#Using the following link:

$($the link for the best selling books on the New York Times$)$

#$1.$ Where are the titles stored? Copy and paste the HTML Element that contains all the titles

#$2.$ What type of HTML Element does contians the titles

#$3.$write a script that pulls all of the following information

# $-$ Title

# $-$ Author

# $-$ Publisher

# $-$ Description

# $-$ How Long on the list

# Use the above script to write a loop that stores the above informaiton

# for each week URL will change from above to

$\text{'}($the url for the best selling books in the New York Times$)/$books$/$best$-$sellers$/$YEAR$/$MONTH$/$DAY$/$combined$-$print$-$and$-$e$-$book$-$nonfiction$/\text{'}$

#where YEAR, MONTH, AND DAY will need to be input through a script

#it is important to note that the NYT only publishes weekly

#so you will need to have a something that tests if you are getting results back

#

# PICK $2$ RANDOM DATES THAT ARE NOT THE ONES BELOW

# MAKE SURE IT IS ONE YEAR

#

#with the above information I would like you to add:

# $-$ Date you entered in you URL

# $-$ Week number

from datetime import datetime as dt

from datetime import timedelta

import requests

from bs$4$ import BeautifulSoup as soup

import pandas as pd # type: ignore

def date$\_$range$($start$,$end,step$)$:

start $=$ dt$.$strptime$($start$,\text{'}\%$Y$-\%$m$-\%$d$\text{'})$

end $=$ dt$.$strptime$($end$,\text{'}\%$Y$-\%$m$-\%$d$\text{'})$

while start $<=$ end:

yield start

start $+=$ timedelta$($step$)$

for x in date$\_$range$(\text{'}2024-10-01\text{'},\text{'}2024-10-30\text{'},7)$:

url $=$ f$\text{'}($the link to the page$)/$books$/$best$-$sellers$/\{$x$.$year$\}/\{$x$.$month$\}/\{$x$.$day$\}/$combined$-$print$-$and$-$e$-$book$-$nonfiction$/\text{'}$

#r $=$ requests.get$($url$)$

#print$($r$.$status$\_$code$)$ #check if this is $404$ pass else write your scrape$\_$code