aboutsummaryrefslogtreecommitdiff
path: root/pyaggr3g470r/lib
diff options
context:
space:
mode:
authorFrançois Schmidts <francois.schmidts@gmail.com>2015-07-05 17:41:06 +0200
committerFrançois Schmidts <francois.schmidts@gmail.com>2015-07-06 09:04:58 +0200
commitc1551acb30513f96d0053b96e240da7ab68833d2 (patch)
tree9b7beac4a521edf095d6c352cd2d0801428b521b /pyaggr3g470r/lib
parentconstructing feed from normal url also (diff)
downloadnewspipe-c1551acb30513f96d0053b96e240da7ab68833d2.tar.gz
newspipe-c1551acb30513f96d0053b96e240da7ab68833d2.tar.bz2
newspipe-c1551acb30513f96d0053b96e240da7ab68833d2.zip
making bookmaklet work for any url
Diffstat (limited to 'pyaggr3g470r/lib')
-rw-r--r--pyaggr3g470r/lib/utils.py21
1 files changed, 13 insertions, 8 deletions
diff --git a/pyaggr3g470r/lib/utils.py b/pyaggr3g470r/lib/utils.py
index 6d6725c8..a4f2e043 100644
--- a/pyaggr3g470r/lib/utils.py
+++ b/pyaggr3g470r/lib/utils.py
@@ -1,9 +1,12 @@
import types
import urllib
+import logging
import requests
import feedparser
from bs4 import BeautifulSoup, SoupStrainer
+logger = logging.getLogger(__name__)
+
def default_handler(obj):
"""JSON handler for default query formatting"""
@@ -48,8 +51,13 @@ def construct_feed_from(url=None, fp_parsed=None, feed=None, query_site=True):
if url is None and fp_parsed is not None:
url = fp_parsed.get('url')
if url is not None and fp_parsed is None:
- response = requests.get(url, verify=False)
- fp_parsed = feedparser.parse(response.content)
+ try:
+ response = requests.get(url, verify=False)
+ fp_parsed = feedparser.parse(response.content,
+ request_headers=response.headers)
+ except Exception:
+ logger.exception('failed to retreive that url')
+ fp_parsed = {'bozo': True}
assert url is not None and fp_parsed is not None
feed = feed or {}
feed_split = urllib.parse.urlsplit(url)
@@ -106,17 +114,14 @@ def construct_feed_from(url=None, fp_parsed=None, feed=None, query_site=True):
if feed['icon'] is not None:
break
- if feed['icon'] is None:
+ if feed.get('icon') is None:
feed['icon'] = try_splits('/favicon.ico', site_split, feed_split)
- if feed['icon'] is None:
+ if 'icon' in feed and feed['icon'] is None:
del feed['icon']
if not feed.get('link'):
alternate = bs_parsed.find_all(check_keys(rel=['alternate'],
type=['application/rss+xml']))
- if len(alternate) == 1:
- feed['link'] = alternate[0].attrs['href']
- elif len(alternate) > 1:
+ if len(alternate) >= 1:
feed['link'] = alternate[0].attrs['href']
- feed['other_link'] = [al.attrs['href'] for al in alternate[1:]]
return feed
bgstack15