turtlebasket/JobSpy
1
0
Fork 0
mirror of https://github.com/Bunsly/JobSpy.git synced 2026-03-04 19:44:30 -08:00
Code Issues Packages Projects Releases Wiki Activity

add offset param & email extraction (#51)

Browse Source 
* add offset param

* [enh]: extract emails
This commit is contained in:
Cullen Watson
2023-09-28 18:11:28 -05:00
committed by GitHub
parent 286b9e1256
commit af07c1ecbd
17 changed files with 1209 additions and 1126 deletions
Download Patch File Download Diff File Expand all files Collapse all files

167
examples/JobSpy_Demo.ipynb Normal file
View File

@@ -0,0 +1,167 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"id": "00a94b47-f47b-420f-ba7e-714ef219c006",
"metadata": {},
"outputs": [],
"source": [
"from jobspy import scrape_jobs\n",
"import pandas as pd\n",
"from IPython.display import display, HTML"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "9f773e6c-d9fc-42cc-b0ef-63b739e78435",
"metadata": {},
"outputs": [],
"source": [
"pd.set_option('display.max_columns', None)\n",
"pd.set_option('display.max_rows', None)\n",
"pd.set_option('display.width', None)\n",
"pd.set_option('display.max_colwidth', 50)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "1253c1f8-9437-492e-9dd3-e7fe51099420",
"metadata": {},
"outputs": [],
"source": [
"# example 1 (no hyperlinks, USA)\n",
"jobs = scrape_jobs(\n",
" site_name=[\"linkedin\"],\n",
" location='san francisco',\n",
" search_term=\"engineer\",\n",
" results_wanted=5,\n",
"\n",
" # use if you want to use a proxy\n",
" # proxy=\"socks5://jobspy:5a4vpWtj4EeJ2hoYzk@us.smartproxy.com:10001\",\n",
" proxy=\"http://jobspy:5a4vpWtj4EeJ2hoYzk@us.smartproxy.com:10001\",\n",
" #proxy=\"https://jobspy:5a4vpWtj4EeJ2hoYzk@us.smartproxy.com:10001\",\n",
")\n",
"display(jobs)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "6a581b2d-f7da-4fac-868d-9efe143ee20a",
"metadata": {},
"outputs": [],
"source": [
"# example 2 - remote USA & hyperlinks\n",
"jobs = scrape_jobs(\n",
" site_name=[\"linkedin\", \"zip_recruiter\", \"indeed\"],\n",
" # location='san francisco',\n",
" search_term=\"software engineer\",\n",
" country_indeed=\"USA\",\n",
" hyperlinks=True,\n",
" is_remote=True,\n",
" results_wanted=5, \n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "fe8289bc-5b64-4202-9a64-7c117c83fd9a",
"metadata": {},
"outputs": [],
"source": [
"# use if hyperlinks=True\n",
"html = jobs.to_html(escape=False)\n",
"# change max-width: 200px to show more or less of the content\n",
"truncate_width = f'<style>.dataframe td {{ max-width: 200px; overflow: hidden; text-overflow: ellipsis; white-space: nowrap; }}</style>{html}'\n",
"display(HTML(truncate_width))"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "951c2fe1-52ff-407d-8bb1-068049b36777",
"metadata": {},
"outputs": [],
"source": [
"# example 3 - with hyperlinks, international - linkedin (no zip_recruiter)\n",
"jobs = scrape_jobs(\n",
" site_name=[\"linkedin\"],\n",
" location='berlin',\n",
" search_term=\"engineer\",\n",
" hyperlinks=True,\n",
" results_wanted=5,\n",
" easy_apply=True\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "1e37a521-caef-441c-8fc2-2eb5b2e7da62",
"metadata": {},
"outputs": [],
"source": [
"# use if hyperlinks=True\n",
"html = jobs.to_html(escape=False)\n",
"# change max-width: 200px to show more or less of the content\n",
"truncate_width = f'<style>.dataframe td {{ max-width: 200px; overflow: hidden; text-overflow: ellipsis; white-space: nowrap; }}</style>{html}'\n",
"display(HTML(truncate_width))"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "0650e608-0b58-4bf5-ae86-68348035b16a",
"metadata": {},
"outputs": [],
"source": [
"# example 4 - international indeed (no zip_recruiter)\n",
"jobs = scrape_jobs(\n",
" site_name=[\"indeed\"],\n",
" search_term=\"engineer\",\n",
" country_indeed = \"China\",\n",
" hyperlinks=True\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "40913ac8-3f8a-4d7e-ac47-afb88316432b",
"metadata": {},
"outputs": [],
"source": [
"# use if hyperlinks=True\n",
"html = jobs.to_html(escape=False)\n",
"# change max-width: 200px to show more or less of the content\n",
"truncate_width = f'<style>.dataframe td {{ max-width: 200px; overflow: hidden; text-overflow: ellipsis; white-space: nowrap; }}</style>{html}'\n",
"display(HTML(truncate_width))"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.5"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

31
examples/JobSpy_Demo.py Normal file
View File

@@ -0,0 +1,31 @@
from jobspy import scrape_jobs
import pandas as pd
jobs: pd.DataFrame = scrape_jobs(
site_name=["indeed", "linkedin", "zip_recruiter"],
search_term="software engineer",
location="Dallas, TX",
results_wanted=50, # be wary the higher it is, the more likey you'll get blocked (rotating proxy should work tho)
country_indeed='USA',
offset=25 # start jobs from an offset (use if search failed and want to continue)
# proxy="http://jobspy:5a4vpWtj8EeJ2hoYzk@ca.smartproxy.com:20001",
)
# formatting for pandas
pd.set_option('display.max_columns', None)
pd.set_option('display.max_rows', None)
pd.set_option('display.width', None)
pd.set_option('display.max_colwidth', 50) # set to 0 to see full job url / desc
# 1: output to console
print(jobs)
# 2: output to .csv
jobs.to_csv('./jobs.csv', index=False)
print('outputted to jobs.csv')
# 3: output to .xlsx
# jobs.to_xlsx('jobs.xlsx', index=False)
# 4: display in Jupyter Notebook (1. pip install jupyter 2. jupyter notebook)
# display(jobs)