From a46b5559e0ce8f953b60296c41d470544c907987 Mon Sep 17 00:00:00 2001 From: Kaif Kohari Date: Sat, 22 Aug 2020 03:28:26 +0530 Subject: [PATCH] Job fetching (#2219) * Adding job scarping algorithm to web programming * Delete fetch_jobs.py * Adding Jobs Scraping to web programming * Add Python type hints Co-authored-by: Christian Clauss --- web_programming/fetch_jobs.py | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) create mode 100644 web_programming/fetch_jobs.py diff --git a/web_programming/fetch_jobs.py b/web_programming/fetch_jobs.py new file mode 100644 index 000000000..888f41294 --- /dev/null +++ b/web_programming/fetch_jobs.py @@ -0,0 +1,23 @@ +""" +Scraping jobs given job title and location from indeed website +""" +from typing import Generator, Tuple + +import requests +from bs4 import BeautifulSoup + +url = "https://www.indeed.co.in/jobs?q=mobile+app+development&l=" + + +def fetch_jobs(location: str = "mumbai") -> Generator[Tuple[str, str], None, None]: + soup = BeautifulSoup(requests.get(url + location).content, "html.parser") + # This attribute finds out all the specifics listed in a job + for job in soup.find_all("div", attrs={"data-tn-component": "organicJob"}): + job_title = job.find("a", attrs={"data-tn-element": "jobTitle"}).text.strip() + company_name = job.find("span", {"class": "company"}).text.strip() + yield job_title, company_name + + +if __name__ == "__main__": + for i, job in enumerate(fetch_jobs("Bangalore"), 1): + print(f"Job {i:>2} is {job[0]} at {job[1]}")