Remove extra logging
This commit is contained in:
parent
0bd9f05250
commit
9a449bf3ca
|
@ -83,41 +83,32 @@ def update_story(story, is_manual=False):
|
||||||
elif story['source'] == 'manual':
|
elif story['source'] == 'manual':
|
||||||
res = manual.story(story['ref'])
|
res = manual.story(story['ref'])
|
||||||
|
|
||||||
logging.info('Got story')
|
|
||||||
|
|
||||||
if res:
|
if res:
|
||||||
story.update(res) # join dicts
|
story.update(res) # join dicts
|
||||||
else:
|
else:
|
||||||
logging.info('Story not ready yet')
|
logging.info('Story not ready yet')
|
||||||
return False
|
return False
|
||||||
|
|
||||||
logging.info('story joined')
|
|
||||||
|
|
||||||
if story['date'] and not is_manual and story['date'] + TWO_DAYS < time.time():
|
if story['date'] and not is_manual and story['date'] + TWO_DAYS < time.time():
|
||||||
logging.info('Story too old, removing')
|
logging.info('Story too old, removing')
|
||||||
return False
|
return False
|
||||||
|
|
||||||
logging.info('story age good')
|
|
||||||
|
|
||||||
if story.get('url', '') and not story.get('text', ''):
|
if story.get('url', '') and not story.get('text', ''):
|
||||||
logging.info('inside if')
|
logging.info('inside if')
|
||||||
if not get_content_type(story['url']).startswith('text/'):
|
if not get_content_type(story['url']).startswith('text/'):
|
||||||
logging.info('URL invalid file type / content type:')
|
logging.info('URL invalid file type / content type:')
|
||||||
logging.info(story['url'])
|
logging.info(story['url'])
|
||||||
return False
|
return False
|
||||||
logging.info('content type good')
|
|
||||||
|
|
||||||
if any([domain in story['url'] for domain in INVALID_DOMAINS]):
|
if any([domain in story['url'] for domain in INVALID_DOMAINS]):
|
||||||
logging.info('URL invalid domain:')
|
logging.info('URL invalid domain:')
|
||||||
logging.info(story['url'])
|
logging.info(story['url'])
|
||||||
return False
|
return False
|
||||||
logging.info('domain good')
|
|
||||||
|
|
||||||
logging.info('Getting article ' + story['url'])
|
logging.info('Getting article ' + story['url'])
|
||||||
story['text'] = get_article(story['url'])
|
story['text'] = get_article(story['url'])
|
||||||
if not story['text']: return False
|
if not story['text']: return False
|
||||||
|
|
||||||
logging.info('returning true')
|
|
||||||
return True
|
return True
|
||||||
|
|
||||||
if __name__ == '__main__':
|
if __name__ == '__main__':
|
||||||
|
|
|
@ -73,14 +73,10 @@ def story(ref):
|
||||||
html = api(API_ITEM(ref))
|
html = api(API_ITEM(ref))
|
||||||
if not html: return False
|
if not html: return False
|
||||||
|
|
||||||
logging.info('Got Tildes html')
|
|
||||||
|
|
||||||
soup = BeautifulSoup(html, features='html.parser')
|
soup = BeautifulSoup(html, features='html.parser')
|
||||||
a = soup.find('article', class_='topic-full')
|
a = soup.find('article', class_='topic-full')
|
||||||
if a is None: return False
|
if a is None: return False
|
||||||
|
|
||||||
logging.info('Got article tag')
|
|
||||||
|
|
||||||
h = a.find('header')
|
h = a.find('header')
|
||||||
lu = h.find('a', class_='link-user')
|
lu = h.find('a', class_='link-user')
|
||||||
|
|
||||||
|
@ -106,8 +102,6 @@ def story(ref):
|
||||||
ch = a.find('header', class_='topic-comments-header')
|
ch = a.find('header', class_='topic-comments-header')
|
||||||
s['num_comments'] = int(ch.h2.string.split(' ')[0]) if ch else 0
|
s['num_comments'] = int(ch.h2.string.split(' ')[0]) if ch else 0
|
||||||
|
|
||||||
logging.info('Parsed html data')
|
|
||||||
|
|
||||||
if s['score'] < 8 and s['num_comments'] < 6:
|
if s['score'] < 8 and s['num_comments'] < 6:
|
||||||
return False
|
return False
|
||||||
|
|
||||||
|
|
Loading…
Reference in New Issue
Block a user