Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
import os
|
| 2 |
import gradio as gr
|
| 3 |
-
import
|
| 4 |
from bs4 import BeautifulSoup
|
| 5 |
from urllib.parse import urlencode
|
| 6 |
from fastmcp import FastMCP
|
|
@@ -11,7 +11,7 @@ mcp = FastMCP("Indeed Web Scraper Agent")
|
|
| 11 |
@mcp.tool(name="search_jobs")
|
| 12 |
def search_jobs_tool(query: str, location: str, limit: int = 10, salary: str = None, job_type: str = None):
|
| 13 |
"""
|
| 14 |
-
Scrape jobs from Indeed website using
|
| 15 |
|
| 16 |
Args:
|
| 17 |
query (str): Job title or keywords to search for.
|
|
@@ -32,12 +32,10 @@ def search_jobs_tool(query: str, location: str, limit: int = 10, salary: str = N
|
|
| 32 |
}
|
| 33 |
|
| 34 |
url = base_url + urlencode(params)
|
| 35 |
-
headers = {
|
| 36 |
-
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64)"
|
| 37 |
-
}
|
| 38 |
|
| 39 |
try:
|
| 40 |
-
|
|
|
|
| 41 |
response.raise_for_status()
|
| 42 |
|
| 43 |
soup = BeautifulSoup(response.text, "html.parser")
|
|
@@ -94,8 +92,8 @@ app = gr.Interface(
|
|
| 94 |
gr.Textbox(label="Job Type (optional, ignored)")
|
| 95 |
],
|
| 96 |
outputs="markdown",
|
| 97 |
-
title="Indeed Job Search (with BeautifulSoup) + FastMCP",
|
| 98 |
-
description="Search jobs by scraping Indeed.ca using
|
| 99 |
)
|
| 100 |
|
| 101 |
if __name__ == "__main__":
|
|
|
|
| 1 |
import os
|
| 2 |
import gradio as gr
|
| 3 |
+
import cloudscraper
|
| 4 |
from bs4 import BeautifulSoup
|
| 5 |
from urllib.parse import urlencode
|
| 6 |
from fastmcp import FastMCP
|
|
|
|
| 11 |
@mcp.tool(name="search_jobs")
|
| 12 |
def search_jobs_tool(query: str, location: str, limit: int = 10, salary: str = None, job_type: str = None):
|
| 13 |
"""
|
| 14 |
+
Scrape jobs from Indeed website using cloudscraper + BeautifulSoup.
|
| 15 |
|
| 16 |
Args:
|
| 17 |
query (str): Job title or keywords to search for.
|
|
|
|
| 32 |
}
|
| 33 |
|
| 34 |
url = base_url + urlencode(params)
|
|
|
|
|
|
|
|
|
|
| 35 |
|
| 36 |
try:
|
| 37 |
+
scraper = cloudscraper.create_scraper()
|
| 38 |
+
response = scraper.get(url)
|
| 39 |
response.raise_for_status()
|
| 40 |
|
| 41 |
soup = BeautifulSoup(response.text, "html.parser")
|
|
|
|
| 92 |
gr.Textbox(label="Job Type (optional, ignored)")
|
| 93 |
],
|
| 94 |
outputs="markdown",
|
| 95 |
+
title="Indeed Job Search (with BeautifulSoup + Cloudscraper) + FastMCP",
|
| 96 |
+
description="Search jobs by scraping Indeed.ca using cloudscraper and BeautifulSoup. Results sorted by most recent."
|
| 97 |
)
|
| 98 |
|
| 99 |
if __name__ == "__main__":
|