coss_archiving/manual/gather_media_files.py

70 lines
2.0 KiB
Python

"""
Runs the news_fetch pipeline against a manually curated list of urls and saves them locally
"""
import sys
sys.path.append("../news_fetch")
import runner
import os
import logging
logger = logging.getLogger()
class DummyMessage:
"""Required by the dispatcher"""
ts = 0
def __init__(self, url):
self.urls = [url]
def fetch():
dispatcher = runner.Dispatcher()
dispatcher.workers_in = [
{"FetchWorker": runner.FetchWorker(), "DownloadWorker": runner.DownloadWorker()},
{"UploadWorker": runner.UploadWorker()}
]
print_worker = runner.PrintWorker("Finished processing", sent = True)
dispatcher.workers_out = [{"PrintWorker": print_worker}]
dispatcher.start()
with open("media_urls.txt", "r") as f:
url_list = [l.replace("\n", "") for l in f.readlines()]
with open("media_urls.txt", "w") as f:
f.write("") # empty the file once it is read so that it does not get processed again
if url_list:
logger.info(f"Found {len(url_list)} media urls")
for u in url_list:
dispatcher.incoming_request(DummyMessage(u))
else:
logger.info(f"No additional media urls found. Running the pipeline with messages from db.")
print_worker.keep_alive()
def show():
for a in runner.models.ArticleDownload.select():
print(f"""
URL: {a.article_url}
ARCHIVE_URL: {a.archive_url}
ARTICLE_SOURCE: {a.source_name}
FILE_NAME: {a.file_name}
""")
if __name__ == "__main__":
logger.info("Overwriting production values for single time media-fetch")
if not os.path.exists("../.dev/"):
os.mkdir("../.dev/")
runner.configuration.models.set_db(
runner.configuration.SqliteDatabase("../.dev/media_downloads.db")
)
runner.configuration.main_config["downloads"]["local_storage_path"] = "../.dev/"
if len(sys.argv) == 1: # no additional arguments
fetch()
elif sys.argv[1] == "show":
show()