indymedia
/
epicyon
mirror of https://gitlab.com/bashrc2/epicyon
7
4
Fork 1
Code Issues 14 Releases Wiki Activity

Add exception for file read

merge-requests/30/head
Bob Mottram 2024-07-18 20:32:03 +01:00
parent 8c30b537ab
commit e95f6b8261
1 changed files with 45 additions and 41 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

86
webapp_hashtagswarm.py
View File

@ -138,48 +138,52 @@ def html_hash_tag_swarm(base_dir: str, actor: str, translate: {}) -> str:
tags_filename) tags_filename)
continue continue
with open(tags_filename, 'r', encoding='utf-8') as fp_tags: try:
while True: with open(tags_filename, 'r', encoding='utf-8') as fp_tags:
line = fp_tags.readline() while True:
if not line: line = fp_tags.readline()
break if not line:
if ' ' not in line: break
break if ' ' not in line:
sections = line.split(' ') break
if len(sections) != 3: sections = line.split(' ')
break if len(sections) != 3:
post_days_since_epoch_str = sections[0] break
if not post_days_since_epoch_str.isdigit(): post_days_since_epoch_str = sections[0]
break if not post_days_since_epoch_str.isdigit():
post_days_since_epoch = int(post_days_since_epoch_str) break
if post_days_since_epoch < recently: post_days_since_epoch = int(post_days_since_epoch_str)
break if post_days_since_epoch < recently:
post_url = sections[2] break
if '##' not in post_url: post_url = sections[2]
break if '##' not in post_url:
post_domain = post_url.split('##')[1] break
if '#' in post_domain: post_domain = post_url.split('##')[1]
post_domain = post_domain.split('#')[0] if '#' in post_domain:
post_domain = post_domain.split('#')[0]
if domain_histogram.get(post_domain): if domain_histogram.get(post_domain):
domain_histogram[post_domain] = \ domain_histogram[post_domain] = \
domain_histogram[post_domain] + 1 domain_histogram[post_domain] + 1
else: else:
domain_histogram[post_domain] = 1 domain_histogram[post_domain] = 1
tag_swarm.append(hash_tag_name) tag_swarm.append(hash_tag_name)
category_filename = \ category_filename = \
tags_filename.replace('.txt', '.category') tags_filename.replace('.txt', '.category')
if os.path.isfile(category_filename): if os.path.isfile(category_filename):
category_str = \ category_str = \
get_hashtag_category(base_dir, hash_tag_name) get_hashtag_category(base_dir, hash_tag_name)
if len(category_str) < max_tag_length: if len(category_str) < max_tag_length:
if '#' not in category_str and \ if '#' not in category_str and \
'&' not in category_str and \ '&' not in category_str and \
'"' not in category_str and \ '"' not in category_str and \
"'" not in category_str: "'" not in category_str:
if category_str not in category_swarm: if category_str not in category_swarm:
category_swarm.append(category_str) category_swarm.append(category_str)
break break
except OSError as exc:
print('EX: html_hash_tag_swarm unable to read ' +
tags_filename + ' ' + str(exc))
break break
if not tag_swarm: if not tag_swarm: