scrapHtml.py

#This gist I created to extract data from downloaded html in seperate folder, 
#fetch one string from html file & and use that string to rename file

import shutil
import glob, os
from bs4 import BeautifulSoup

wdir=os.getcwd()+"/result/Year8k9k"
for fname in ["150-N","8752-8784","8790-8891","8893-8930","8933-8979","8983-9150"]:
	os.chdir(wdir+"/"+fname)
	for file in glob.glob("*.html"):
		with open(file, 'r') as content_file:
			content = content_file.read()
		soup = BeautifulSoup(content, 'html.parser')
		table=soup.find_all('table')
		rows = table[4].find_all('tr')
		rollNo=rows[0].findAll('td')[1].find('font').find(text=True)
		shutil.move(file,'log_'+rollNo.strip()+'.html')
	print(fname)
	os.chdir(wdir)