def test_clean_html_body(self):
from yarss2 import load_libs
load_libs()
web_page = """<html>
<head>
<title>
Page title
</title>
</head>
<body>
<p id="firstpara" align="center">
This is paragraph
<b>
one
</b>
</p>
<p id="secondpara" align="blah">
This is paragraph
<b>
two
</b>
</p>
</body>
</html>"""
http.clean_html_body(web_page)
def test_clean_html_body(self):
from yarss2 import load_libs
load_libs()
web_page = """<html>
<head>
<title>
Page title
</title>
</head>
<body>
<p id="firstpara" align="center">
This is paragraph
<b>
one
</b>
</p>
<p id="secondpara" align="blah">
This is paragraph
<b>
two
</b>
</p>
</body>
</html>"""
cleaned = http.clean_html_body(web_page)
def add_torrent_callback(torrent_download):
torrent_download = TorrentDownload(torrent_download)
if torrent_download.success:
return
textview = self.glade.get_widget("textview_messages")
textbuffer = textview.get_buffer()
readable_body = http.clean_html_body(torrent_download.filedump)
textbuffer.set_text(readable_body)
notebook = self.glade.get_widget("notebook_lower")
notebook.set_current_page(1)
# Quick hack to make sure the message is visible to the user.
hpaned = self.glade.get_widget("hpaned_matching")
#if hpaned.get_position() == 0:
max_pos = hpaned.get_property("max-position")
hpaned.set_position(int(max_pos * 0.3))
def add_torrent_callback(torrent_download):
torrent_download = TorrentDownload(torrent_download)
if torrent_download.success:
return True
if torrent_download.filedump is None:
return
readable_body = http.clean_html_body(torrent_download.filedump)
textbuffer = self.get_object("textview_messages").get_buffer()
textbuffer.set_text(readable_body)
self.get_object("notebook_lower").set_current_page(1)
# Quick hack to make sure the message is visible to the user.
hpaned = self.get_object("hpaned_matching")
max_pos = hpaned.get_property("max-position")
hpaned.set_position(int(max_pos * 0.3))
return False
def fetch_and_parse_rssfeed_atom(url_file_stream_or_string, site_cookies_dict=None,
user_agent=None, request_headers=None, timeout=10):
result = http.download_file(url_file_stream_or_string, site_cookies_dict=site_cookies_dict,
user_agent=user_agent, request_headers=request_headers, timeout=timeout)
import atoma
atoma.rss.supported_rss_versions = []
parsed_feeds = {}
try:
atoma_result = atoma.parse_rss_bytes(result['content'])
parsed_feeds = atoma_result_to_dict(atoma_result)
except atoma.FeedXMLError as err:
readable_body = http.clean_html_body(result['content'])
parsed_feeds["raw_result"] = readable_body
parsed_feeds["bozo"] = 1
parsed_feeds["feed"] = {}
parsed_feeds["items"] = []
parsed_feeds["bozo_exception"] = err
parsed_feeds['parser'] = "atoma"
return parsed_feeds