Python: Web Scraping

instagram_profile_stats.py

from requests_html import HTMLSession
import re

session = HTMLSession()

out_header = ('URL' + ';' + 'Account Name' + ';' + 'Displayed Full Name' + ';' + 'Submitted Posts'
				+ ';' + 'Followers' + ';' + 'Postcount (Number)')

sel_handle = '#react-root > section > main > div > header > section > div:nth-of-type(1) > h1'
sel_iposts = '#react-root > section > main > div > header > section > ul > li:nth-child(1) > span'
sel_follow = '#react-root > section > main > div > header > section > ul > li:nth-child(2) > span'
sel_dsname = '#react-root > section > main > div > header > section > div:nth-of-type(2) > h1'

try:
	file = open('input_ig.txt', mode='rt', encoding='utf-8', errors='strict', newline=None)
	lines = filter(None, (line.rstrip() for line in file))
except OSError:
	raise SystemExit('[Error] Could not open file "input_ig.txt" ..')

print(out_header)
for line in lines:
	r = session.get(line)
	r.html.render()
	try:
		handle = r.html.find(sel_handle, first=True).text
		iposts = r.html.find(sel_iposts, first=True).text
		follow = r.html.find(sel_follow, first=True).text
		dsname = r.html.find(sel_dsname, first=True).text.encode('cp1252', errors='ignore')
		dsname = dsname.decode('utf-8')
		pcount = re.match(r'\d+', iposts.replace(',', '')).group(0)
	except AttributeError:
		output = line + ';' + '<--->'+ ';' + 'Some error occured with this URL!'
	else:
		output = line + ';' + handle + ';' + dsname + ';' + iposts + ';' + follow + ';' + pcount
	print(output)
file.close()

instagram_statscrape.ps1

param (
	[String]$File
)

function Process_URL([String]$URL) {
	$meta_desc = curl -s $URL | rg 'og:description'
	if ($meta_desc.length -eq 0) {
		$outp = $URL + ';' + '<-->' + ';' + 'Error: Something is wrong with this URL..'
	} else {
		$accn = $URL -replace "(.*(\.com\/)(?<acc>.*)\/.*)", '${acc}'
		$name = $meta_desc -replace "(^.*(from\s(?<name>.*)\s.*)\(.*$)", '${name}'
		$post = $meta_desc -replace "(.*(Following\,\s)(?<posts>.*)(\s-).*)", '${posts}'
		$fllw = $meta_desc -replace "(.*(content=.)(?<fllw>.*?)(\,.*))", '${fllw}'
		$pnum = $post.Replace(',','') -replace "((\d*)(\sPosts))", '$2'
		$outp = $URL + ';' + $accn + ';' + $name + ';' + $post + ';' + $fllw + ';' + $pnum
	}
	Write-Output $outp
}

if ([String]::IsNullOrWhiteSpace($File) -or (($File -eq "--help") -or ($File -eq "-h") -or ($File -eq "?"))) {
	Write-Output "[instagram_statscrape] Usage: instagram_statscrape <FILE> OR \Path\to\instagram_statscrape.ps1 <FILE>"
} elseif (-not (Test-Path $File)) {
	Write-Output "[instagram_statscrape] File '$File' not found!"
} else {
	$out_header = 'URL' + ';' + 'Account Name' + ';' + 'Displayed Full Name' + ';' + `
			  	  'Submitted Posts' + ';' + 'Followers' + ';' + 'Postcount (Number only)'
	Write-Output $out_header
	foreach($Line in [System.IO.File]::ReadLines(((Get-Item $File).FullName))) {
		if (-not ([String]::IsNullOrWhiteSpace($Line))) {
			Process_URL($Line)
		}
	}
}