denis/spiderss
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

add postprocessing error handling

Browse source
This commit is contained in:
Denis Lehmann 2020-04-18 12:21:50 +02:00
parent 6247a29f90
commit c162c8ba44
1 changed files with 9 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

12
spiderss.py
View file

@ -129,10 +129,16 @@ def get_article_body(article, scrape):
# Postprocess HTML # Postprocess HTML
def postprocess(text): def postprocess(text):
processor = subprocess.Popen(postprocessor.split(' '), stdin = subprocess.PIPE, stdout = subprocess.PIPE, stderr = subprocess.STDOUT) try:
output = processor.communicate(input = text.encode())[0].decode().strip() processor = subprocess.Popen(postprocessor.split(' '), stdin = subprocess.PIPE, stdout = subprocess.PIPE, stderr = subprocess.PIPE)
(output, err) = processor.communicate(input = text.encode())
if err:
raise Exception(err.decode().strip())
except Exception as e:
error(' while postprocessing: {}'.format(e))
sys.exit(1)
return output return output.decode().strip()
# Get constructed article # Get constructed article