Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Update requirements #5

Merged
merged 2 commits into from
Apr 14, 2024
Merged

Update requirements #5

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
12d03a8
update requirements and delete temp dirs
sk-ram Apr 14, 2024
6734029
scrape all pages
sk-ram Apr 14, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
23 changes: 15 additions & 8 deletions app/scraper.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,7 @@
from instructor import Instructor
from openai import OpenAI
from geopy.geocoders import Nominatim

import shutil
class messageData(BaseModel):
city: str
country: str
Expand Down Expand Up @@ -111,8 +111,10 @@ def scrape(
lfp = f"{work_dir}/twitter/tweet_{page}.json"

save_tweets(new_tweets, lfp)
scraped_data_repository.register_scraped_json(current_data, job_id, lfp )

try:
scraped_data_repository.register_scraped_json(current_data, job_id, lfp )
except Exception as e:
logger.info("could not register file")
last_successful_data = current_data
else:
logger.error(f"{job_id}: Error: {response.status_code} - {response.text}")
Expand All @@ -125,8 +127,10 @@ def scrape(
protocol=protocol,
relative_path=f"twitter/{tracer_id}/{job_id}/scraped/tweet_all.json",
)
scraped_data_repository.register_scraped_json(final_data, job_id, f"{work_dir}/twitter/tweet_all.json" )

try:
scraped_data_repository.register_scraped_json(final_data, job_id, f"{work_dir}/twitter/tweet_all.json" )
except Exception as e:
logger.info("could not register file")
# write augmented data to file: --> title, content, extracted_location, lattitude, longitude, month, day, year, disaster_type

df = pd.DataFrame(augmented_results, columns=["Title", "Tweet", "Extracted_Location", "Resolved_Latitude", "Resolved_Longitude", "Month", "Day", "Year", "Disaster_Type"])
Expand All @@ -137,8 +141,10 @@ def scrape(
protocol=protocol,
relative_path=f"twitter/{tracer_id}/{job_id}/augmented/data.json",
)
scraped_data_repository.register_scraped_json(final_augmented_data, job_id, f"{work_dir}/twitter/augmented_twitter_scrape.json" )

try:
scraped_data_repository.register_scraped_json(final_augmented_data, job_id, f"{work_dir}/twitter/augmented_twitter_scrape.json" )
except Exception as e:
logger.info("could not register file")
break
except requests.exceptions.HTTPError as e:
job_state = BaseJobState.FAILED
Expand All @@ -162,7 +168,7 @@ def scrape(

job_state = BaseJobState.FINISHED
logger.info(f"{job_id}: Job finished")

shutil.rmtree(work_dir)
return JobOutput(
job_state=job_state,
tracer_id=str(job_id),
Expand All @@ -172,6 +178,7 @@ def scrape(
except Exception as error:
logger.error(f"{job_id}: Unable to scrape data. Job with tracer_id {job_id} failed. Error:\n{error}")
job_state = BaseJobState.FAILED
shutil.rmtree(work_dir)
return JobOutput(
job_state=job_state,
tracer_id=str(job_id),
Expand Down
4 changes: 2 additions & 2 deletions requirements.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,8 +12,8 @@ idna==3.4
instructor==1.1.0
numpy==1.26.1
pandas==2.1.3
pydantic==2.4.2
pydantic_core==2.10.1
pydantic==2.7.0
pydantic_core==2.18.1
python-dateutil==2.8.2
python-dotenv==1.0.0
pytz==2023.3.post1
Expand Down