Spaces:
Running
Running
Update app.py
Browse files
app.py
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
import gradio as gr
|
2 |
import logging
|
3 |
from linkedin_jobs_scraper import LinkedinScraper
|
4 |
-
from linkedin_jobs_scraper.events import Events, EventData
|
5 |
from linkedin_jobs_scraper.query import Query, QueryOptions, QueryFilters
|
6 |
-
from linkedin_jobs_scraper.filters import TimeFilters
|
7 |
import pandas as pd
|
8 |
|
9 |
# Configure logging
|
@@ -21,80 +21,93 @@ def on_data(data: EventData):
|
|
21 |
'Location': data.location,
|
22 |
'Job Link': data.link,
|
23 |
'Description Length': len(data.description),
|
|
|
24 |
})
|
25 |
|
26 |
def on_end():
|
27 |
print("[ON_END] Scraping completed.")
|
28 |
|
29 |
-
#
|
30 |
-
def scrape_jobs(query, locations):
|
31 |
global job_data
|
32 |
try:
|
33 |
job_data = []
|
34 |
-
|
35 |
scraper = LinkedinScraper(
|
36 |
chrome_executable_path=None,
|
37 |
chrome_binary_location=None,
|
38 |
chrome_options=None,
|
39 |
headless=True,
|
40 |
-
max_workers=
|
41 |
slow_mo=0.8,
|
42 |
page_load_timeout=60,
|
43 |
)
|
44 |
-
|
45 |
-
# Catching the exception for missing chrome and notify the user
|
46 |
scraper.on(Events.DATA, on_data)
|
47 |
scraper.on(Events.END, on_end)
|
48 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
49 |
queries = [
|
50 |
Query(
|
51 |
query=query,
|
52 |
options=QueryOptions(
|
53 |
locations=locations.split(','),
|
54 |
apply_link=True,
|
55 |
-
skip_promoted_jobs=
|
56 |
page_offset=0,
|
57 |
limit=100,
|
58 |
filters=QueryFilters(
|
59 |
-
|
|
|
60 |
),
|
61 |
),
|
62 |
),
|
63 |
]
|
64 |
|
65 |
scraper.run(queries)
|
66 |
-
|
67 |
-
# Convert to DataFrame and return
|
68 |
if job_data:
|
69 |
-
df = pd.DataFrame(job_data)
|
70 |
-
|
|
|
71 |
else:
|
72 |
-
return pd.DataFrame(),
|
|
|
73 |
except Exception as e:
|
74 |
# Handle errors gracefully
|
75 |
-
message = f"
|
76 |
return None, message
|
77 |
|
78 |
-
|
79 |
-
|
80 |
-
df, message
|
81 |
-
return df, message
|
82 |
|
83 |
-
#
|
84 |
iface = gr.Interface(
|
85 |
fn=gradio_interface,
|
86 |
inputs=[
|
87 |
gr.Textbox(label="Job Query", placeholder="e.g., Data Scientist", value="Unity developers"),
|
88 |
-
gr.Textbox(label="Locations (comma-separated)", placeholder="e.g., United States", value="United States"),
|
|
|
|
|
|
|
|
|
|
|
|
|
89 |
],
|
90 |
outputs=[
|
91 |
-
gr.Dataframe(label="Job Results", headers=[
|
92 |
gr.Textbox(label="Message"),
|
93 |
],
|
94 |
-
title="
|
95 |
-
description="
|
96 |
)
|
97 |
|
98 |
-
# Launch app
|
99 |
if __name__ == "__main__":
|
100 |
-
iface.launch()
|
|
|
1 |
import gradio as gr
|
2 |
import logging
|
3 |
from linkedin_jobs_scraper import LinkedinScraper
|
4 |
+
from linkedin_jobs_scraper.events import Events, EventData, EventMetrics
|
5 |
from linkedin_jobs_scraper.query import Query, QueryOptions, QueryFilters
|
6 |
+
from linkedin_jobs_scraper.filters import RelevanceFilters, TimeFilters, OnSiteOrRemoteFilters
|
7 |
import pandas as pd
|
8 |
|
9 |
# Configure logging
|
|
|
21 |
'Location': data.location,
|
22 |
'Job Link': data.link,
|
23 |
'Description Length': len(data.description),
|
24 |
+
'Description': data.description,
|
25 |
})
|
26 |
|
27 |
def on_end():
|
28 |
print("[ON_END] Scraping completed.")
|
29 |
|
30 |
+
# Scraper function
|
31 |
+
def scrape_jobs(query, locations, time_filter):
|
32 |
global job_data
|
33 |
try:
|
34 |
job_data = []
|
35 |
+
|
36 |
scraper = LinkedinScraper(
|
37 |
chrome_executable_path=None,
|
38 |
chrome_binary_location=None,
|
39 |
chrome_options=None,
|
40 |
headless=True,
|
41 |
+
max_workers=10,
|
42 |
slow_mo=0.8,
|
43 |
page_load_timeout=60,
|
44 |
)
|
45 |
+
|
|
|
46 |
scraper.on(Events.DATA, on_data)
|
47 |
scraper.on(Events.END, on_end)
|
48 |
|
49 |
+
if time_filter == "From Past Month":
|
50 |
+
time_filter = TimeFilters.MONTH
|
51 |
+
elif time_filter == "From Last 24 Hours":
|
52 |
+
time_filter = TimeFilters.DAY
|
53 |
+
else:
|
54 |
+
time_filter = TimeFilters.MONTH
|
55 |
+
|
56 |
queries = [
|
57 |
Query(
|
58 |
query=query,
|
59 |
options=QueryOptions(
|
60 |
locations=locations.split(','),
|
61 |
apply_link=True,
|
62 |
+
skip_promoted_jobs=False,
|
63 |
page_offset=0,
|
64 |
limit=100,
|
65 |
filters=QueryFilters(
|
66 |
+
# relevance=RelevanceFilters.RECENT,
|
67 |
+
time=time_filter,
|
68 |
),
|
69 |
),
|
70 |
),
|
71 |
]
|
72 |
|
73 |
scraper.run(queries)
|
74 |
+
|
|
|
75 |
if job_data:
|
76 |
+
df = pd.DataFrame(job_data)
|
77 |
+
message = f"Jobs ({len(job_data)}) data successfully scraped."
|
78 |
+
return df, message
|
79 |
else:
|
80 |
+
return pd.DataFrame(), '-'
|
81 |
+
|
82 |
except Exception as e:
|
83 |
# Handle errors gracefully
|
84 |
+
message = f"An error occurred during scraping: {e}"
|
85 |
return None, message
|
86 |
|
87 |
+
def gradio_interface(query, locations, time_filter):
|
88 |
+
df, message = scrape_jobs(query, locations, time_filter)
|
89 |
+
return df, message
|
|
|
90 |
|
91 |
+
#App Layout
|
92 |
iface = gr.Interface(
|
93 |
fn=gradio_interface,
|
94 |
inputs=[
|
95 |
gr.Textbox(label="Job Query", placeholder="e.g., Data Scientist", value="Unity developers"),
|
96 |
+
gr.Textbox(label="Locations (comma-separated)", placeholder="e.g., United States, India", value="United States, United Kingdom, Canada, Germany, India"),
|
97 |
+
gr.Dropdown(
|
98 |
+
label="Time Filter",
|
99 |
+
choices=["From Past Month", "From Last 24 Hours"],
|
100 |
+
value="From Past Month", # Default option
|
101 |
+
type="value",
|
102 |
+
),
|
103 |
],
|
104 |
outputs=[
|
105 |
+
gr.Dataframe(label="Job Results", headers=['Date','Company', 'ApplyLink'], interactive=True),
|
106 |
gr.Textbox(label="Message"),
|
107 |
],
|
108 |
+
title="Job Scraper",
|
109 |
+
description="Enter a job query and locations to scrape job postings and display the results in a table.",
|
110 |
)
|
111 |
|
|
|
112 |
if __name__ == "__main__":
|
113 |
+
iface.launch()
|