Data scraping

Cineb.net scraping

The data scraped in this section are from the website cineb.net, from which I created a data set of movies and TV series.

As shown below, I have created an excel file with contents of said data in it.

Python code

from bs4 import BeautifulSoup
import requests, openpyxl
									
excel = openpyxl.Workbook()
print(excel.sheetnames)
sheet = excel.active
sheet.title = 'Top Rated Movies on CSFD.cz'
print(excel.sheetnames)
sheet.append(['Section', 'Media Type', 'Media Title', 'Year of Release', 'Length', 'Quality', 'Season', 'Episode' ])

try:
    source = requests.get('https://cineb.net/')
    source.raise_for_status

    soup = BeautifulSoup(source.text, 'html.parser')

    # first we want the movies in the featured
    movies = soup.find('ul', class_="film-list-ul").find_all('li')
    section = 'Featured'
    mediatype = 'Movie'
    episode = ''
    season = ''
    print('Section: ' + section)

    for movie in movies:
        name = movie.find('h3', class_="film-name").a.text
        mytext = movie.find('div', class_="fd-infor").text
        mysplit = mytext.split('\n')
        quality = mysplit[1]
        year = mysplit[2]
        length = mysplit[4]
        print('Movie: ' + name + "[" + quality + "] " + year + ' ' + length)
        sheet.append([section, mediatype, name, year, length, quality, season, episode])

    moviesCount = len(movies)
    print(f'Featured movies: {moviesCount}')

    # now we want the movies in the trending section
    movies = soup.find(id="trending-movies").find_all('div', class_="flw-item")
    section = 'Trending'
    mediatype = 'Movie'
    print('Section: ' + section)

    for movie in movies:
        name = movie.find('h3', class_="film-name").a.text
        mytext = movie.find('div', class_="fd-infor").text
        mysplit = mytext.split('\n')
        quality = mysplit[1]
        year = mysplit[2]
        length = mysplit[4]
        print('Movie: ' + name + "[" + quality + "] " + year + ' ' + length)
        sheet.append([section, mediatype, name, year, length, quality, season, episode])

    moviesCount = len(movies)
    print(f'Trending movies: {moviesCount}')

    # now we want the series in the trending section
    movies = soup.find(id="trending-tv").find_all('div', class_="flw-item")
    section = 'Trending'
    mediatype = 'Series'
    print('Section: ' + section)
    year = ''
    length = ''

    for movie in movies:
        name = movie.find('h3', class_="film-name").a.text
        mytext = movie.find('div', class_="fd-infor").text
        mysplit = mytext.split('\n')
        quality = mysplit[1]
        season = mysplit[2]
        episode = mysplit[4]
        print('Series: ' + name + "[" + quality + "] " + season + ' ' + episode)
        sheet.append([section, mediatype, name, year, length, quality, season, episode])

    moviesCount = len(movies)
    print(f'Trending series: {moviesCount}')

except Exception as e:
    print(e)


excel.save('Cineb Movies.xlsx')

Excel file

This is the contents of the Excel file with the scraped data:

Timejobs.com scraping

In this section we are looking at scraped data from timejobs.com

In this code, we are looking for jobs which require python skills and also the ability to exclude skills in which the user might not be proficient in. I have also set a timer in which, if there's case of new job posting python in them, it refreshes every 10 minutes and includes said jobs.

Python code

# in this code, I am trying to find job application with the serach of 'python' 
from bs4 import BeautifulSoup
import requests
import time
	
# here I am trying to find skills that I am not familiar with so that i can rule them out
print('Put some skill that you  not are familiar with')
unfamliar_skill = input('>')
print(f'Filtering out {unfamliar_skill}')
	
# In this segment, I am looking for jobs on this website 
def find_jobs():
	html_text = requests.get('https://www.timesjobs.com/candidate/job-search.html?searchType=personalizedSearch&from=submit&txtKeywords=Java+%2C+Python&txtLocation=').text
	soup = BeautifulSoup(html_text, 'lxml')
	jobs = soup.find_all('li', class_ = "clearfix job-bx wht-shd-bx")
	
	for job in jobs:
		posted_date = job.find('span', class_ = 'sim-posted').span.text
# in this portion of the code, I am trying to find job within a few days and not everything so the files i get back aren't too huge
		if 'few' in posted_date:
			company_name = job.find('h3', class_ = 'joblist-comp-name').text.replace(' ','') 
			skills = job.find('span', class_ = 'srp-skills').text.replace(' ','') 
			more_info = job.header.h2.a['href']
# And here again I am trying to rule out skills I dont know from the job search           
			if unfamliar_skill not in skills:
				posted_date = job.find('span', class_ = 'sim-posted').span.text
	
				print(f"Company Name: {company_name.strip()}")
				print(f"Required Skills: {skills.strip()}")
				print(f"More Info: {more_info}") 
	
				print('')
# the time i want this  program running 
if __name__ == '__main__':
	while True:
		find_jobs()
		time_wait = 10
		print(f'waiting {time_wait} minutes...')
		time.sleep(time_wait * 60)
	

Results of running the code: