Spaces:
Paused
Paused
File size: 15,194 Bytes
56c7b6d | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 | {
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"#!pip3 install python-docx\n",
"#!pip3 install openai\n",
"#!pip3 install spacy"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"import os # For file path operations\n",
"import re # For regular expressions (finding keywords)\n",
"import requests # For making HTTP requests to fetch job description\n",
"from docx import Document # From python-docx for reading/writing Word documents\n",
"from docx.shared import Pt # For setting font sizes, etc.\n",
"import time\n",
"import datetime\n",
"import pandas as pd\n",
"\n",
"import spacy\n",
"from datetime import datetime, timedelta\n",
"import undetected_chromedriver as uc\n",
"from selenium import webdriver\n",
"from selenium.webdriver.common.by import By\n",
"from selenium.webdriver.common.keys import Keys\n",
"from selenium.webdriver.support.ui import WebDriverWait\n",
"from selenium.webdriver.support import expected_conditions as EC"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Getting the job from linked in then put the file as input file"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"🔍 Scraping LinkedIn Jobs...\n",
"\n",
"⏳ Skipping job: (Posted 15 days ago)\n",
"⏳ Skipping job: ******* ******* *********** ********* - *-******** (*/*/*) (Posted 115 days ago)\n",
"\n",
"✅ Jobs saved to /Users/eimon/Desktop/Code/AI works/Job apply AI agent/Job-apply-AI-agent/CV maker/linkedin_jobs_2025-02-27.xlsx\n"
]
}
],
"source": [
"def configure_driver():\n",
" options = webdriver.ChromeOptions()\n",
" options.add_argument(\"--headless\")\n",
" options.add_argument(\"--no-sandbox\")\n",
" options.add_argument(\"--disable-dev-shm-usage\")\n",
" driver = uc.Chrome(options=options)\n",
" return driver\n",
"\n",
"def scrape_linkedin_jobs(keyword, location):\n",
" print(\"\\n🔍 Scraping LinkedIn Jobs...\\n\")\n",
" driver = configure_driver()\n",
" search_url = f\"https://www.linkedin.com/jobs/search?keywords={keyword.replace(' ', '%20')}&location={location.replace(' ', '%20')}\"\n",
" driver.get(search_url)\n",
" \n",
" for _ in range(3): \n",
" driver.execute_script(\"window.scrollBy(0, 800);\")\n",
" time.sleep(2)\n",
" \n",
" wait = WebDriverWait(driver, 15)\n",
" try:\n",
" wait.until(EC.presence_of_element_located((By.CLASS_NAME, \"base-card\")))\n",
" except:\n",
" print(\"❌ No LinkedIn jobs found.\")\n",
" driver.quit()\n",
" return []\n",
"\n",
" jobs = []\n",
" today = datetime.today()\n",
" job_elements = driver.find_elements(By.CLASS_NAME, \"base-card\")\n",
" \n",
" for job in job_elements[:10]:\n",
" try:\n",
" title = job.find_element(By.CSS_SELECTOR, \"h3\").text.strip()\n",
" company = job.find_element(By.CSS_SELECTOR, \"h4\").text.strip()\n",
" link = job.find_element(By.TAG_NAME, \"a\").get_attribute(\"href\")\n",
" \n",
" try:\n",
" date_element = job.find_element(By.CSS_SELECTOR, \"time\")\n",
" posted_time = date_element.get_attribute(\"datetime\")\n",
" if posted_time:\n",
" posted_date = datetime.strptime(posted_time[:10], \"%Y-%m-%d\")\n",
" days_ago = (today - posted_date).days\n",
" if days_ago > 14:\n",
" print(f\"⏳ Skipping job: {title} (Posted {days_ago} days ago)\")\n",
" continue\n",
" except:\n",
" print(f\"⚠️ Could not find post time for: {title}, assuming it's recent.\")\n",
" days_ago = \"Unknown\"\n",
" \n",
" jobs.append({\"title\": title, \"company\": company, \"link\": link, \"source\": \"LinkedIn\", \"posted_days_ago\": days_ago})\n",
" except Exception as e:\n",
" print(f\"⚠️ Skipping a job entry due to error: {e}\")\n",
" continue\n",
" \n",
" driver.quit()\n",
" return jobs\n",
"\n",
"if __name__ == \"__main__\":\n",
" keyword = input(\"Enter job title (e.g., Software Engineer): \")\n",
" location = input(\"Enter location (e.g., Remote, New York, Berlin): \")\n",
" \n",
" linkedin_jobs = scrape_linkedin_jobs(keyword, location)\n",
" \n",
" if linkedin_jobs:\n",
" df = pd.DataFrame(linkedin_jobs)\n",
" today_date = datetime.today().strftime(\"%Y-%m-%d\")\n",
" filename = f\"linkedin_jobs_{today_date}.xlsx\"\n",
" \n",
" folder_path = \"/Users/eimon/Desktop/Code/AI works/Job apply AI agent/Job-apply-AI-agent/CV maker\"\n",
" os.makedirs(folder_path, exist_ok=True) # Ensure directory exists\n",
" input_file = os.path.join(folder_path, filename)\n",
" \n",
" df.to_excel(input_file, index=False)\n",
" print(f\"\\n✅ Jobs saved to {input_file}\")\n",
" else:\n",
" print(\"\\n❌ No LinkedIn jobs found.\")\n",
" input_file = None\n"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"/Users/eimon/Desktop/Code/AI works/Job apply AI agent/Job-apply-AI-agent/CV maker/linkedin_jobs_2025-02-27.xlsx\n"
]
}
],
"source": [
"#chekcing the input file is getting correctly\n",
"print(input_file)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Getting the description of the job. fetch_full_job_details"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"def fetch_full_job_details(job_url: str) -> tuple:\n",
" \"\"\"\n",
" Opens the LinkedIn job page, fetches the job title, company name, and full job description.\n",
" Returns (job_title, company_name, job_description).\n",
" \"\"\"\n",
" options = uc.ChromeOptions()\n",
" options.add_argument(\"--headless\") # or remove this if you want to see the browser\n",
" options.add_argument(\"--no-sandbox\")\n",
" options.add_argument(\"--disable-dev-shm-usage\")\n",
"\n",
" driver = uc.Chrome(options=options)\n",
" driver.get(job_url)\n",
"\n",
" # Default empty values\n",
" job_title = \"\"\n",
" company_name = \"\"\n",
" job_description = \"\"\n",
"\n",
" try:\n",
" wait = WebDriverWait(driver, 15)\n",
"\n",
" # 1) Job Title (example selector)\n",
" title_elem = wait.until(\n",
" EC.presence_of_element_located((By.CSS_SELECTOR, \"h1.topcard__title\"))\n",
" )\n",
" job_title = title_elem.get_attribute(\"innerText\")\n",
"\n",
" # 2) Company Name (example selector)\n",
" company_elem = wait.until(\n",
" EC.presence_of_element_located((By.CSS_SELECTOR, \"a.topcard__org-name-link\"))\n",
" )\n",
" company_name = company_elem.get_attribute(\"innerText\")\n",
"\n",
" # 3) Full Job Description (often \"description__text\" class)\n",
" desc_elem = wait.until(\n",
" EC.presence_of_element_located((By.CLASS_NAME, \"description__text\"))\n",
" )\n",
" job_description = desc_elem.get_attribute(\"innerText\")\n",
"\n",
" except Exception as e:\n",
" print(f\"Error scraping {job_url}: {e}\")\n",
"\n",
" finally:\n",
" driver.quit()\n",
"\n",
" return job_title.strip(), company_name.strip(), job_description.strip()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### After modifying the excel sheet with description"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" title \\\n",
"0 Working Student - Digital Analytics (all genders) \n",
"1 Working Student Graphic Design (m/w/d) \n",
"2 Werkstudent \n",
"3 Working Student Corporate and Business Develop... \n",
"4 Working Student in Product Marketing \n",
"\n",
" company \\\n",
"0 Digitl \n",
"1 Fanblast \n",
"2 DDC Management Consultants \n",
"3 PRIOjet GmbH \n",
"4 Rabot Energy \n",
"\n",
" link source \\\n",
"0 https://de.linkedin.com/jobs/view/working-stud... LinkedIn \n",
"1 https://de.linkedin.com/jobs/view/working-stud... LinkedIn \n",
"2 https://de.linkedin.com/jobs/view/werkstudent-... LinkedIn \n",
"3 https://de.linkedin.com/jobs/view/working-stud... LinkedIn \n",
"4 https://de.linkedin.com/jobs/view/working-stud... LinkedIn \n",
"\n",
" posted_days_ago description \\\n",
"0 5 Digitl ist ein junges und innovatives Unterneh... \n",
"1 8 About fanblast\\n\\nFanblast is a fast-growing S... \n",
"2 6 DDC Management Consultants ist als Management-... \n",
"3 6 Hi! We’re happy that you’re here.\\n\\n\\n\\n\\nPRI... \n",
"4 13 Why us?\\n\\nRABOT Energy is looking for a motiv... \n",
"\n",
" Extracted Skills Extracted Requirements \n",
"0 [] [] \n",
"1 [] [required, ability to, proficiency in, experie... \n",
"2 [] [] \n",
"3 [] [required, experience in] \n",
"4 [] [experience in] \n"
]
}
],
"source": [
"import pandas as pd\n",
"import re\n",
"\n",
"# Load the updated Excel file\n",
"input_file = \"final_job_descriptions.xlsx\"\n",
"df = pd.read_excel(input_file)\n",
"\n",
"# Define your existing skills and categories\n",
"my_skills = {\n",
" \"Data Science & Machine Learning\": [\"Python\", \"R\", \"TensorFlow\", \"NumPy\", \"Pandas\", \"Seaborn\", \"Scikit-learn\"],\n",
" \"Statistical Modeling & AI\": [\"ML models\", \"AI\", \"Custom-GPT\", \"Deep Learning\"],\n",
" \"AI Agent\": [\"n8n\", \"Python AI Agent\", \"Automation\"],\n",
" \"Business Intelligence & Dashboarding\": [\"Power BI\", \"Tableau\", \"SQL\", \"Data Visualization\"],\n",
" \"Database Optimization\": [\"SQL\", \"MySQL\", \"PostgreSQL\"],\n",
" \"Programming Languages\": [\"Python\", \"Java\", \"C\", \"JavaScript\"],\n",
" \"Microsoft Tools\": [\"Azure\", \"Microsoft 365\", \"Dynamics 365\"]\n",
"}\n",
"\n",
"# Common requirement phrases\n",
"requirement_keywords = [\"experience in\", \"knowledge of\", \"proficiency in\", \"familiarity with\", \"required\", \"preferred\", \"must have\", \"ability to\"]\n",
"\n",
"def extract_skills_and_requirements(description):\n",
" \"\"\"\n",
" Extracts relevant skills and job requirements from the job description\n",
" based on predefined skills and requirement keywords.\n",
" \"\"\"\n",
" description = description.lower() # Convert to lowercase for easier matching\n",
"\n",
" # Identify matching skills\n",
" matched_skills = set()\n",
" for category, skills in my_skills.items():\n",
" for skill in skills:\n",
" pattern = rf\"\\b{re.escape(skill.lower())}\\b\"\n",
" if re.search(pattern, description):\n",
" matched_skills.add(skill)\n",
"\n",
" # Extract job requirements based on common keywords\n",
" matched_requirements = set()\n",
" for keyword in requirement_keywords:\n",
" if keyword in description:\n",
" matched_requirements.add(keyword)\n",
"\n",
" return list(matched_skills), list(matched_requirements)\n",
"\n",
"def process_job_descriptions(df, desc_col=\"description\", title_col=\"title\"):\n",
" \"\"\"\n",
" Extracts skills and requirements from job descriptions and stores them in the DataFrame.\n",
" \"\"\"\n",
" skills_list = []\n",
" requirements_list = []\n",
"\n",
" for idx, row in df.iterrows():\n",
" description_text = str(row.get(desc_col, \"\"))\n",
" job_title = str(row.get(title_col, \"No Title Provided\"))\n",
"\n",
" if not description_text.strip():\n",
" skills_list.append([])\n",
" requirements_list.append([])\n",
" continue\n",
" \n",
" matched_skills, matched_requirements = extract_skills_and_requirements(description_text)\n",
" skills_list.append(matched_skills)\n",
" requirements_list.append(matched_requirements)\n",
"\n",
" df[\"Extracted Skills\"] = skills_list\n",
" df[\"Extracted Requirements\"] = requirements_list\n",
" return df\n",
"\n",
"# Process the job descriptions and display results\n",
"df = process_job_descriptions(df)\n",
"print(df)\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"##### Getting some keywords"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "CV_R",
"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": "3.11.11"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|