان         NaN                       https://irangaah.ir/province/gilan                گیلان         NaN                      https://irangaah.ir/iran/geography   جغرافیای ایران
2                 https://irangaah.ir/ashtian         آشتیان         NaN                  https://irangaah.ir/province/mazandaran             مازندران         NaN         https://irangaah.ir/iran/geography/persian-gulf        خلیج فارس
3                 https://irangaah.ir/tafresh           تفرش         NaN             https://irangaah.ir/province/east-azerbaijan       آذربایجان شرقی         NaN          https://irangaah.ir/iran/geography/caspian-sea        دریای خزر
4                 https://irangaah.ir/khomeyn           خمین         NaN             https://irangaah.ir/province/west-azerbaijan       آذربایجان غربی         NaN     https://irangaah.ir/iran/geography/zagros-mountains            زاگرس
5                https://irangaah.ir/mahallat          محلات         NaN                  https://irangaah.ir/province/kermanshah             کرمانشاه         NaN        https://irangaah.ir/iran/geography/damavand-peak           دماوند
6                 https://irangaah.ir/shazand          شازند         NaN                   https://irangaah.ir/province/khuzestan              خوزستان         NaN                        https://irangaah.ir/iran/history      تاریخ ایران
7                   https://irangaah.ir/saveh           ساوه         NaN                        https://irangaah.ir/province/fars                 فارس         NaN      https://irangaah.ir/iran/history/achaemenid-empire        هخامنشیان
8              https://irangaah.ir/zarandiyeh         زرندیه         NaN                      https://irangaah.ir/province/kerman                کرمان         NaN        https://irangaah.ir/iran/history/sassanid-empire         ساسانیان
9                 https://irangaah.ir/komijan         کمیجان         NaN             https://irangaah.ir/province/razavi-khorasan          خراسان رضوی         NaN             https://irangaah.ir/iran/history/persepolis        تخت جمشید
10                https://irangaah.ir/khandab          خنداب         NaN                     https://irangaah.ir/province/isfahan               اصفهان         NaN                        https://irangaah.ir/iran/culture      فرهنگ ایران
11                https://irangaah.ir/farahan         فراهان         NaN      https://irangaah.ir/province/sistan-and-baluchestan    سیستان و بلوچستان         NaN     https://irangaah.ir/iran/culture/shahnameh-ferdowsi          شاهنامه
12                 https://irangaah.ir/astara         آستارا         NaN                   https://irangaah.ir/province/kurdistan              کردستان         NaN          https://irangaah.ir/iran/culture/hafez-shirazi             حافظ
13  https://irangaah.ir/astaneh-ye-ashrafiyeh  آستانه اشرفیه         NaN                     https://irangaah.ir/province/hamadan                همدان         NaN          https://irangaah.ir/iran/culture/saadi-shirazi             سعدی
14          https://irangaah.ir/bandar-anzali      بندرانزلی         NaN   https://irangaah.ir/province/chaharmahal-and-bakhtiari   چهارمحال و بختیاری         NaN  https://irangaah.ir/iran/culture/molana-jalal-din-rumi           مولانا
15                 https://irangaah.ir/talesh          طوالش         NaN                    https://irangaah.ir/province/lorestan               لرستان         NaN                              https://irangaah.ir/cities     شهرهای ایران
16                  https://irangaah.ir/rasht            رشت         NaN                        https://irangaah.ir/province/ilam                ایلام         NaN                        https://irangaah.ir/universities       دانشگاه‌ها
17               https://irangaah.ir/langerud         لنگرود         NaN  https://irangaah.ir/province/kohgiluyeh-and-boyer-ahmad  کهگیلویه و بویراحمد         NaN                               https://irangaah.ir/banks          بانک‌ها
18                 https://irangaah.ir/rudbar         رودبار         NaN                     https://irangaah.ir/province/bushehr                بوشهر         NaN                                https://irangaah.ir/azan       اوقات شرعی
19                 https://irangaah.ir/rudsar          رودسر         NaN                      https://irangaah.ir/province/zanjan                زنجان         NaN                             https://irangaah.ir/weather         هواشناسی
DataFrame info:
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 482 entries, 0 to 481
Data columns (total 8 columns):
 #   Column            Non-Null Count  Dtype  
---  ------            --------------  -----  
 0   cities            482 non-null    object 
 1   شهرستان‌ها        482 non-null    object 
 2   Unnamed: 2        0 non-null      float64
 3   provinces         31 non-null     object 
 4   استان‌ها          31 non-null     object 
 5   Unnamed: 5        0 non-null      float64
 6   urls              24 non-null     object 
 7   صفحات اصلی ایران  24 non-null     object 
dtypes: float64(2), object(6)
memory usage: 30.2+ KB
None

# Let's inspect all non-null entries in the columns to get a full mapping of words to URLs
mapping = {}

# Cities / Counties
for idx, row in df[['شهرستان‌ها', 'cities']].dropna().iterrows():
    word = str(row['شهرستان‌ها']).strip()
    url = str(row['cities']).strip()
    mapping[word] = url

# Provinces
for idx, row in df[['استان‌ها', 'provinces']].dropna().iterrows():
    word = str(row['استان‌ها']).strip()
    url = str(row['provinces']).strip()
    mapping[word] = url

# Main pages
for idx, row in df[['صفحات اصلی ایران', 'urls']].dropna().iterrows():
    word = str(row['صفحات اصلی ایران']).strip()
    url = str(row['urls']).strip()
    mapping[word] = url

print(f"Total mapped words/phrases: {len(mapping)}")
for k in list(mapping.keys())[:30]:
    print(f"'{k}': '{mapping[k]}'")

Total mapped words/phrases: 522
'اراک': 'https://irangaah.ir/arak'
'دلیجان': 'https://irangaah.ir/delijan'
'آشتیان': 'https://irangaah.ir/ashtian'
'تفرش': 'https://irangaah.ir/tafresh'
'خمین': 'https://irangaah.ir/khomeyn'
'محلات': 'https://irangaah.ir/mahallat'
'شازند': 'https://irangaah.ir/shazand'
'ساوه': 'https://irangaah.ir/saveh'
'زرندیه': 'https://irangaah.ir/zarandiyeh'
'کمیجان': 'https://irangaah.ir/komijan'
'خنداب': 'https://irangaah.ir/khandab'
'فراهان': 'https://irangaah.ir/farahan'
'آستارا': 'https://irangaah.ir/astara'
'آستانه اشرفیه': 'https://irangaah.ir/astaneh-ye-ashrafiyeh'
'بندرانزلی': 'https://irangaah.ir/bandar-anzali'
'طوالش': 'https://irangaah.ir/talesh'
'رشت': 'https://irangaah.ir/rasht'
'لنگرود': 'https://irangaah.ir/langerud'
'رودبار': 'https://irangaah.ir/rudbar'
'رودسر': 'https://irangaah.ir/rudsar'
'صومعه‌سرا': 'https://irangaah.ir/somehsara'
'فومن': 'https://irangaah.ir/fuman'
'لاهیجان': 'https://irangaah.ir/lahijan'
'شفت': 'https://irangaah.ir/shaft'
'املش': 'https://irangaah.ir/amlash'
'رضوانشهر': 'https://irangaah.ir/rezvanshahr'
'سیاهکل': 'https://irangaah.ir/siahkal'
'ماسال': 'https://irangaah.ir/masal'
'خمام': 'https://irangaah.ir/khomam'
'آمل': 'https://irangaah.ir/amol'

gilan_related = ['گیلان', 'رشت', 'آستارا', 'آستانه اشرفیه', 'بندرانزلی', 'طوالش', 'تالش', 'لنگرود', 'رودبار', 'رودسر', 'صومعه‌سرا', 'صومعه سرا', 'فومن', 'لاهیجان', 'شفت', 'املش', 'رضوانشهر', 'سیاهکل', 'ماسال', 'خمام', 'دریای خزر', 'ایران', 'تهران', 'مازندران', 'زنجان', 'اردبیل', 'زاگرس', 'دانشگاه‌ها', 'هواشناسی']
for word in gilan_related:
    if word in mapping:
        print(f"'{word}': '{mapping[word]}'")
    else:
        print(f"'{word}': NOT FOUND")

'گیلان': 'https://irangaah.ir/province/gilan'
'رشت': 'https://irangaah.ir/rasht'
'آستارا': 'https://irangaah.ir/astara'
'آستانه اشرفیه': 'https://irangaah.ir/astaneh-ye-ashrafiyeh'
'بندرانزلی': 'https://irangaah.ir/bandar-anzali'
'طوالش': 'https://irangaah.ir/talesh'
'تالش': NOT FOUND
'لنگرود': 'https://irangaah.ir/langerud'
'رودبار': 'https://irangaah.ir/rudbar'
'رودسر': 'https://irangaah.ir/rudsar'
'صومعه‌سرا': 'https://irangaah.ir/somehsara'
'صومعه سرا': NOT FOUND
'فومن': 'https://irangaah.ir/fuman'
'لاهیجان': 'https://irangaah.ir/lahijan'
'شفت': 'https://irangaah.ir/shaft'
'املش': 'https://irangaah.ir/amlash'
'رضوانشهر': 'https://irangaah.ir/rezvanshahr'
'سیاهکل': 'https://irangaah.ir/siahkal'
'ماسال': 'https://irangaah.ir/masal'
'خمام': 'https://irangaah.ir/khomam'
'دریای خزر': 'https://irangaah.ir/iran/geography/caspian-sea'
'ایران': 'https://irangaah.ir/iran'
'تهران': 'https://irangaah.ir/province/tehran'
'مازندران': 'https://irangaah.ir/province/mazandaran'
'زنجان': 'https://irangaah.ir/province/zanjan'
'اردبیل': 'https://irangaah.ir/province/ardabil'
'زاگرس': 'https://irangaah.ir/iran/geography/zagros-mountains'
'دانشگاه‌ها': 'https://irangaah.ir/universities'
'هواشناسی': 'https://irangaah.ir/weather'