def test_lxml_etree_bug(self):
try:
import lxml.etree
except ImportError:
pass
else:
doc = u"<feed>&illformed_charref</feed>".encode('utf8')
# Importing lxml.etree currently causes libxml2 to
# throw SAXException instead of SAXParseException.
feedparser.parse(feedparser._StringIO(doc))
self.assertTrue(True)
def test_lxml_etree_bug(self):
try:
import lxml.etree
except ImportError:
pass
else:
doc = u"<feed>&illformed_charref</feed>".encode('utf8')
# Importing lxml.etree currently causes libxml2 to
# throw SAXException instead of SAXParseException.
feedparser.parse(feedparser._StringIO(doc))
self.assertTrue(True)
def send_head(self):
"""Send custom headers defined in test case
Example:
<!--
Header: Content-type: application/atom+xml
Header: X-Foo: bar
-->
"""
# Short-circuit the HTTP status test `test_redirect_to_304()`
if self.path == "/-/return-304.xml":
self.send_response(304)
self.send_header("Content-type", "text/xml")
self.end_headers()
return feedparser._StringIO(u"".encode("utf-8"))
path = self.translate_path(self.path)
# the compression tests' filenames determine the header sent
if self.path.startswith("/tests/compression"):
if self.path.endswith("gz"):
headers = {"Content-Encoding": "gzip"}
else:
headers = {"Content-Encoding": "deflate"}
headers["Content-type"] = "application/xml"
else:
headers = dict(
[
(k.decode("utf-8"), v.decode("utf-8").strip())
for k, v in self.headers_re.findall(open(path, "rb").read())
]
)
f = open(path, "rb")
if (self.headers.get("if-modified-since") == headers.get("Last-Modified", "nom")) or (
self.headers.get("if-none-match") == headers.get("ETag", "nomatch")
):
status = 304
else:
status = 200
headers.setdefault("Status", status)
self.send_response(int(headers["Status"]))
headers.setdefault("Content-type", self.guess_type(path))
self.send_header("Content-type", headers["Content-type"])
self.send_header("Content-Length", str(os.stat(f.name)[6]))
for k, v in headers.items():
if k not in ("Status", "Content-type"):
self.send_header(k, v)
self.end_headers()
return f
def send_head(self):
"""Send custom headers defined in test case
Example:
<!--
Header: Content-type: application/atom+xml
Header: X-Foo: bar
-->
"""
# Short-circuit the HTTP status test `test_redirect_to_304()`
if self.path == '/-/return-304.xml':
self.send_response(304)
self.send_header('Content-type', 'text/xml')
self.end_headers()
return feedparser._StringIO(u''.encode('utf-8'))
path = self.translate_path(self.path)
# the compression tests' filenames determine the header sent
if self.path.startswith('/tests/compression'):
if self.path.endswith('gz'):
headers = {'Content-Encoding': 'gzip'}
else:
headers = {'Content-Encoding': 'deflate'}
headers['Content-type'] = 'application/xml'
else:
headers = dict([
(k.decode('utf-8'), v.decode('utf-8').strip())
for k, v in self.headers_re.findall(open(path, 'rb').read())
])
f = open(path, 'rb')
if (self.headers.get('if-modified-since') == headers.get('Last-Modified', 'nom')) \
or (self.headers.get('if-none-match') == headers.get('ETag', 'nomatch')):
status = 304
else:
status = 200
headers.setdefault('Status', status)
self.send_response(int(headers['Status']))
headers.setdefault('Content-type', self.guess_type(path))
self.send_header("Content-type", headers['Content-type'])
self.send_header("Content-Length", str(os.stat(f.name)[6]))
for k, v in headers.items():
if k not in ('Status', 'Content-type'):
self.send_header(k, v)
self.end_headers()
return f
def send_head(self):
"""Send custom headers defined in test case
Example:
<!--
Header: Content-type: application/atom+xml
Header: X-Foo: bar
-->
"""
# Short-circuit the HTTP status test `test_redirect_to_304()`
if self.path == '/-/return-304.xml':
self.send_response(304)
self.send_header('Content-type', 'text/xml')
self.end_headers()
return feedparser._StringIO(u''.encode('utf-8'))
path = self.translate_path(self.path)
# the compression tests' filenames determine the header sent
if self.path.startswith('/tests/compression'):
if self.path.endswith('gz'):
headers = {'Content-Encoding': 'gzip'}
else:
headers = {'Content-Encoding': 'deflate'}
else:
headers = dict(
[(k.decode('utf-8'), v.decode('utf-8').strip())
for k, v in self.headers_re.findall(open(path, 'rb').read())])
f = open(path, 'rb')
if (self.headers.get('if-modified-since') == headers.get('Last-Modified', 'nom')) \
or (self.headers.get('if-none-match') == headers.get('ETag', 'nomatch')):
status = 304
else:
status = 200
headers.setdefault('Status', status)
self.send_response(int(headers['Status']))
headers.setdefault('Content-type', self.guess_type(path))
self.send_header("Content-type", headers['Content-type'])
self.send_header("Content-Length", str(os.stat(f.name)[6]))
for k, v in headers.items():
if k not in ('Status', 'Content-type'):
self.send_header(k, v)
self.end_headers()
return f
handlers = [handlers]
try:
f = _open_resource(url_file_stream_or_string, etag, modified, agent,
referrer, handlers)
data = f.read()
except Exception, e:
result['bozo'] = 1
result['bozo_exception'] = e
data = ''
f = None
# if feed is gzip-compressed, decompress it
if f and data and hasattr(f, 'headers'):
if gzip and f.headers.get('content-encoding', '') == 'gzip':
try:
data = gzip.GzipFile(fileobj=_StringIO(data)).read()
except Exception, e:
# Some feeds claim to be gzipped but they're not, so
# we get garbage. Ideally, we should re-request the
# feed without the 'Accept-encoding: gzip' header,
# but we don't.
result['bozo'] = 1
result['bozo_exception'] = e
data = ''
elif zlib and f.headers.get('content-encoding', '') == 'deflate':
try:
data = zlib.decompress(data, -zlib.MAX_WBITS)
except Exception, e:
result['bozo'] = 1
result['bozo_exception'] = e
data = ''
if type(handlers) == types.InstanceType:
handlers = [handlers]
try:
f = _open_resource(url_file_stream_or_string, etag, modified, agent, referrer, handlers)
data = f.read()
except Exception, e:
result['bozo'] = 1
result['bozo_exception'] = e
data = ''
f = None
# if feed is gzip-compressed, decompress it
if f and data and hasattr(f, 'headers'):
if gzip and f.headers.get('content-encoding', '') == 'gzip':
try:
data = gzip.GzipFile(fileobj=_StringIO(data)).read()
except Exception, e:
# Some feeds claim to be gzipped but they're not, so
# we get garbage. Ideally, we should re-request the
# feed without the 'Accept-encoding: gzip' header,
# but we don't.
result['bozo'] = 1
result['bozo_exception'] = e
data = ''
elif zlib and f.headers.get('content-encoding', '') == 'deflate':
try:
data = zlib.decompress(data, -zlib.MAX_WBITS)
except Exception, e:
result['bozo'] = 1
result['bozo_exception'] = e
data = ''
if len(xyz) == 0:
sys.exit(
"config file not setup. newsid wont be updated,setup new config before run"
)
df = pd.read_csv(
'../../PythonFlask/Extraction/Sources/RSS_ExtractionFormatV2.csv',
index_col=0)
# In[2]:
df2 = df[['Name', 'Rss', 'NTags', 'SCOPE', 'Type']]
# In[4]:
feedparser._open_resource = lambda *args, **kwargs: feedparser._StringIO(
requests.get(args[0], timeout=15).content)
feeds = []
posts = []
description = []
counter = 0
for url in df2['Rss']:
feed = feedparser.parse(url)
Name = df2['Name'][counter]
Ntags = df2['NTags'][counter]
Scope = df2['SCOPE'][counter]
Type = df2['Type'][counter]
counter = counter + 1
for post in feed.entries:
try:
