diff options
author | Cédric Bonhomme <cedric@cedricbonhomme.org> | 2020-02-26 11:27:31 +0100 |
---|---|---|
committer | Cédric Bonhomme <cedric@cedricbonhomme.org> | 2020-02-26 11:27:31 +0100 |
commit | 62b3afeeedfe054345f86093e2d243e956c1e3c9 (patch) | |
tree | bbd58f5c8c07f5d87b1c1cca73fa1d5af6178f48 /src/lib/utils.py | |
parent | Updated Python dependencies. (diff) | |
download | newspipe-62b3afeeedfe054345f86093e2d243e956c1e3c9.tar.gz newspipe-62b3afeeedfe054345f86093e2d243e956c1e3c9.tar.bz2 newspipe-62b3afeeedfe054345f86093e2d243e956c1e3c9.zip |
The project is now using Poetry.
Diffstat (limited to 'src/lib/utils.py')
-rw-r--r-- | src/lib/utils.py | 89 |
1 files changed, 0 insertions, 89 deletions
diff --git a/src/lib/utils.py b/src/lib/utils.py deleted file mode 100644 index d206b769..00000000 --- a/src/lib/utils.py +++ /dev/null @@ -1,89 +0,0 @@ -import re -import types -import urllib -import logging -import requests -from hashlib import md5 -from flask import request, url_for - -import conf - -logger = logging.getLogger(__name__) - - -def default_handler(obj, role='admin'): - """JSON handler for default query formatting""" - if hasattr(obj, 'isoformat'): - return obj.isoformat() - if hasattr(obj, 'dump'): - return obj.dump(role=role) - if isinstance(obj, (set, frozenset, types.GeneratorType)): - return list(obj) - if isinstance(obj, BaseException): - return str(obj) - raise TypeError("Object of type %s with value of %r " - "is not JSON serializable" % (type(obj), obj)) - - -def try_keys(dico, *keys): - for key in keys: - if key in dico: - return dico[key] - return - - -def rebuild_url(url, base_split): - split = urllib.parse.urlsplit(url) - if split.scheme and split.netloc: - return url # url is fine - new_split = urllib.parse.SplitResult( - scheme=split.scheme or base_split.scheme, - netloc=split.netloc or base_split.netloc, - path=split.path, query='', fragment='') - return urllib.parse.urlunsplit(new_split) - - -def try_get_icon_url(url, *splits): - for split in splits: - if split is None: - continue - rb_url = rebuild_url(url, split) - response = None - # if html in content-type, we assume it's a fancy 404 page - try: - response = jarr_get(rb_url) - content_type = response.headers.get('content-type', '') - except Exception: - pass - else: - if response is not None and response.ok \ - and 'html' not in content_type and response.content: - return response.url - return None - - -def to_hash(text): - return md5(text.encode('utf8') if hasattr(text, 'encode') else text)\ - .hexdigest() - - -def clear_string(data): - """ - Clear a string by removing HTML tags, HTML special caracters - and consecutive white spaces (more that one). - """ - p = re.compile('<[^>]+>') # HTML tags - q = re.compile('\s') # consecutive white spaces - return p.sub('', q.sub(' ', data)) - - -def redirect_url(default='home'): - return request.args.get('next') or request.referrer or url_for(default) - - -async def jarr_get(url, **kwargs): - request_kwargs = {'verify': False, 'allow_redirects': True, - 'timeout': conf.CRAWLER_TIMEOUT, - 'headers': {'User-Agent': conf.CRAWLER_USER_AGENT}} - request_kwargs.update(kwargs) - return requests.get(url, **request_kwargs) |