turtlebasket
/
JobSpy
mirror of https://github.com/Bunsly/JobSpy
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Library Migration (#31)

pull/35/head
Zachary Hampton 2023-09-03 07:29:25 -07:00 committed by GitHub
parent 7efece8fe9
commit 153ac35248
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
36 changed files with 3604 additions and 1473 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
.docker/config.json
View File

@ -1,3 +0,0 @@
{
"experimental": "enabled"
}

33
.github/workflows/docker-build.yml vendored
View File

@ -1,33 +0,0 @@
name: Build and Push Docker Image
on:
push:
branches:
- main
jobs:
build:
runs-on: ubuntu-latest
steps:
- name: Checkout code
uses: actions/checkout@v2
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v1
- name: Login to GitHub Docker Registry
uses: docker/login-action@v1
with:
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.DOCKER_TOKEN }}
- name: Build and Push Image
uses: docker/build-push-action@v2
with:
context: .
file: ./Dockerfile
push: true
tags: ghcr.io/${{ github.repository_owner }}/jobspy:latest
platforms: linux/amd64,linux/arm64

33
.github/workflows/publish-to-pypi.yml vendored Normal file
View File

@ -0,0 +1,33 @@
name: Publish Python 🐍 distributions 📦 to PyPI
on: push
jobs:
build-n-publish:
name: Build and publish Python 🐍 distributions 📦 to PyPI
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v3
- name: Set up Python
uses: actions/setup-python@v4
with:
python-version: "3.10"
- name: Install poetry
run: >-
python3 -m
pip install
poetry
--user
- name: Build distribution 📦
run: >-
python3 -m
poetry
build
- name: Publish distribution 📦 to PyPI
if: startsWith(github.ref, 'refs/tags')
uses: pypa/gh-action-pypi-publish@release/v1
with:
password: ${{ secrets.PYPI_API_TOKEN }}

89
.github/workflows/test.yml vendored
View File

@ -1,89 +0,0 @@
name: JobSpy API Tests
on: [push, pull_request]
jobs:
test_api:
runs-on: ubuntu-latest
steps:
- name: Checkout repository
uses: actions/checkout@v2
- name: Set up Python 3.10
uses: actions/setup-python@v2
with:
python-version: '3.10'
- name: Install dependencies
run: pip install -r requirements.txt
- name: Install jq
run: sudo apt-get install jq
- name: Start JobSpy FastAPI app
run: uvicorn main:app --host 0.0.0.0 --port 8000 &
- name: Wait for server to be up
run: |
for i in {1..10}; do
curl -s http://0.0.0.0:8000/api/v1/jobs && break || sleep 1
done
- name: Check health
run: |
health_status=$(curl -L -s -o /dev/null -w "%{http_code}" http://0.0.0.0:8000/health)
if [ "$health_status" != "200" ]; then
echo "Error: Health check failed with status code $health_status"
exit 1
fi
# not checking currently because of bad ip at Github's servers being blocked
# - name: Check HTTP status to POST /api/v1/jobs/
# run: |
# response=$(curl -L -s -X 'POST' -H 'Content-Type: application/json' -d '{
# "site_type": ["indeed", "linkedin"],
# "search_term": "software engineer",
# "location": "austin, tx",
# "distance": 10,
# "job_type": "fulltime",
# "results_wanted": 5
# }' http://0.0.0.0:8000/api/v1/jobs -w "%{http_code}")
#
# status_code="${response: -3}"
# echo "Received status code: $status_code"
#
# if [ "$status_code" != "200" ]; then
# echo "Error: Expected status code 200, but got $status_code"
# exit 1
# fi
#
# echo "${response::-3}" > response.json
# cat response.json
#
# - name: Check error field in response
# run: |
# global_error=$(jq '.error' response.json)
# indeed_error=$(jq '.indeed.error' response.json)
# linkedin_error=$(jq '.linkedin.error' response.json)
#
# if [[ "$indeed_error" != "null" || "$linkedin_error" != "null" ]]; then
# echo "Error found in response:"
# echo "Global Error: $global_error"
# echo "Indeed Error: $indeed_error"
# echo "LinkedIn Error: $linkedin_error"
# exit 1
# fi
#
# - name: Verify returned_results in response
# run: |
# indeed_results=$(jq '.indeed.returned_results' response.json)
# linkedin_results=$(jq '.linkedin.returned_results' response.json)
#
# if [[ $indeed_results -ne 5 || $linkedin_results -ne 5 ]]; then
# echo "Mismatch in results_wanted and returned_results:"
# echo "Indeed: Expected 5, Got $indeed_results"
# echo "LinkedIn: Expected 5, Got $linkedin_results"
# exit 1
# fi

3
.gitignore vendored
View File

@ -5,4 +5,5 @@
**/__pycache__/ **/__pycache__/
*.pyc *.pyc
.env .env
client_secret.json dist
/.ipynb_checkpoints/

13
.vscode/launch.json vendored
View File

@ -1,13 +0,0 @@
{
"version": "0.2.0",
"configurations": [
{
"name": "Python: Module",
"type": "python",
"request": "launch",
"module": "uvicorn",
"args": ["main:app","--reload"]
}
]
}

15
Dockerfile
View File

@ -1,15 +0,0 @@
FROM python:3.10-slim
WORKDIR /app
COPY . /app
RUN apt-get update && \
apt-get install -y jq && \
pip install --no-cache-dir -r requirements.txt
EXPOSE 8000
ENV PORT=8000
CMD sh -c "uvicorn main:app --host 0.0.0.0 --port $PORT"

702
JobSpy_Demo.ipynb Normal file
View File

@ -0,0 +1,702 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 2,
"id": "c3f21577-477d-451e-9914-5d67e8a89075",
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>site</th>\n",
" <th>title</th>\n",
" <th>company_name</th>\n",
" <th>city</th>\n",
" <th>state</th>\n",
" <th>job_type</th>\n",
" <th>interval</th>\n",
" <th>min_amount</th>\n",
" <th>max_amount</th>\n",
" <th>job_url</th>\n",
" <th>description</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>indeed</td>\n",
" <td>Firmware Engineer</td>\n",
" <td>Advanced Motion Controls</td>\n",
" <td>Camarillo</td>\n",
" <td>CA</td>\n",
" <td>fulltime</td>\n",
" <td>yearly</td>\n",
" <td>145000</td>\n",
" <td>110000</td>\n",
" <td>https://www.indeed.com/viewjob?jk=a2e7077fdd3c...</td>\n",
" <td>We are looking for an experienced Firmware Eng...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>indeed</td>\n",
" <td>Computer Engineer</td>\n",
" <td>Honeywell</td>\n",
" <td></td>\n",
" <td>None</td>\n",
" <td>fulltime</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>https://www.indeed.com/viewjob?jk=5a1da623ee75...</td>\n",
" <td>Join a team recognized for leadership, innovat...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>indeed</td>\n",
" <td>Software Engineer</td>\n",
" <td>Splunk</td>\n",
" <td>Remote</td>\n",
" <td>None</td>\n",
" <td>fulltime</td>\n",
" <td>yearly</td>\n",
" <td>159500</td>\n",
" <td>116000</td>\n",
" <td>https://www.indeed.com/viewjob?jk=155495ca3f46...</td>\n",
" <td>A little about us. Splunk is the key to enterp...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>indeed</td>\n",
" <td>Development Operations Engineer</td>\n",
" <td>Stratacache</td>\n",
" <td>Dayton</td>\n",
" <td>OH</td>\n",
" <td>fulltime</td>\n",
" <td>yearly</td>\n",
" <td>90000</td>\n",
" <td>83573</td>\n",
" <td>https://www.indeed.com/viewjob?jk=77cf3540c06e...</td>\n",
" <td>Stratacache, Inc. delivers in-store retail exp...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>indeed</td>\n",
" <td>Computer Engineer</td>\n",
" <td>Honeywell</td>\n",
" <td></td>\n",
" <td>None</td>\n",
" <td>fulltime</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>https://www.indeed.com/viewjob?jk=7fadbb7c936f...</td>\n",
" <td>Join a team recognized for leadership, innovat...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>indeed</td>\n",
" <td>Full Stack Developer</td>\n",
" <td>Reinventing Geospatial, Inc. (RGi)</td>\n",
" <td>Herndon</td>\n",
" <td>VA</td>\n",
" <td>fulltime</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>https://www.indeed.com/viewjob?jk=11b2b5b0dd44...</td>\n",
" <td>Job Highlights As a Full Stack Software Engine...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>indeed</td>\n",
" <td>Software Engineer</td>\n",
" <td>Workiva</td>\n",
" <td>Remote</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>yearly</td>\n",
" <td>134000</td>\n",
" <td>79000</td>\n",
" <td>https://www.indeed.com/viewjob?jk=ec3ab6eb9253...</td>\n",
" <td>Are you ready to embark on an exciting journey...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>indeed</td>\n",
" <td>Senior Software Engineer</td>\n",
" <td>SciTec</td>\n",
" <td>Boulder</td>\n",
" <td>CO</td>\n",
" <td>fulltime</td>\n",
" <td>yearly</td>\n",
" <td>164000</td>\n",
" <td>93000</td>\n",
" <td>https://www.indeed.com/viewjob?jk=781e4cf0cf6d...</td>\n",
" <td>SciTec has been awarded multiple government co...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>indeed</td>\n",
" <td>Software Engineer</td>\n",
" <td>Microsoft</td>\n",
" <td></td>\n",
" <td>None</td>\n",
" <td>fulltime</td>\n",
" <td>yearly</td>\n",
" <td>182600</td>\n",
" <td>94300</td>\n",
" <td>https://www.indeed.com/viewjob?jk=21e05b9e9d96...</td>\n",
" <td>At Microsoft we are seeking people who have a ...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>indeed</td>\n",
" <td>Software Engineer</td>\n",
" <td>Avalon Healthcare Solutions</td>\n",
" <td>Remote</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>https://www.indeed.com/viewjob?jk=da35b9bb74a0...</td>\n",
" <td>Avalon Healthcare Solutions, headquartered in ...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>linkedin</td>\n",
" <td>Software Engineer</td>\n",
" <td>Fieldguide</td>\n",
" <td>San Francisco</td>\n",
" <td>CA</td>\n",
" <td>fulltime</td>\n",
" <td>yearly</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>https://www.linkedin.com/jobs/view/3696158160</td>\n",
" <td>About us:Fieldguide is establishing a new stat...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>linkedin</td>\n",
" <td>Software Engineer - Early Career</td>\n",
" <td>Lockheed Martin</td>\n",
" <td>Sunnyvale</td>\n",
" <td>CA</td>\n",
" <td>fulltime</td>\n",
" <td>yearly</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>https://www.linkedin.com/jobs/view/3693012711</td>\n",
" <td>Description:By bringing together people that u...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>linkedin</td>\n",
" <td>Software Engineer - Early Career</td>\n",
" <td>Lockheed Martin</td>\n",
" <td>Edwards</td>\n",
" <td>CA</td>\n",
" <td>fulltime</td>\n",
" <td>yearly</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>https://www.linkedin.com/jobs/view/3700669785</td>\n",
" <td>Description:By bringing together people that u...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>linkedin</td>\n",
" <td>Software Engineer - Early Career</td>\n",
" <td>Lockheed Martin</td>\n",
" <td>Fort Worth</td>\n",
" <td>TX</td>\n",
" <td>fulltime</td>\n",
" <td>yearly</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>https://www.linkedin.com/jobs/view/3701775201</td>\n",
" <td>Description:By bringing together people that u...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>linkedin</td>\n",
" <td>Software Engineer - Early Career</td>\n",
" <td>Lockheed Martin</td>\n",
" <td>Fort Worth</td>\n",
" <td>TX</td>\n",
" <td>fulltime</td>\n",
" <td>yearly</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>https://www.linkedin.com/jobs/view/3701772329</td>\n",
" <td>Description:By bringing together people that u...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>linkedin</td>\n",
" <td>Software Engineer - Early Career</td>\n",
" <td>Lockheed Martin</td>\n",
" <td>Fort Worth</td>\n",
" <td>TX</td>\n",
" <td>fulltime</td>\n",
" <td>yearly</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>https://www.linkedin.com/jobs/view/3701769637</td>\n",
" <td>Description:By bringing together people that u...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>linkedin</td>\n",
" <td>Software Engineer</td>\n",
" <td>SpiderOak</td>\n",
" <td>Austin</td>\n",
" <td>TX</td>\n",
" <td>fulltime</td>\n",
" <td>yearly</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>https://www.linkedin.com/jobs/view/3707174719</td>\n",
" <td>We're only as strong as our weakest link.In th...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>linkedin</td>\n",
" <td>Software Engineer - Early Career</td>\n",
" <td>Lockheed Martin</td>\n",
" <td>Fort Worth</td>\n",
" <td>TX</td>\n",
" <td>fulltime</td>\n",
" <td>yearly</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>https://www.linkedin.com/jobs/view/3701770659</td>\n",
" <td>Description:By bringing together people that u...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>linkedin</td>\n",
" <td>Full-Stack Software Engineer</td>\n",
" <td>Rain</td>\n",
" <td>New York</td>\n",
" <td>NY</td>\n",
" <td>fulltime</td>\n",
" <td>yearly</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>https://www.linkedin.com/jobs/view/3696158877</td>\n",
" <td>Rain’s mission is to create the fastest and ea...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>linkedin</td>\n",
" <td>Software Engineer</td>\n",
" <td>Nike</td>\n",
" <td>Portland</td>\n",
" <td>OR</td>\n",
" <td>contract</td>\n",
" <td>yearly</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>https://www.linkedin.com/jobs/view/3693340247</td>\n",
" <td>Work options: FlexibleWe consider remote, on-p...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>zip_recruiter</td>\n",
" <td>(USA) Software Engineer III - Prototype Engine...</td>\n",
" <td>Walmart</td>\n",
" <td>Dallas</td>\n",
" <td>TX</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>https://click.appcast.io/track/hcgsw4k?cs=ngp&amp;...</td>\n",
" <td>We are currently seeking a highly skilled and ...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>21</th>\n",
" <td>zip_recruiter</td>\n",
" <td>Software Engineer - New Grad</td>\n",
" <td>ZipRecruiter</td>\n",
" <td>Santa Monica</td>\n",
" <td>CA</td>\n",
" <td>fulltime</td>\n",
" <td>yearly</td>\n",
" <td>130000</td>\n",
" <td>150000</td>\n",
" <td>https://www.ziprecruiter.com/jobs/ziprecruiter...</td>\n",
" <td>We offer a hybrid work environment. Most US-ba...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>zip_recruiter</td>\n",
" <td>Software Developer</td>\n",
" <td>Robert Half</td>\n",
" <td>Corpus Christi</td>\n",
" <td>TX</td>\n",
" <td>fulltime</td>\n",
" <td>yearly</td>\n",
" <td>105000</td>\n",
" <td>115000</td>\n",
" <td>https://www.ziprecruiter.com/jobs/robert-half-...</td>\n",
" <td>Robert Half has an opening for a Software Deve...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23</th>\n",
" <td>zip_recruiter</td>\n",
" <td>Software Engineer</td>\n",
" <td>Advantage Technical</td>\n",
" <td>Ontario</td>\n",
" <td>CA</td>\n",
" <td>fulltime</td>\n",
" <td>yearly</td>\n",
" <td>100000</td>\n",
" <td>150000</td>\n",
" <td>https://www.ziprecruiter.com/jobs/advantage-te...</td>\n",
" <td>New career opportunity available with major Ma...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24</th>\n",
" <td>zip_recruiter</td>\n",
" <td>Software Developer</td>\n",
" <td>Robert Half</td>\n",
" <td>Tucson</td>\n",
" <td>AZ</td>\n",
" <td>temporary</td>\n",
" <td>hourly</td>\n",
" <td>47</td>\n",
" <td>55</td>\n",
" <td>https://www.ziprecruiter.com/jobs/robert-half-...</td>\n",
" <td>Robert Half is accepting inquiries for a SQL S...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25</th>\n",
" <td>zip_recruiter</td>\n",
" <td>Full Stack Software Engineer</td>\n",
" <td>ZipRecruiter</td>\n",
" <td>Phoenix</td>\n",
" <td>AZ</td>\n",
" <td>fulltime</td>\n",
" <td>yearly</td>\n",
" <td>105000</td>\n",
" <td>145000</td>\n",
" <td>https://www.ziprecruiter.com/jobs/ziprecruiter...</td>\n",
" <td>We offer a hybrid work environment. Most US-ba...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>26</th>\n",
" <td>zip_recruiter</td>\n",
" <td>Software Developer IV</td>\n",
" <td>Kforce Inc.</td>\n",
" <td>Mountain View</td>\n",
" <td>CA</td>\n",
" <td>contract</td>\n",
" <td>hourly</td>\n",
" <td>55</td>\n",
" <td>75</td>\n",
" <td>https://www.kforce.com/Jobs/job.aspx?job=1696~...</td>\n",
" <td>Kforce has a client that is seeking a Software...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>27</th>\n",
" <td>zip_recruiter</td>\n",
" <td>Software Developer | Onsite | Omaha, NE - Omaha</td>\n",
" <td>OneStaff Medical</td>\n",
" <td>Omaha</td>\n",
" <td>NE</td>\n",
" <td>fulltime</td>\n",
" <td>yearly</td>\n",
" <td>60000</td>\n",
" <td>110000</td>\n",
" <td>https://www.ziprecruiter.com/jobs/onestaff-med...</td>\n",
" <td>Company Description: We are looking for a well...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>28</th>\n",
" <td>zip_recruiter</td>\n",
" <td>Senior Software Engineer</td>\n",
" <td>RightStaff, Inc.</td>\n",
" <td>Dallas</td>\n",
" <td>TX</td>\n",
" <td>fulltime</td>\n",
" <td>yearly</td>\n",
" <td>120000</td>\n",
" <td>180000</td>\n",
" <td>https://www.ziprecruiter.com/jobs/rightstaff-i...</td>\n",
" <td>Job Description:We are seeking a talented and ...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>29</th>\n",
" <td>zip_recruiter</td>\n",
" <td>Software Developer - .Net Core - 12886</td>\n",
" <td>Walker Elliott</td>\n",
" <td>Dallas</td>\n",
" <td>TX</td>\n",
" <td>fulltime</td>\n",
" <td>yearly</td>\n",
" <td>105000</td>\n",
" <td>130000</td>\n",
" <td>https://www.ziprecruiter.com/jobs/walker-ellio...</td>\n",
" <td>Our highly successful DFW based client has bee...</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" site title \\\n",
"0 indeed Firmware Engineer \n",
"1 indeed Computer Engineer \n",
"2 indeed Software Engineer \n",
"3 indeed Development Operations Engineer \n",
"4 indeed Computer Engineer \n",
"5 indeed Full Stack Developer \n",
"6 indeed Software Engineer \n",
"7 indeed Senior Software Engineer \n",
"8 indeed Software Engineer \n",
"9 indeed Software Engineer \n",
"10 linkedin Software Engineer \n",
"11 linkedin Software Engineer - Early Career \n",
"12 linkedin Software Engineer - Early Career \n",
"13 linkedin Software Engineer - Early Career \n",
"14 linkedin Software Engineer - Early Career \n",
"15 linkedin Software Engineer - Early Career \n",
"16 linkedin Software Engineer \n",
"17 linkedin Software Engineer - Early Career \n",
"18 linkedin Full-Stack Software Engineer \n",
"19 linkedin Software Engineer \n",
"20 zip_recruiter (USA) Software Engineer III - Prototype Engine... \n",
"21 zip_recruiter Software Engineer - New Grad \n",
"22 zip_recruiter Software Developer \n",
"23 zip_recruiter Software Engineer \n",
"24 zip_recruiter Software Developer \n",
"25 zip_recruiter Full Stack Software Engineer \n",
"26 zip_recruiter Software Developer IV \n",
"27 zip_recruiter Software Developer | Onsite | Omaha, NE - Omaha \n",
"28 zip_recruiter Senior Software Engineer \n",
"29 zip_recruiter Software Developer - .Net Core - 12886 \n",
"\n",
" company_name city state job_type \\\n",
"0 Advanced Motion Controls Camarillo CA fulltime \n",
"1 Honeywell None fulltime \n",
"2 Splunk Remote None fulltime \n",
"3 Stratacache Dayton OH fulltime \n",
"4 Honeywell None fulltime \n",
"5 Reinventing Geospatial, Inc. (RGi) Herndon VA fulltime \n",
"6 Workiva Remote None None \n",
"7 SciTec Boulder CO fulltime \n",
"8 Microsoft None fulltime \n",
"9 Avalon Healthcare Solutions Remote None None \n",
"10 Fieldguide San Francisco CA fulltime \n",
"11 Lockheed Martin Sunnyvale CA fulltime \n",
"12 Lockheed Martin Edwards CA fulltime \n",
"13 Lockheed Martin Fort Worth TX fulltime \n",
"14 Lockheed Martin Fort Worth TX fulltime \n",
"15 Lockheed Martin Fort Worth TX fulltime \n",
"16 SpiderOak Austin TX fulltime \n",
"17 Lockheed Martin Fort Worth TX fulltime \n",
"18 Rain New York NY fulltime \n",
"19 Nike Portland OR contract \n",
"20 Walmart Dallas TX None \n",
"21 ZipRecruiter Santa Monica CA fulltime \n",
"22 Robert Half Corpus Christi TX fulltime \n",
"23 Advantage Technical Ontario CA fulltime \n",
"24 Robert Half Tucson AZ temporary \n",
"25 ZipRecruiter Phoenix AZ fulltime \n",
"26 Kforce Inc. Mountain View CA contract \n",
"27 OneStaff Medical Omaha NE fulltime \n",
"28 RightStaff, Inc. Dallas TX fulltime \n",
"29 Walker Elliott Dallas TX fulltime \n",
"\n",
" interval min_amount max_amount \\\n",
"0 yearly 145000 110000 \n",
"1 None None None \n",
"2 yearly 159500 116000 \n",
"3 yearly 90000 83573 \n",
"4 None None None \n",
"5 None None None \n",
"6 yearly 134000 79000 \n",
"7 yearly 164000 93000 \n",
"8 yearly 182600 94300 \n",
"9 None None None \n",
"10 yearly None None \n",
"11 yearly None None \n",
"12 yearly None None \n",
"13 yearly None None \n",
"14 yearly None None \n",
"15 yearly None None \n",
"16 yearly None None \n",
"17 yearly None None \n",
"18 yearly None None \n",
"19 yearly None None \n",
"20 None None None \n",
"21 yearly 130000 150000 \n",
"22 yearly 105000 115000 \n",
"23 yearly 100000 150000 \n",
"24 hourly 47 55 \n",
"25 yearly 105000 145000 \n",
"26 hourly 55 75 \n",
"27 yearly 60000 110000 \n",
"28 yearly 120000 180000 \n",
"29 yearly 105000 130000 \n",
"\n",
" job_url \\\n",
"0 https://www.indeed.com/viewjob?jk=a2e7077fdd3c... \n",
"1 https://www.indeed.com/viewjob?jk=5a1da623ee75... \n",
"2 https://www.indeed.com/viewjob?jk=155495ca3f46... \n",
"3 https://www.indeed.com/viewjob?jk=77cf3540c06e... \n",
"4 https://www.indeed.com/viewjob?jk=7fadbb7c936f... \n",
"5 https://www.indeed.com/viewjob?jk=11b2b5b0dd44... \n",
"6 https://www.indeed.com/viewjob?jk=ec3ab6eb9253... \n",
"7 https://www.indeed.com/viewjob?jk=781e4cf0cf6d... \n",
"8 https://www.indeed.com/viewjob?jk=21e05b9e9d96... \n",
"9 https://www.indeed.com/viewjob?jk=da35b9bb74a0... \n",
"10 https://www.linkedin.com/jobs/view/3696158160 \n",
"11 https://www.linkedin.com/jobs/view/3693012711 \n",
"12 https://www.linkedin.com/jobs/view/3700669785 \n",
"13 https://www.linkedin.com/jobs/view/3701775201 \n",
"14 https://www.linkedin.com/jobs/view/3701772329 \n",
"15 https://www.linkedin.com/jobs/view/3701769637 \n",
"16 https://www.linkedin.com/jobs/view/3707174719 \n",
"17 https://www.linkedin.com/jobs/view/3701770659 \n",
"18 https://www.linkedin.com/jobs/view/3696158877 \n",
"19 https://www.linkedin.com/jobs/view/3693340247 \n",
"20 https://click.appcast.io/track/hcgsw4k?cs=ngp&... \n",
"21 https://www.ziprecruiter.com/jobs/ziprecruiter... \n",
"22 https://www.ziprecruiter.com/jobs/robert-half-... \n",
"23 https://www.ziprecruiter.com/jobs/advantage-te... \n",
"24 https://www.ziprecruiter.com/jobs/robert-half-... \n",
"25 https://www.ziprecruiter.com/jobs/ziprecruiter... \n",
"26 https://www.kforce.com/Jobs/job.aspx?job=1696~... \n",
"27 https://www.ziprecruiter.com/jobs/onestaff-med... \n",
"28 https://www.ziprecruiter.com/jobs/rightstaff-i... \n",
"29 https://www.ziprecruiter.com/jobs/walker-ellio... \n",
"\n",
" description \n",
"0 We are looking for an experienced Firmware Eng... \n",
"1 Join a team recognized for leadership, innovat... \n",
"2 A little about us. Splunk is the key to enterp... \n",
"3 Stratacache, Inc. delivers in-store retail exp... \n",
"4 Join a team recognized for leadership, innovat... \n",
"5 Job Highlights As a Full Stack Software Engine... \n",
"6 Are you ready to embark on an exciting journey... \n",
"7 SciTec has been awarded multiple government co... \n",
"8 At Microsoft we are seeking people who have a ... \n",
"9 Avalon Healthcare Solutions, headquartered in ... \n",
"10 About us:Fieldguide is establishing a new stat... \n",
"11 Description:By bringing together people that u... \n",
"12 Description:By bringing together people that u... \n",
"13 Description:By bringing together people that u... \n",
"14 Description:By bringing together people that u... \n",
"15 Description:By bringing together people that u... \n",
"16 We're only as strong as our weakest link.In th... \n",
"17 Description:By bringing together people that u... \n",
"18 Rain’s mission is to create the fastest and ea... \n",
"19 Work options: FlexibleWe consider remote, on-p... \n",
"20 We are currently seeking a highly skilled and ... \n",
"21 We offer a hybrid work environment. Most US-ba... \n",
"22 Robert Half has an opening for a Software Deve... \n",
"23 New career opportunity available with major Ma... \n",
"24 Robert Half is accepting inquiries for a SQL S... \n",
"25 We offer a hybrid work environment. Most US-ba... \n",
"26 Kforce has a client that is seeking a Software... \n",
"27 Company Description: We are looking for a well... \n",
"28 Job Description:We are seeking a talented and ... \n",
"29 Our highly successful DFW based client has bee... "
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"from jobscrape import scrape_jobs\n",
"import pandas as pd\n",
"\n",
"jobs: pd.DataFrame = scrape_jobs(\n",
" site_name=[\"indeed\", \"linkedin\", \"zip_recruiter\"],\n",
" search_term=\"software engineer\",\n",
" results_wanted=10\n",
")\n",
"\n",
"if jobs.empty:\n",
" print(\"No jobs found.\")\n",
"else:\n",
"\n",
" #1 print\n",
" 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) # set to 0 to see full job url / desc\n",
" print(jobs)\n",
"\n",
" #2 display in Jupyter Notebook\n",
" display(jobs)\n",
"\n",
" #3 output to csv\n",
" jobs.to_csv('jobs.csv', index=False)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "efd667ef-fdf0-452a-b5e5-ce6825755be7",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "1574dc17-0a42-4655-964f-5c03a6d3deb0",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "my-poetry-env",
"language": "python",
"name": "my-poetry-env"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.11"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

290
README.md
View File

@ -1,240 +1,100 @@
# JobSpy AIO Scraper # JobSpy
**JobSpy** is a simple, yet comprehensive, job scraping library.
## Features ## Features
- Scrapes job postings from **LinkedIn**, **Indeed** & **ZipRecruiter** simultaneously - Scrapes job postings from **LinkedIn**, **Indeed** & **ZipRecruiter** simultaneously
- Returns jobs as JSON or CSV with title, location, company, description & other data - Aggregates the job postings in a Pandas DataFrame
- Imports directly into **Google Sheets**
- Optional JWT authorization
![jobspy_gsheet](https://github.com/cullenwatson/JobSpy/assets/78247585/9f0a997c-4e33-4167-b04e-31ab1f606edb) ### Installation
`pip install jobscrape`
_Python version >= [3.10](https://www.python.org/downloads/release/python-3100/) required_
### Usage
```python
from jobscrape import scrape_jobs
import pandas as pd
jobs: pd.DataFrame = scrape_jobs(
site_name=["indeed", "linkedin", "zip_recruiter"],
search_term="software engineer",
results_wanted=10
)
if jobs.empty:
print("No jobs found.")
else:
#1 print
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
print(jobs)
#2 display in Jupyter Notebook
display(jobs)
#3 output to csv
jobs.to_csv('jobs.csv', index=False)
```
### Output
```
site title company_name city state job_type interval min_amount max_amount job_url description
indeed Software Engineer AMERICAN SYSTEMS Arlington VA None yearly 200000 150000 https://www.indeed.com/viewjob?jk=5e409e577046... THIS POSITION COMES WITH A 10K SIGNING BONUS! ...
indeed Senior Software Engineer TherapyNotes.com Philadelphia PA fulltime yearly 135000 110000 https://www.indeed.com/viewjob?jk=da39574a40cb... About Us TherapyNotes is the national leader i...
linkedin Software Engineer - Early Career Lockheed Martin Sunnyvale CA fulltime yearly None None https://www.linkedin.com/jobs/view/3693012711 Description:By bringing together people that u...
linkedin Full-Stack Software Engineer Rain New York NY fulltime yearly None None https://www.linkedin.com/jobs/view/3696158877 Rain’s mission is to create the fastest and ea...
zip_recruiter Software Engineer - New Grad ZipRecruiter Santa Monica CA fulltime yearly 130000 150000 https://www.ziprecruiter.com/jobs/ziprecruiter... We offer a hybrid work environment. Most US-ba...
zip_recruiter Software Developer TEKsystems Phoenix AZ fulltime hourly 65 75 https://www.ziprecruiter.com/jobs/teksystems-0... Top Skills' Details• 6 years of Java developme.```
```
### Parameters for `scrape_jobs()`
### API
POST `/api/v1/jobs/`
### Request Schema
```plaintext ```plaintext
Required Required
├── site_type (List[enum]): linkedin, zip_recruiter, indeed ├── site_type (List[enum]): linkedin, zip_recruiter, indeed
└── search_term (str) └── search_term (str)
Optional Optional
├── location (int) ├── location (int)
├── distance (int) ├── distance (int): in miles
├── job_type (enum): fulltime, parttime, internship, contract ├── job_type (enum): fulltime, parttime, internship, contract
├── is_remote (bool) ├── is_remote (bool)
├── results_wanted (int): per site_type ├── results_wanted (int): number of job results to retrieve for each site specified in 'site_type'
├── easy_apply (bool): only for linkedin ├── easy_apply (bool): filters for jobs on LinkedIn that have the 'Easy Apply' option
└── output_format (enum): json, csv, gsheet
```
### Request Example
```json
"site_type": ["indeed", "linkedin"],
"search_term": "software engineer",
"location": "austin, tx",
"distance": 10,
"job_type": "fulltime",
"results_wanted": 15
"output_format": "gsheet"
``` ```
### Response Schema ### Response Schema
```plaintext ```plaintext
site_type (enum): JobPost
JobResponse ├── title (str)
├── success (bool) ├── company_name (str)
├── error (str) ├── job_url (str)
├── jobs (List[JobPost]) ├── location (object)
│ └── JobPost │ ├── country (str)
│ ├── title (str) │ ├── city (str)
│ ├── company_name (str) │ ├── state (str)
│ ├── job_url (str) ├── description (str)
│ ├── location (object) ├── job_type (enum)
│ │ ├── country (str) ├── compensation (object)
│ │ ├── city (str) │ ├── interval (CompensationInterval): yearly, monthly, weekly, daily, hourly
│ │ ├── state (str) │ ├── min_amount (float)
│ ├── description (str) │ ├── max_amount (float)
│ ├── job_type (enum) │ └── currency (str)
│ ├── compensation (object) └── date_posted (datetime)
│ │ ├── interval (CompensationInterval): yearly, monthly, weekly, daily, hourly
│ │ ├── min_amount (float)
│ │ ├── max_amount (float)
│ │ └── currency (str)
│ └── date_posted (datetime)
│
├── total_results (int)
└── returned_results (int)
```
### Response Example (GOOGLE SHEETS)
```json
{
"status": "Successfully uploaded to Google Sheets",
"error": null,
"linkedin": null,
"indeed": null,
"zip_recruiter": null
}
```
### Response Example (JSON)
```json
{
"indeed": {
"success": true,
"error": null,
"jobs": [
{
"title": "Software Engineer",
"company_name": "INTEL",
"job_url": "https://www.indeed.com/jobs/viewjob?jk=a2cfbb98d2002228",
"location": {
"country": "USA",
"city": "Austin",
"state": "TX",
},
"description": "Job Description Designs, develops, tests, and debugs..."
"job_type": "fulltime",
"compensation": {
"interval": "yearly",
"min_amount": 209760.0,
"max_amount": 139480.0,
"currency": "USD"
},
"date_posted": "2023-08-18T00:00:00"
}, ...
],
"total_results": 845,
"returned_results": 15
},
"linkedin": {
"success": true,
"error": null,
"jobs": [
{
"title": "Software Engineer 1",
"company_name": "Public Partnerships | PPL",
"job_url": "https://www.linkedin.com/jobs/view/3690013792",
"location": {
"country": "USA",
"city": "Austin",
"state": "TX",
},
"description": "Public Partnerships LLC supports individuals with disabilities..."
"job_type": null,
"compensation": null,
"date_posted": "2023-07-31T00:00:00"
}, ...
],
"total_results": 2000,
"returned_results": 15
}
}
```
### Response Example (CSV)
```
Site, Title, Company Name, Job URL, Country, City, State, Job Type, Compensation Interval, Min Amount, Max Amount, Currency, Date Posted, Description
indeed, Software Engineer, INTEL, https://www.indeed.com/jobs/viewjob?jk=a2cfbb98d2002228, USA, Austin, TX, fulltime, yearly, 209760.0, 139480.0, USD, 2023-08-18T00:00:00, Job Description Designs...
linkedin, Software Engineer 1, Public Partnerships | PPL, https://www.linkedin.com/jobs/view/3690013792, USA, Austin, TX, , , , , , 2023-07-31T00:00:00, Public Partnerships LLC supports...
``` ```
## Installation
### Docker Setup
_Requires [Docker Desktop](https://www.docker.com/products/docker-desktop/)_
[JobSpy API Image](https://ghcr.io/cullenwatson/jobspy:latest) is continuously updated and available on GitHub Container Registry. ### FAQ
To pull the Docker image: #### Encountering issues with your queries?
```bash Try reducing the number of `results_wanted` and/or broadening the filters. If problems persist, please submit an issue.
docker pull ghcr.io/cullenwatson/jobspy:latest
```
#### Params #### Received a response code 429?
This means you've been blocked by the job board site for sending too many requests. Consider waiting a few seconds, or try using a VPN. Proxy support coming soon.
By default:
* Port: `8000`
* Google sheet name: `JobSpy`
* Relative path of `client_secret.json` (for Google Sheets, see below to obtain)
To run the image with these default settings, use:
Example (Cmd Prompt - Windows):
```bash
docker run -v %cd%/client_secret.json:/app/client_secret.json -p 8000:8000 ghcr.io/cullenwatson/jobspy
```
Example (Unix):
```bash
docker run -v $(pwd)/client_secret.json:/app/client_secret.json -p 8000:8000 ghcr.io/cullenwatson/jobspy
```
#### Using custom params
Example:
* Port: `8030`
* Google sheet name: `CustomName`
* Absolute path of `client_secret.json`: `C:\config\client_secret.json`
To pass these custom params:
```bash
docker run -v C:\config\client_secret.json:/app/client_secret.json -e GSHEET_NAME=CustomName -e PORT=8030 -p 8030:8030 ghcr.io/cullenwatson/jobspy
```
### Python installation (alternative to Docker)
_Python version >= [3.10](https://www.python.org/downloads/release/python-3100/) required_
1. Clone this repository `git clone https://github.com/cullenwatson/jobspy`
2. Install the dependencies with `pip install -r requirements.txt`
4. Run the server with `uvicorn main:app --reload`
### Google Sheets Setup
#### Obtaining an Access Key: [Video Guide](https://youtu.be/w533wJuilao?si=5u3m50pRtdhqkg9Z&t=43)
* Enable the [Google Sheets & Google Drive API](https://console.cloud.google.com/)
* Create credentials -> service account -> create & continue
* Select role -> basic: editor -> done
* Click on the email you just created in the service account list
* Go to the Keys tab -> add key -> create new key -> JSON -> Create
#### Using the key in the repo
* Copy the key file into the JobSpy repo as `client_secret.json`
* Go to [my template sheet](https://docs.google.com/spreadsheets/d/1mOgb-ZGZy_YIhnW9OCqIVvkFwiKFvhMBjNcbakW7BLo/edit?usp=sharing): File -> Make a Copy -> Rename to JobSpy
* Share the Google sheet with the email located in the field `client_email` in the `client_secret.json` above with editor rights
* If you changed the name of the sheet:
- Python install: add `.env` in the repo and add `GSHEET_NAME` param with the sheet name as the value, e.g. `GSHEET_NAME=CustomName`
- Docker install: use custom param `-e GSHEET_NAME=CustomName` in `docker run` (see above)
### How to call the API
#### [Postman](https://www.postman.com/downloads/) (preferred):
To use Postman:
1. Locate the files in the `/postman/` directory.
2. Import the Postman collection and environment JSON files.
#### Swagger UI:
Or you can call the API with the interactive documentation at [localhost:8000/docs](http://localhost:8000/docs).
## FAQ
### I'm having issues with my queries. What should I do?
Try reducing the number of `results_wanted` and/or broadening the filters. If issues still persist, feel free to submit an issue.
### I'm getting response code 429. What should I do?
You have been blocked by the job board site for sending too many requests. Wait a couple seconds or use a VPN.
### How to enable auth?
Change `AUTH_REQUIRED` in `/settings.py` to `True`
The auth uses [supabase](https://supabase.com). Create a project with a `users` table and disable RLS.
<img src="https://github.com/cullenwatson/jobspy/assets/78247585/03af18e1-5386-49ad-a2cf-d34232d9d747" width="500">
Add these three environment variables:
- `SUPABASE_URL`: go to project settings -> API -> Project URL
- `SUPABASE_KEY`: go to project settings -> API -> service_role secret
- `JWT_SECRET_KEY` - type `openssl rand -hex 32` in terminal to create a 32 byte secret key
Use these endpoints to register and get an access token:
![image](https://github.com/cullenwatson/jobspy/assets/78247585/c84c33ec-1fe8-4152-9c8c-6c4334aecfc3)

9
api/__init__.py
View File

@ -1,9 +0,0 @@
from fastapi import APIRouter
from api.auth import router as auth_router
from .v1 import router as v1_router
router = APIRouter(
prefix="/api",
)
router.include_router(v1_router)
router.include_router(auth_router)

8
api/auth/__init__.py
View File

@ -1,8 +0,0 @@
from fastapi import APIRouter
from api.auth.token import router as token_router
from api.auth.register import router as register_router
router = APIRouter(prefix="/auth", tags=["auth"])
router.include_router(token_router)
router.include_router(register_router)

65
api/auth/auth_utils.py
View File

@ -1,65 +0,0 @@
from datetime import datetime, timedelta
from jose import jwt, JWTError
from fastapi import HTTPException, status, Depends
from fastapi.security import OAuth2PasswordBearer
from api.core.users import TokenData
from api.auth.db_utils import UserInDB, get_user
oauth2_scheme = OAuth2PasswordBearer(tokenUrl="/api/auth/token")
def create_access_token(data: dict) -> str:
"""
Creates a JWT token based on the data provided.
:param data
:return: encoded_jwt
"""
to_encode = data.copy()
expire = datetime.utcnow() + timedelta(minutes=ACCESS_TOKEN_EXPIRE_MINUTES)
to_encode.update({"exp": expire})
encoded_jwt = jwt.encode(to_encode, JWT_SECRET_KEY, algorithm=ALGORITHM)
return encoded_jwt
async def get_current_user(token: str = Depends(oauth2_scheme)):
"""
Returns the current user associated with the provided JWT token.
:param token
:raises HTTPException: If the token is invalid or the user does not exist.
:return: The UserInDB instance associated with the token.
"""
credential_exception = HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED,
detail="Could not validate credentials",
headers={"WWW-Authenticate": "Bearer"},
)
try:
payload = jwt.decode(token, JWT_SECRET_KEY, algorithms=[ALGORITHM])
username: str = payload.get("sub")
if username is None:
raise credential_exception
token_data = TokenData(username=username)
except JWTError:
raise credential_exception
current_user = get_user(token_data.username)
if current_user is None:
raise credential_exception
return current_user
async def get_active_current_user(current_user: UserInDB = Depends(get_current_user)):
"""
Returns the current user if the user account is active.
:param current_user: A UserInDB instance representing the current user.
:raises HTTPException: If the user account is inactive.
:return: The UserInDB instance if the user account is active.
"""
if current_user.disabled:
raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED, detail="Inactive user."
)
return current_user

89
api/auth/db_utils.py
View File

@ -1,89 +0,0 @@
from typing import Optional, Union
from passlib.context import CryptContext
from supabase_py import create_client, Client
from fastapi import HTTPException, status
from api.core.users import UserInDB
from settings import SUPABASE_URL, SUPABASE_KEY
pwd_context = CryptContext(schemes=["bcrypt"], deprecated="auto")
if SUPABASE_URL:
supabase: Client = create_client(SUPABASE_URL, SUPABASE_KEY)
def create_user(user_create: UserInDB):
"""
Creates a new user record in the 'users' table in Supabase.
:param user_create: The data of the user to be created.
:raises HTTPException: If an error occurs while creating the user.
:return: The result of the insert operation.
"""
result = supabase.table("users").insert(user_create.dict()).execute()
print(f"Insert result: {result}")
if "error" in result and result["error"]:
raise HTTPException(
status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
detail=f"User could not be created due to {result['error']['message']}",
)
return result
def get_user(username: str) -> Optional[UserInDB]:
"""
Retrieves a user from the 'users' table by their username.
:param username: The username of the user to retrieve.
:return: The user data if found, otherwise None.
"""
result = supabase.table("users").select().eq("username", username).execute()
if "error" in result and result["error"]:
print(f"Error: {result['error']['message']}")
return None
else:
if result["data"]:
user_data = result["data"][0]
return UserInDB(**user_data)
else:
return None
def verify_password(password: str, hashed_password: str) -> bool:
"""
Verifies a password against a hashed password using the bcrypt hashing algorithm.
:param password: The plaintext password to verify.
:param hashed_password: The hashed password to compare against.
:return: True if the password matches the hashed password, otherwise False.
"""
return pwd_context.verify(password, hashed_password)
def get_password_hash(password: str) -> str:
"""
Hashes a password using the bcrypt hashing algorithm.
:param password: The plaintext password to hash.
:return: The hashed password
"""
return pwd_context.hash(password)
def authenticate_user(username: str, password: str) -> Union[UserInDB, bool]:
"""
Authenticates a user based on their username and password.
:param username: The username of the user to authenticate.
:param password: The plaintext password to authenticate.
:return: The authenticated user if the username and password are correct, otherwise False.
"""
user = get_user(username)
if not user:
return False
if not verify_password(password, user.hashed_password):
return False
return user

33
api/auth/register/__init__.py
View File

@ -1,33 +0,0 @@
from fastapi import APIRouter, HTTPException, status
from api.core.users import UserCreate, UserInDB
from api.auth.db_utils import get_user, get_password_hash, create_user
router = APIRouter(prefix="/register")
@router.post("/", response_model=dict)
async def register_new_user(user: UserCreate) -> dict:
"""
Creates new user
:param user:
:raises HTTPException: If the username already exists.
:return: A dictionary containing a detail key with a success message.
"""
existing_user = get_user(user.username)
if existing_user is not None:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail="Username already exists",
)
hashed_password = get_password_hash(user.password)
user_create = UserInDB(
username=user.username,
email=user.email,
full_name=user.full_name,
hashed_password=hashed_password,
disabled=False,
)
create_user(user_create)
return {"detail": "User created successfully"}

30
api/auth/token/__init__.py
View File

@ -1,30 +0,0 @@
from fastapi import APIRouter, Depends, HTTPException, status
from fastapi.security import OAuth2PasswordRequestForm
from api.core.users import Token
from api.auth.db_utils import authenticate_user
from api.auth.auth_utils import create_access_token
router = APIRouter(prefix="/token")
@router.post("/", response_model=Token)
async def login_for_access_token(
form_data: OAuth2PasswordRequestForm = Depends(),
) -> Token:
"""
Authenticates a user and provides an access token.
:param form_data: OAuth2PasswordRequestForm object containing the user's credentials.
:raises HTTPException: If the user cannot be authenticated.
:return: A Token object containing the access token and the token type.
"""
user = authenticate_user(form_data.username, form_data.password)
if not user:
raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED,
detail="Incorrect username or password",
headers={"WWW-Authenticate": "Bearer"},
)
access_token = create_access_token(data={"sub": user.username})
return Token(access_token=access_token, token_type="bearer")

7
api/core/formatters/__init__.py
View File

@ -1,7 +0,0 @@
from enum import Enum
class OutputFormat(Enum):
CSV = "csv"
JSON = "json"
GSHEET = "gsheet"

133
api/core/formatters/csv/__init__.py
View File

@ -1,133 +0,0 @@
import gspread
from oauth2client.service_account import ServiceAccountCredentials
import csv
from io import StringIO
from datetime import datetime
from ...jobs import *
from ...scrapers import *
from settings import *
class CSVFormatter:
@staticmethod
def fetch_job_urls(credentials: Any) -> set:
"""
Fetches all the job urls from the google sheet to prevent duplicates
:param credentials:
:return: urls
"""
try:
gc = gspread.authorize(credentials)
sh = gc.open(GSHEET_NAME)
worksheet = sh.get_worksheet(0)
data = worksheet.get_all_values()
job_urls = set()
for row in data[1:]:
job_urls.add(row[3])
return job_urls
except Exception as e:
raise e
@staticmethod
def upload_to_google_sheet(csv_data: str):
"""
Appends rows to google sheet
:param csv_data:
:return:
"""
try:
scope = [
"https://www.googleapis.com/auth/spreadsheets",
"https://www.googleapis.com/auth/drive.file",
"https://www.googleapis.com/auth/drive",
]
credentials = ServiceAccountCredentials.from_json_keyfile_name(
"client_secret.json", scope
)
gc = gspread.authorize(credentials)
sh = gc.open(GSHEET_NAME)
worksheet = sh.get_worksheet(0)
data_string = csv_data.getvalue()
reader = csv.reader(StringIO(data_string))
job_urls = CSVFormatter.fetch_job_urls(credentials)
rows = list(reader)
for i, row in enumerate(rows):
if i == 0:
continue
if row[4] in job_urls:
continue
row[6] = format(int(row[6]), ",d") if row[6] else ""
row[7] = format(int(row[7]), ",d") if row[7] else ""
worksheet.append_row(row)
except Exception as e:
raise e
@staticmethod
def generate_filename() -> str:
"""
Adds a timestamp to the filename header
:return: filename
"""
timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
return f"JobSpy_results_{timestamp}.csv"
@staticmethod
def format(jobs: CommonResponse) -> StringIO:
"""
Transfomr the jobs objects into csv
:param jobs:
:return: csv
"""
output = StringIO()
writer = csv.writer(output)
headers = [
"Title",
"Company Name",
"City",
"State",
"Job Type",
"Pay Cycle",
"Min Amount",
"Max Amount",
"Date Posted",
"Description",
"Job URL",
]
writer.writerow(headers)
for site, job_response in jobs.dict().items():
if isinstance(job_response, dict) and job_response.get("success"):
for job in job_response["jobs"]:
writer.writerow(
[
job["title"],
job["company_name"],
job["location"]["city"],
job["location"]["state"],
job["job_type"].value if job.get("job_type") else "",
job["compensation"]["interval"].value
if job["compensation"]
else "",
job["compensation"]["min_amount"]
if job["compensation"]
else "",
job["compensation"]["max_amount"]
if job["compensation"]
else "",
job.get("date_posted", ""),
job["description"],
job["job_url"],
]
)
output.seek(0)
return output

28
api/core/users/__init__.py
View File

@ -1,28 +0,0 @@
from pydantic import BaseModel
class User(BaseModel):
username: str
full_name: str
email: str
disabled: bool = False
class UserCreate(BaseModel):
username: str
full_name: str
email: str
password: str
class UserInDB(User):
hashed_password: str
class TokenData(BaseModel):
username: str
class Token(BaseModel):
access_token: str
token_type: str

11
api/v1/__init__.py
View File

@ -1,11 +0,0 @@
from fastapi import APIRouter, Depends
from .jobs import router as jobs_router
from api.auth.auth_utils import get_active_current_user
from settings import AUTH_REQUIRED
if AUTH_REQUIRED:
router = APIRouter(prefix="/v1", dependencies=[Depends(get_active_current_user)])
else:
router = APIRouter(prefix="/v1")
router.include_router(jobs_router)

68
api/v1/jobs/__init__.py
View File

@ -1,68 +0,0 @@
import io
from fastapi import APIRouter
from fastapi.responses import StreamingResponse
from concurrent.futures import ThreadPoolExecutor
from api.core.scrapers.indeed import IndeedScraper
from api.core.scrapers.ziprecruiter import ZipRecruiterScraper
from api.core.scrapers.linkedin import LinkedInScraper
from api.core.formatters.csv import CSVFormatter
from api.core.scrapers import (
ScraperInput,
Site,
JobResponse,
OutputFormat,
CommonResponse,
)
from typing import List, Dict, Tuple, Union
router = APIRouter(prefix="/jobs", tags=["jobs"])
SCRAPER_MAPPING = {
Site.LINKEDIN: LinkedInScraper,
Site.INDEED: IndeedScraper,
Site.ZIP_RECRUITER: ZipRecruiterScraper,
}
@router.post("/")
async def scrape_jobs(scraper_input: ScraperInput) -> CommonResponse:
"""
Asynchronously scrapes job data from multiple job sites.
:param scraper_input:
:return: scraper_response
"""
def scrape_site(site: Site) -> Tuple[str, JobResponse]:
scraper_class = SCRAPER_MAPPING[site]
scraper = scraper_class()
scraped_data: JobResponse = scraper.scrape(scraper_input)
return (site.value, scraped_data)
with ThreadPoolExecutor(max_workers=3) as executor:
results = dict(executor.map(scrape_site, scraper_input.site_type))
scraper_response = CommonResponse(status="JSON response success", **results)
if scraper_input.output_format == OutputFormat.CSV:
csv_output = CSVFormatter.format(scraper_response)
response = StreamingResponse(csv_output, media_type="text/csv")
response.headers[
"Content-Disposition"
] = f"attachment; filename={CSVFormatter.generate_filename()}"
return response
elif scraper_input.output_format == OutputFormat.GSHEET:
csv_output = CSVFormatter.format(scraper_response)
try:
CSVFormatter.upload_to_google_sheet(csv_output)
return CommonResponse(
status="Successfully uploaded to Google Sheets", **results
)
except Exception as e:
return CommonResponse(
status="Failed to upload to Google Sheet", error=repr(e), **results
)
else:
return scraper_response

121
jobscrape/__init__.py Normal file
View File

@ -0,0 +1,121 @@
import pandas as pd
from typing import List, Dict, Tuple, Union
from concurrent.futures import ThreadPoolExecutor
from .core.jobs import JobType
from .core.scrapers.indeed import IndeedScraper
from .core.scrapers.ziprecruiter import ZipRecruiterScraper
from .core.scrapers.linkedin import LinkedInScraper
from .core.scrapers import (
ScraperInput,
Site,
JobResponse,
CommonResponse,
)
SCRAPER_MAPPING = {
Site.LINKEDIN: LinkedInScraper,
Site.INDEED: IndeedScraper,
Site.ZIP_RECRUITER: ZipRecruiterScraper,
}
def _map_str_to_site(site_name: str) -> Site:
return Site[site_name.upper()]
def scrape_jobs(
site_name: str | Site | List[Site],
search_term: str,
location: str = "",
distance: int = None,
is_remote: bool = False,
job_type: JobType = None,
easy_apply: bool = False, # linkedin
results_wanted: int = 15
) -> pd.DataFrame:
"""
Asynchronously scrapes job data from multiple job sites.
:return: results_wanted: pandas dataframe containing job data
"""
if type(site_name) == str:
site_name = _map_str_to_site(site_name)
site_type = [site_name] if type(site_name) == Site else site_name
scraper_input = ScraperInput(
site_type=site_type,
search_term=search_term,
location=location,
distance=distance,
is_remote=is_remote,
job_type=job_type,
easy_apply=easy_apply,
results_wanted=results_wanted,
)
def scrape_site(site: Site) -> Tuple[str, JobResponse]:
scraper_class = SCRAPER_MAPPING[site]
scraper = scraper_class()
scraped_data: JobResponse = scraper.scrape(scraper_input)
return site.value, scraped_data
results = {}
for site in scraper_input.site_type:
site_value, scraped_data = scrape_site(site)
results[site_value] = scraped_data
dfs = []
for site, job_response in results.items():
for job in job_response.jobs:
data = job.dict()
data['site'] = site
# Formatting JobType
data['job_type'] = data['job_type'].value if data['job_type'] else None
# Formatting Location
location_obj = data.get('location')
if location_obj and isinstance(location_obj, dict):
data['city'] = location_obj.get('city', '')
data['state'] = location_obj.get('state', '')
data['country'] = location_obj.get('country', 'USA')
else:
data['city'] = None
data['state'] = None
data['country'] = None
# Formatting Compensation
compensation_obj = data.get('compensation')
if compensation_obj and isinstance(compensation_obj, dict):
data['interval'] = compensation_obj.get('interval').value if compensation_obj.get('interval') else None
data['min_amount'] = compensation_obj.get('min_amount')
data['max_amount'] = compensation_obj.get('max_amount')
data['currency'] = compensation_obj.get('currency', 'USD')
else:
data['interval'] = None
data['min_amount'] = None
data['max_amount'] = None
data['currency'] = None
job_df = pd.DataFrame([data])
dfs.append(job_df)
if dfs:
df = pd.concat(dfs, ignore_index=True)
desired_order = ['site', 'title', 'company_name', 'city', 'state','job_type',
'interval', 'min_amount', 'max_amount', 'job_url', 'description',]
df = df[desired_order]
else:
df = pd.DataFrame()
return df

0
api/core/__init__.py → jobscrape/core/__init__.py
View File

26
api/core/jobs/__init__.py → jobscrape/core/jobs/__init__.py
View File

@ -1,4 +1,4 @@
from typing import Union from typing import Union, Optional
from datetime import date from datetime import date
from enum import Enum from enum import Enum
@ -19,10 +19,11 @@ class JobType(Enum):
VOLUNTEER = "volunteer" VOLUNTEER = "volunteer"
class Location(BaseModel): class Location(BaseModel):
country: str = "USA" country: str = "USA"
city: str = None city: str = None
state: str = None state: Optional[str] = None
class CompensationInterval(Enum): class CompensationInterval(Enum):
@ -35,8 +36,8 @@ class CompensationInterval(Enum):
class Compensation(BaseModel): class Compensation(BaseModel):
interval: CompensationInterval interval: CompensationInterval
min_amount: int min_amount: int = None
max_amount: int max_amount: int = None
currency: str = "USD" currency: str = "USD"
@ -44,11 +45,11 @@ class JobPost(BaseModel):
title: str title: str
company_name: str company_name: str
job_url: str job_url: str
location: Location location: Optional[Location]
description: str = None description: str = None
job_type: JobType = None job_type: Optional[JobType] = None
compensation: Compensation = None compensation: Optional[Compensation] = None
date_posted: date = None date_posted: date = None
@ -56,7 +57,7 @@ class JobResponse(BaseModel):
success: bool success: bool
error: str = None error: str = None
total_results: int = None total_results: Optional[int] = None
jobs: list[JobPost] = [] jobs: list[JobPost] = []
@ -64,6 +65,11 @@ class JobResponse(BaseModel):
@validator("returned_results", pre=True, always=True) @validator("returned_results", pre=True, always=True)
def set_returned_results(cls, v, values): def set_returned_results(cls, v, values):
if v is None and values.get("jobs"): jobs_list = values.get("jobs")
return len(values["jobs"])
if v is None:
if jobs_list is not None:
return len(jobs_list)
else:
return 0
return v return v

8
api/core/scrapers/__init__.py → jobscrape/core/scrapers/__init__.py
View File

@ -1,5 +1,4 @@
from ..jobs import * from ..jobs import Enum, BaseModel, JobType, JobResponse
from ..formatters import OutputFormat
from typing import List, Dict, Optional, Any from typing import List, Dict, Optional, Any
@ -17,12 +16,11 @@ class Site(Enum):
class ScraperInput(BaseModel): class ScraperInput(BaseModel):
site_type: List[Site] site_type: List[Site]
search_term: str search_term: str
output_format: OutputFormat = OutputFormat.JSON
location: str = None location: str = None
distance: int = None distance: Optional[int] = None
is_remote: bool = False is_remote: bool = False
job_type: JobType = None job_type: Optional[JobType] = None
easy_apply: bool = None # linkedin easy_apply: bool = None # linkedin
results_wanted: int = 15 results_wanted: int = 15

29
api/core/scrapers/indeed/__init__.py → jobscrape/core/scrapers/indeed/__init__.py
View File

@ -1,22 +1,18 @@
import re import re
import sys
import math
import json import json
from typing import Optional, Tuple, List
from datetime import datetime from datetime import datetime
from typing import Optional, Tuple, List
import tls_client import tls_client
import urllib.parse import urllib.parse
from bs4 import BeautifulSoup from bs4 import BeautifulSoup
from bs4.element import Tag from bs4.element import Tag
from fastapi import status
from api.core.jobs import *
from api.core.jobs import JobPost
from api.core.scrapers import Scraper, ScraperInput, Site, StatusException
from concurrent.futures import ThreadPoolExecutor, Future from concurrent.futures import ThreadPoolExecutor, Future
import math
import traceback from ...jobs import JobPost, Compensation, CompensationInterval, Location, JobResponse, JobType
import sys from .. import Scraper, ScraperInput, Site, StatusException
class ParsingException(Exception): class ParsingException(Exception):
@ -66,8 +62,8 @@ class IndeedScraper(Scraper):
response = session.get(self.url + "/jobs", params=params) response = session.get(self.url + "/jobs", params=params)
if ( if (
response.status_code != status.HTTP_200_OK response.status_code != 200
and response.status_code != status.HTTP_307_TEMPORARY_REDIRECT and response.status_code != 307
): ):
raise StatusException(response.status_code) raise StatusException(response.status_code)
@ -131,7 +127,6 @@ class IndeedScraper(Scraper):
location=Location( location=Location(
city=job.get("jobLocationCity"), city=job.get("jobLocationCity"),
state=job.get("jobLocationState"), state=job.get("jobLocationState"),
postal_code=job.get("jobLocationPostal"),
), ),
job_type=job_type, job_type=job_type,
compensation=compensation, compensation=compensation,
@ -140,9 +135,11 @@ class IndeedScraper(Scraper):
) )
return job_post return job_post
for job in jobs["metaData"]["mosaicProviderJobCardsModel"]["results"]: with ThreadPoolExecutor(max_workers=10) as executor:
job_post = process_job(job) job_results: list[Future] = [executor.submit(process_job, job) for job in
job_list.append(job_post) jobs["metaData"]["mosaicProviderJobCardsModel"]["results"]]
job_list = [result.result() for result in job_results if result.result()]
return job_list, total_num_jobs return job_list, total_num_jobs

9
api/core/scrapers/linkedin/__init__.py → jobscrape/core/scrapers/linkedin/__init__.py
View File

@ -4,10 +4,9 @@ from datetime import datetime
import requests import requests
from bs4 import BeautifulSoup from bs4 import BeautifulSoup
from bs4.element import Tag from bs4.element import Tag
from fastapi import status
from api.core.scrapers import Scraper, ScraperInput, Site from .. import Scraper, ScraperInput, Site
from api.core.jobs import * from ...jobs import JobPost, Location, JobResponse, JobType, Compensation, CompensationInterval
class LinkedInScraper(Scraper): class LinkedInScraper(Scraper):
@ -59,7 +58,7 @@ class LinkedInScraper(Scraper):
f"{self.url}/jobs/search", params=params, allow_redirects=True f"{self.url}/jobs/search", params=params, allow_redirects=True
) )
if response.status_code != status.HTTP_200_OK: if response.status_code != 200:
return JobResponse( return JobResponse(
success=False, success=False,
error=f"Response returned {response.status_code}", error=f"Response returned {response.status_code}",
@ -118,6 +117,7 @@ class LinkedInScraper(Scraper):
date_posted=date_posted, date_posted=date_posted,
job_url=job_url, job_url=job_url,
job_type=job_type, job_type=job_type,
compensation=Compensation(interval=CompensationInterval.YEARLY, currency="USD")
) )
job_list.append(job_post) job_list.append(job_post)
if ( if (
@ -185,7 +185,6 @@ class LinkedInScraper(Scraper):
employment_type = employment_type_span.get_text(strip=True) employment_type = employment_type_span.get_text(strip=True)
employment_type = employment_type.lower() employment_type = employment_type.lower()
employment_type = employment_type.replace("-", "") employment_type = employment_type.replace("-", "")
print(employment_type)
return JobType(employment_type) return JobType(employment_type)

237
api/core/scrapers/ziprecruiter/__init__.py → jobscrape/core/scrapers/ziprecruiter/__init__.py
View File

@ -1,18 +1,17 @@
import math import math
import json import json
import re
from datetime import datetime from datetime import datetime
from typing import Optional, Tuple, List from typing import Optional, Tuple, List
from urllib.parse import urlparse, parse_qs from urllib.parse import urlparse, parse_qs
import tls_client import tls_client
from fastapi import status
from bs4 import BeautifulSoup from bs4 import BeautifulSoup
from bs4.element import Tag from bs4.element import Tag
from concurrent.futures import ThreadPoolExecutor, Future from concurrent.futures import ThreadPoolExecutor, Future
from api.core.jobs import JobPost from .. import Scraper, ScraperInput, Site, StatusException
from api.core.scrapers import Scraper, ScraperInput, Site, StatusException from ...jobs import JobPost, Compensation, CompensationInterval, Location, JobResponse, JobType
from api.core.jobs import *
class ZipRecruiterScraper(Scraper): class ZipRecruiterScraper(Scraper):
@ -26,9 +25,12 @@ class ZipRecruiterScraper(Scraper):
self.jobs_per_page = 20 self.jobs_per_page = 20
self.seen_urls = set() self.seen_urls = set()
self.session = tls_client.Session(
client_identifier="chrome112", random_tls_extension_order=True
)
def scrape_page( def scrape_page(
self, scraper_input: ScraperInput, page: int, session: tls_client.Session self, scraper_input: ScraperInput, page: int
) -> tuple[list[JobPost], int | None]: ) -> tuple[list[JobPost], int | None]:
""" """
Scrapes a page of ZipRecruiter for jobs with scraper_input criteria Scrapes a page of ZipRecruiter for jobs with scraper_input criteria
@ -52,91 +54,47 @@ class ZipRecruiterScraper(Scraper):
params = { params = {
"search": scraper_input.search_term, "search": scraper_input.search_term,
"location": scraper_input.location, "location": scraper_input.location,
"radius": scraper_input.distance,
"refine_by_location_type": "only_remote"
if scraper_input.is_remote
else None,
"refine_by_employment": f"employment_type:employment_type:{job_type_value}"
if job_type_value
else None,
"page": page, "page": page,
"form": "jobs-landing"
} }
response = session.get( if scraper_input.is_remote:
params["refine_by_location_type"] = "only_remote"
if scraper_input.distance:
params["radius"] = scraper_input.distance
if job_type_value:
params["refine_by_employment"] = f"employment_type:employment_type:{job_type_value}"
response = self.session.get(
self.url + "/jobs-search", self.url + "/jobs-search",
headers=ZipRecruiterScraper.headers(), headers=ZipRecruiterScraper.headers(),
params=params, params=params,
) )
if response.status_code != status.HTTP_200_OK: if response.status_code != 200:
raise StatusException(response.status_code) raise StatusException(response.status_code)
html_string = response.content html_string = response.text
soup = BeautifulSoup(html_string, "html.parser") soup = BeautifulSoup(html_string, "html.parser")
if page == 1: script_tag = soup.find("script", {"id": "js_variables"})
script_tag = soup.find("script", {"id": "js_variables"}) data = json.loads(script_tag.string)
data = json.loads(script_tag.string)
if page == 1:
job_count = int(data["totalJobCount"].replace(",", "")) job_count = int(data["totalJobCount"].replace(",", ""))
else: else:
job_count = None job_count = None
job_posts = soup.find_all("div", {"class": "job_content"})
def process_job(job: Tag) -> Optional[JobPost]:
"""
Parses a job from the job content tag
:param job: BeautifulSoup Tag for one job post
:return JobPost
"""
job_url = job.find("a", {"class": "job_link"})["href"]
if job_url in self.seen_urls:
return None
title = job.find("h2", {"class": "title"}).text
company = job.find("a", {"class": "company_name"}).text.strip()
description, updated_job_url = ZipRecruiterScraper.get_description(
job_url, session
)
if updated_job_url is not None:
job_url = updated_job_url
if description is None:
description = job.find("p", {"class": "job_snippet"}).text.strip()
job_type_element = job.find("li", {"class": "perk_item perk_type"})
if job_type_element:
job_type_text = (
job_type_element.text.strip()
.lower()
.replace("-", "")
.replace(" ", "")
)
if job_type_text == "contractor":
job_type_text = "contract"
job_type = JobType(job_type_text)
else:
job_type = None
date_posted = ZipRecruiterScraper.get_date_posted(job)
job_post = JobPost(
title=title,
description=description,
company_name=company,
location=ZipRecruiterScraper.get_location(job),
job_type=job_type,
compensation=ZipRecruiterScraper.get_compensation(job),
date_posted=date_posted,
job_url=job_url,
)
return job_post
with ThreadPoolExecutor(max_workers=10) as executor: with ThreadPoolExecutor(max_workers=10) as executor:
job_results: list[Future] = [ if "jobList" in data and data["jobList"]:
executor.submit(process_job, job) for job in job_posts jobs_js = data["jobList"]
] job_results = [executor.submit(self.process_job_js, job) for job in jobs_js]
else:
jobs_html = soup.find_all("div", {"class": "job_content"})
job_results = [executor.submit(self.process_job_html, job) for job in
jobs_html]
job_list = [result.result() for result in job_results if result.result()] job_list = [result.result() for result in job_results if result.result()]
@ -148,19 +106,17 @@ class ZipRecruiterScraper(Scraper):
:param scraper_input: :param scraper_input:
:return: job_response :return: job_response
""" """
session = tls_client.Session(
client_identifier="chrome112", random_tls_extension_order=True
)
pages_to_process = math.ceil(scraper_input.results_wanted / self.jobs_per_page)
pages_to_process = max(3, math.ceil(scraper_input.results_wanted / self.jobs_per_page))
try: try:
#: get first page to initialize session #: get first page to initialize session
job_list, total_results = self.scrape_page(scraper_input, 1, session) job_list, total_results = self.scrape_page(scraper_input, 1)
with ThreadPoolExecutor(max_workers=10) as executor: with ThreadPoolExecutor(max_workers=10) as executor:
futures: list[Future] = [ futures: list[Future] = [
executor.submit(self.scrape_page, scraper_input, page, session) executor.submit(self.scrape_page, scraper_input, page)
for page in range(2, pages_to_process + 1) for page in range(2, pages_to_process + 1)
] ]
@ -169,6 +125,7 @@ class ZipRecruiterScraper(Scraper):
job_list += jobs job_list += jobs
except StatusException as e: except StatusException as e:
return JobResponse( return JobResponse(
success=False, success=False,
@ -192,9 +149,129 @@ class ZipRecruiterScraper(Scraper):
) )
return job_response return job_response
def process_job_html(self, job: Tag) -> Optional[JobPost]:
"""
Parses a job from the job content tag
:param job: BeautifulSoup Tag for one job post
:return JobPost
"""
job_url = job.find("a", {"class": "job_link"})["href"]
if job_url in self.seen_urls:
return None
title = job.find("h2", {"class": "title"}).text
company = job.find("a", {"class": "company_name"}).text.strip()
description, updated_job_url = self.get_description(
job_url
)
if updated_job_url is not None:
job_url = updated_job_url
if description is None:
description = job.find("p", {"class": "job_snippet"}).text.strip()
job_type_element = job.find("li", {"class": "perk_item perk_type"})
if job_type_element:
job_type_text = (
job_type_element.text.strip()
.lower()
.replace("-", "")
.replace(" ", "")
)
if job_type_text == "contractor":
job_type_text = "contract"
job_type = JobType(job_type_text)
else:
job_type = None
date_posted = ZipRecruiterScraper.get_date_posted(job)
job_post = JobPost(
title=title,
description=description,
company_name=company,
location=ZipRecruiterScraper.get_location(job),
job_type=job_type,
compensation=ZipRecruiterScraper.get_compensation(job),
date_posted=date_posted,
job_url=job_url,
)
return job_post
def process_job_js(self, job: dict) -> JobPost:
# Map the job data to the expected fields by the Pydantic model
title = job.get("Title")
description = BeautifulSoup(job.get("Snippet","").strip(), "html.parser").get_text()
company = job.get("OrgName")
location = Location(city=job.get("City"), state=job.get("State"))
try:
job_type = ZipRecruiterScraper.job_type_from_string(job.get("EmploymentType", "").replace("-", "_").lower())
except ValueError:
# print(f"Skipping job due to unrecognized job type: {job.get('EmploymentType')}")
return None
formatted_salary = job.get("FormattedSalaryShort", "")
salary_parts = formatted_salary.split(" ")
min_salary_str = salary_parts[0][1:].replace(",", "")
if '.' in min_salary_str:
min_amount = int(float(min_salary_str) * 1000)
else:
min_amount = int(min_salary_str.replace("K", "000"))
if len(salary_parts) >= 3 and salary_parts[2].startswith("$"):
max_salary_str = salary_parts[2][1:].replace(",", "")
if '.' in max_salary_str:
max_amount = int(float(max_salary_str) * 1000)
else:
max_amount = int(max_salary_str.replace("K", "000"))
else:
max_amount = 0
compensation = Compensation(
interval=CompensationInterval.YEARLY,
min_amount=min_amount,
max_amount=max_amount
)
save_job_url = job.get("SaveJobURL", "")
posted_time_match = re.search(r"posted_time=(\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}Z)", save_job_url)
if posted_time_match:
date_time_str = posted_time_match.group(1)
date_posted_obj = datetime.strptime(date_time_str, "%Y-%m-%dT%H:%M:%SZ")
date_posted = date_posted_obj.date()
else:
date_posted = date.today()
job_url = job.get("JobURL")
return JobPost(
title=title,
description=description,
company_name=company,
location=location,
job_type=job_type,
compensation=compensation,
date_posted=date_posted,
job_url=job_url,
)
return job_post
@staticmethod @staticmethod
def job_type_from_string(value: str) -> Optional[JobType]:
if not value:
return None
if value.lower() == "contractor":
value = "contract"
normalized_value = value.replace("_", "")
for item in JobType:
if item.value == normalized_value:
return item
raise ValueError(f"Invalid value for JobType: {value}")
def get_description( def get_description(
job_page_url: str, session: tls_client.Session self,
job_page_url: str
) -> Tuple[Optional[str], Optional[str]]: ) -> Tuple[Optional[str], Optional[str]]:
""" """
Retrieves job description by going to the job page url Retrieves job description by going to the job page url
@ -202,7 +279,7 @@ class ZipRecruiterScraper(Scraper):
:param session: :param session:
:return: description or None, response url :return: description or None, response url
""" """
response = session.get( response = self.session.get(
job_page_url, headers=ZipRecruiterScraper.headers(), allow_redirects=True job_page_url, headers=ZipRecruiterScraper.headers(), allow_redirects=True
) )
if response.status_code not in range(200, 400): if response.status_code not in range(200, 400):

16
main.py
View File

@ -1,16 +0,0 @@
from fastapi import FastAPI
from supabase_py import create_client, Client
from api import router as api_router
app = FastAPI(
title="JobSpy Backend",
description="Endpoints for job boardLinkedIn, Indeed, and ZipRecruiterscrapers",
version="1.0.0",
)
app.include_router(api_router)
@app.get("/health", tags=["health"])
async def health_check():
return {"message": "JobSpy ready to scrape"}

2435
poetry.lock generated Normal file
View File

File diff suppressed because it is too large Load Diff

401
postman/JobSpy.postman_collection.json
View File

File diff suppressed because one or more lines are too long

15
postman/JobSpy.postman_environment.json
View File

@ -1,15 +0,0 @@
{
"id": "a7ea6d58-8dca-4216-97a9-224dadc1e18f",
"name": "JobSpy",
"values": [
{
"key": "access_token",
"value": "",
"type": "any",
"enabled": true
}
],
"_postman_variable_scope": "environment",
"_postman_exported_at": "2023-07-09T23:51:36.709Z",
"_postman_exported_using": "Postman/10.15.8"
}

23
pyproject.toml Normal file
View File

@ -0,0 +1,23 @@
[tool.poetry]
name = "jobscrape"
version = "0.1.0"
description = "Job scraper for LinkedIn, Indeed & ZipRecruiter"
authors = ["Zachary Hampton <69336300+ZacharyHampton@users.noreply.github.com>", "Cullen Watson <cullen@cullen.ai>"]
readme = "README.md"
[tool.poetry.dependencies]
python = "^3.10"
requests = "^2.31.0"
tls-client = "^0.2.1"
beautifulsoup4 = "^4.12.2"
pandas = "^2.1.0"
pydantic = "^2.3.0"
[tool.poetry.group.dev.dependencies]
pytest = "^7.4.1"
jupyter = "^1.0.0"
[build-system]
requires = ["poetry-core"]
build-backend = "poetry.core.masonry.api"

61
requirements.txt
View File

@ -1,61 +0,0 @@
anyio==3.7.1
atomicwrites==1.4.1
attrs==23.1.0
bcrypt==4.0.1
beautifulsoup4==4.12.2
cachetools==5.3.1
certifi==2023.5.7
cffi==1.15.1
chardet==4.0.0
charset-normalizer==3.2.0
click==8.1.4
colorama==0.4.6
cryptography==41.0.1
dataclasses==0.6
deprecation==2.1.0
ecdsa==0.18.0
exceptiongroup==1.1.2
fastapi==0.99.1
google-auth==2.22.0
google-auth-oauthlib==1.0.0
gotrue==0.2.0
gspread==5.10.0
h11==0.14.0
httpcore==0.12.3
httplib2==0.22.0
httpx==0.16.1
idna==2.10
iniconfig==2.0.0
oauth2client==4.1.3
oauthlib==3.2.2
packaging==23.1
passlib==1.7.4
pluggy==1.2.0
postgrest-py==0.4.0
py==1.11.0
pyasn1==0.5.0
pyasn1-modules==0.3.0
pycparser==2.21
pydantic==1.10.11
pyparsing==3.1.1
pytest==6.2.5
python-dateutil==2.8.2
python-dotenv==1.0.0
python-jose==3.3.0
python-multipart==0.0.6
realtime-py==0.1.3
requests==2.25.1
requests-oauthlib==1.3.1
rfc3986==1.5.0
rsa==4.9
six==1.16.0
sniffio==1.3.0
soupsieve==2.4.1
starlette==0.27.0
supabase-py==0.0.2
tls-client==0.2.1
toml==0.10.2
typing_extensions==4.7.1
urllib3==1.26.16
uvicorn==0.22.0
websockets==9.1

14
settings.py
View File

@ -1,14 +0,0 @@
from dotenv import load_dotenv
import os
load_dotenv()
# gsheets (template to copy at https://docs.google.com/spreadsheets/d/1mOgb-ZGZy_YIhnW9OCqIVvkFwiKFvhMBjNcbakW7BLo/edit?usp=sharing)
GSHEET_NAME = os.environ.get("GSHEET_NAME", "JobSpy")
# optional autha
AUTH_REQUIRED = False
SUPABASE_URL = os.environ.get("SUPABASE_URL")
SUPABASE_KEY = os.environ.get("SUPABASE_KEY")
JWT_SECRET_KEY = os.environ.get("JWT_SECRET_KEY")
ACCESS_TOKEN_EXPIRE_MINUTES = 60
ALGORITHM = "HS256"

10
tests/test_indeed.py Normal file
View File

@ -0,0 +1,10 @@
from jobscrape import scrape_jobs
def test_indeed():
result = scrape_jobs(
site_name="indeed",
search_term="software engineer",
)
assert result is not None

10
tests/test_ziprecruiter.py Normal file
View File

@ -0,0 +1,10 @@
from jobscrape import scrape_jobs
def test_ziprecruiter():
result = scrape_jobs(
site_name="zip_recruiter",
search_term="software engineer",
)
assert result is not None