import streamlit as st
import nltk
import spacy
import pandas as pd
import base64, random
import time, datetime
from pyresparser import ResumeParser
from pdfminer3.layout import LAParams, LTTextBox
from pdfminer3.pdfpage import PDFPage
from pdfminer3.pdfinterp import PDFResourceManager
from pdfminer3.pdfinterp import PDFPageInterpreter
from pdfminer3.converter import TextConverter
import io, random
from streamlit_tags import st_tags
from PIL import Image
import pymysql
from Courses import ds_course, web_course, android_course, ios_course, uiux_course, resume_videos, interview_videos
import pafy
import plotly.express as px
import youtube_dl
nltk.download('punkt')
nltk.download('stopwords')
spacy.load('en_core_web_sm')
def fetch_yt_video(link):
video = pafy.new(link)
return video.title
def get_table_download_link(df, filename, text):
"""Generates a link allowing the data in a given panda dataframe to be downloaded
in: dataframe
out: href string
"""
csv = df.to_csv(index=False)
b64 = base64.b64encode(csv.encode()).decode() # some strings <-> bytes conversions necessary here
# href = f'Download Report'
href = f'{text}'
return href
def pdf_reader(file):
resource_manager = PDFResourceManager()
fake_file_handle = io.StringIO()
converter = TextConverter(resource_manager, fake_file_handle, laparams=LAParams())
page_interpreter = PDFPageInterpreter(resource_manager, converter)
with open(file, 'rb') as fh:
for page in PDFPage.get_pages(fh,
caching=True,
check_extractable=True):
page_interpreter.process_page(page)
print(page)
text = fake_file_handle.getvalue()
# close open handles
converter.close()
fake_file_handle.close()
return text
def show_pdf(file_path):
with open(file_path, "rb") as f:
base64_pdf = base64.b64encode(f.read()).decode('utf-8')
# pdf_display = f'