diff options
| author | François Schmidts <francois.schmidts@gmail.com> | 2015-07-07 14:42:26 +0200 |
|---|---|---|
| committer | François Schmidts <francois.schmidts@gmail.com> | 2015-07-07 14:42:26 +0200 |
| commit | 9c9e1058c588a3e2f80e35c5dd95bac234e597f4 (patch) | |
| tree | 12b8cc24e0ef68c95c6950e306c4494ed3c1f273 /pyaggr3g470r/lib | |
| parent | making the crawler getting the feed with high traffic earlier (diff) | |
| download | newspipe-9c9e1058c588a3e2f80e35c5dd95bac234e597f4.tar.gz newspipe-9c9e1058c588a3e2f80e35c5dd95bac234e597f4.tar.bz2 newspipe-9c9e1058c588a3e2f80e35c5dd95bac234e597f4.zip | |
rebuilding feed url as well
Diffstat (limited to 'pyaggr3g470r/lib')
| -rw-r--r-- | pyaggr3g470r/lib/feed_utils.py | 7 | ||||
| -rw-r--r-- | pyaggr3g470r/lib/utils.py | 2 |
2 files changed, 6 insertions, 3 deletions
diff --git a/pyaggr3g470r/lib/feed_utils.py b/pyaggr3g470r/lib/feed_utils.py index a7149d79..367fd4b5 100644 --- a/pyaggr3g470r/lib/feed_utils.py +++ b/pyaggr3g470r/lib/feed_utils.py @@ -23,6 +23,7 @@ def construct_feed_from(url=None, fp_parsed=None, feed=None, query_site=True): assert url is not None and fp_parsed is not None feed = feed or {} feed_split = urllib.parse.urlsplit(url) + site_split = None if not fp_parsed['bozo']: feed['link'] = url feed['site_link'] = try_keys(fp_parsed['feed'], 'href', 'link') @@ -82,8 +83,8 @@ def construct_feed_from(url=None, fp_parsed=None, feed=None, query_site=True): del feed['icon'] if not feed.get('link'): - alternate = bs_parsed.find_all(check_keys(rel=['alternate'], + alternates = bs_parsed.find_all(check_keys(rel=['alternate'], type=['application/rss+xml'])) - if len(alternate) >= 1: - feed['link'] = alternate[0].attrs['href'] + if len(alternates) >= 1: + feed['link'] = rebuild_url(alternates[0].attrs['href'], feed_split) return feed diff --git a/pyaggr3g470r/lib/utils.py b/pyaggr3g470r/lib/utils.py index 280256f6..62284de1 100644 --- a/pyaggr3g470r/lib/utils.py +++ b/pyaggr3g470r/lib/utils.py @@ -42,6 +42,8 @@ def rebuild_url(url, base_split): def try_splits(url, *splits): for split in splits: + if split is None: + continue rb_url = rebuild_url(url, split) response = requests.get(rb_url, verify=False, timeout=10) if response.ok and 'html' not in response.headers['content-type']: |