def run_feed(self, feed=None, download=False, ignoreFirst=False, force=False, readout=True):
""" Run the query for one URI and apply filters """
self.shutdown = False
def dup_title(title):
""" Check if this title was in this or other feeds
Return matching feed name
"""
title = title.lower()
for fd in self.jobs:
for lk in self.jobs[fd]:
item = self.jobs[fd][lk]
if item.get('status', ' ')[0] == 'D' and \
item.get('title', '').lower() == title:
return fd
return ''
if not feed:
return 'No such feed'
newlinks = []
new_downloads = []
# Preparations, get options
try:
feeds = config.get_rss()[feed]
except KeyError:
logging.error(T('Incorrect RSS feed description "%s"'), feed)
logging.info("Traceback: ", exc_info=True)
return T('Incorrect RSS feed description "%s"') % feed
uri = feeds.uri()
defCat = feeds.cat()
import sabnzbd.api
if not notdefault(defCat) or defCat not in sabnzbd.api.list_cats(default=False):
defCat = None
defPP = feeds.pp()
if not notdefault(defPP):
defPP = None
defScript = feeds.script()
if not notdefault(defScript):
defScript = None
defPrio = feeds.priority()
if not notdefault(defPrio):
defPrio = None
# Preparations, convert filters to regex's
regexes = []
reTypes = []
reCats = []
rePPs = []
rePrios = []
reScripts = []
reEnabled = []
for filter in feeds.filters():
reCat = filter[0]
if defCat in ('', '*'):
reCat = None
reCats.append(reCat)
rePPs.append(filter[1])
reScripts.append(filter[2])
reTypes.append(filter[3])
if filter[3] in ('<', '>', 'F'):
regexes.append(filter[4])
else:
regexes.append(convert_filter(filter[4]))
rePrios.append(filter[5])
reEnabled.append(filter[6] != '0')
regcount = len(regexes)
# Set first if this is the very first scan of this URI
first = (feed not in self.jobs) and ignoreFirst
# Add sabnzbd's custom User Agent
feedparser.USER_AGENT = 'SABnzbd+/%s' % sabnzbd.version.__version__
# Check for nzbs.org
if 'nzbs.org/' in uri and '&dl=1' not in uri:
uri += '&dl=1'
# Read the RSS feed
msg = None
entries = None
if readout:
uri = uri.replace(' ', '%20')
logging.debug("Running feedparser on %s", uri)
d = feedparser.parse(uri.replace('feed://', 'http://'))
logging.debug("Done parsing %s", uri)
if not d:
msg = T('Failed to retrieve RSS from %s: %s') % (uri, '?')
logging.info(msg)
return unicoder(msg)
status = d.get('status', 999)
if status in (401, 402, 403):
msg = T('Do not have valid authentication for feed %s') % feed
logging.info(msg)
return unicoder(msg)
if status >= 500 and status <= 599:
msg = T('Server side error (server code %s); could not get %s on %s') % (status, feed, uri)
logging.info(msg)
return unicoder(msg)
entries = d.get('entries')
if 'bozo_exception' in d and not entries:
msg = str(d['bozo_exception'])
if 'CERTIFICATE_VERIFY_FAILED' in msg:
msg = T('Server %s uses an untrusted HTTPS certificate') % get_urlbase(uri)
logging.error(msg)
else:
msg = T('Failed to retrieve RSS from %s: %s') % (uri, xml_name(msg))
logging.info(msg)
return unicoder(msg)
if not entries:
msg = T('RSS Feed %s was empty') % uri
logging.info(msg)
if feed not in self.jobs:
self.jobs[feed] = {}
jobs = self.jobs[feed]
if readout:
if not entries:
return unicoder(msg)
else:
entries = jobs.keys()
# Sort in the order the jobs came from the feed
entries.sort(lambda x, y: jobs[x].get('order', 0) - jobs[y].get('order', 0))
order = 0
# Filter out valid new links
for entry in entries:
if self.shutdown:
return
if readout:
try:
link, category, size = _get_link(uri, entry)
except (AttributeError, IndexError):
link = None
category = u''
size = 0L
logging.info(T('Incompatible feed') + ' ' + uri)
logging.info("Traceback: ", exc_info=True)
return T('Incompatible feed')
title = entry.title
else:
link = entry
category = jobs[link].get('orgcat', '')
if category in ('', '*'):
category = None
title = jobs[link].get('title', '')
size = jobs[link].get('size', 0L)
if link:
# Make sure spaces are quoted in the URL
link = link.strip().replace(' ', '%20')
newlinks.append(link)
if link in jobs:
jobstat = jobs[link].get('status', ' ')[0]
else:
jobstat = 'N'
if jobstat in 'NGB' or (jobstat == 'X' and readout):
# Match this title against all filters
logging.debug('Trying title %s', title)
result = False
myCat = defCat
myPP = defPP
myScript = defScript
myPrio = defPrio
n = 0
if 'F' in reTypes:
season, episode = sabnzbd.newsunpack.analyse_show(title)[1:3]
season = int_conv(season)
episode = int_conv(episode)
else:
season = episode = 0
# Match against all filters until an positive or negative match
logging.debug('Size %s for %s', size, title)
for n in xrange(regcount):
if reEnabled[n]:
if category and reTypes[n] == 'C':
found = re.search(regexes[n], category)
if not found:
logging.debug("Filter rejected on rule %d", n)
result = False
break
elif reTypes[n] == '<' and size and from_units(regexes[n]) < size:
# "Size at most" : too large
logging.debug('Filter rejected on rule %d', n)
result = False
break
elif reTypes[n] == '>' and size and from_units(regexes[n]) > size:
# "Size at least" : too small
logging.debug('Filter rejected on rule %d', n)
result = False
break
elif reTypes[n] == 'F' and not ep_match(season, episode, regexes[n]):
# "Starting from SxxEyy", too early episode
logging.debug('Filter requirement match on rule %d', n)
result = False
break
else:
if regexes[n]:
found = re.search(regexes[n], title)
else:
found = False
if reTypes[n] == 'M' and not found:
logging.debug("Filter rejected on rule %d", n)
result = False
break
if found and reTypes[n] == 'A':
logging.debug("Filter matched on rule %d", n)
result = True
break
if found and reTypes[n] == 'R':
logging.debug("Filter rejected on rule %d", n)
result = False
break
if len(reCats):
if notdefault(reCats[n]):
myCat = reCats[n]
elif category and not defCat:
myCat = cat_convert(category)
if myCat:
myCat, catPP, catScript, catPrio = cat_to_opts(myCat)
else:
myCat = catPP = catScript = catPrio = None
if notdefault(rePPs[n]):
myPP = rePPs[n]
elif not (reCats[n] or category):
myPP = catPP
if notdefault(reScripts[n]):
myScript = reScripts[n]
elif not (notdefault(reCats[n]) or category):
myScript = catScript
if rePrios[n] not in (str(DEFAULT_PRIORITY), ''):
myPrio = rePrios[n]
elif not ((rePrios[n] != str(DEFAULT_PRIORITY)) or category):
myPrio = catPrio
if cfg.no_dupes() and dup_title(title):
if cfg.no_dupes() == 1:
logging.info("Ignoring duplicate job %s", title)
continue
else:
myPrio = DUP_PRIORITY
act = download and not first
if link in jobs:
act = act and not jobs[link].get('status', '').endswith('*')
act = act or force
star = first or jobs[link].get('status', '').endswith('*')
else:
star = first
if result:
_HandleLink(jobs, link, title, size, 'G', category, myCat, myPP, myScript,
act, star, order, priority=myPrio, rule=str(n))
if act:
new_downloads.append(title)
else:
_HandleLink(jobs, link, title, size, 'B', category, myCat, myPP, myScript,
False, star, order, priority=myPrio, rule=str(n))
order += 1
# Send email if wanted and not "forced"
if new_downloads and cfg.email_rss() and not force:
emailer.rss_mail(feed, new_downloads)
remove_obsolete(jobs, newlinks)
return ''
def run_feed(self, feed=None, download=False, ignoreFirst=False, force=False, readout=True):
""" Run the query for one URI and apply filters """
self.shutdown = False
if not feed:
return 'No such feed'
newlinks = []
new_downloads = []
# Preparations, get options
try:
feeds = config.get_rss()[feed]
except KeyError:
logging.error(T('Incorrect RSS feed description "%s"'), feed)
logging.info("Traceback: ", exc_info=True)
return T('Incorrect RSS feed description "%s"') % feed
uris = feeds.uri()
defCat = feeds.cat()
import sabnzbd.api
if not notdefault(defCat) or defCat not in sabnzbd.api.list_cats(default=False):
defCat = None
defPP = feeds.pp()
if not notdefault(defPP):
defPP = None
defScript = feeds.script()
if not notdefault(defScript):
defScript = None
defPrio = feeds.priority()
if not notdefault(defPrio):
defPrio = None
# Preparations, convert filters to regex's
regexes = []
reTypes = []
reCats = []
rePPs = []
rePrios = []
reScripts = []
reEnabled = []
for filter in feeds.filters():
reCat = filter[0]
if defCat in ('', '*'):
reCat = None
reCats.append(reCat)
rePPs.append(filter[1])
reScripts.append(filter[2])
reTypes.append(filter[3])
if filter[3] in ('<', '>', 'F', 'S'):
regexes.append(filter[4])
else:
regexes.append(convert_filter(filter[4]))
rePrios.append(filter[5])
reEnabled.append(filter[6] != '0')
regcount = len(regexes)
# Set first if this is the very first scan of this URI
first = (feed not in self.jobs) and ignoreFirst
# Add sabnzbd's custom User Agent
feedparser.USER_AGENT = 'SABnzbd+/%s' % sabnzbd.version.__version__
# Read the RSS feed
msg = None
entries = None
if readout:
all_entries = []
for uri in uris:
uri = uri.replace(' ', '%20')
logging.debug("Running feedparser on %s", uri)
feed_parsed = feedparser.parse(uri.replace('feed://', 'http://'))
logging.debug("Done parsing %s", uri)
if not feed_parsed:
msg = T('Failed to retrieve RSS from %s: %s') % (uri, '?')
logging.info(msg)
status = feed_parsed.get('status', 999)
if status in (401, 402, 403):
msg = T('Do not have valid authentication for feed %s') % feed
logging.info(msg)
if status >= 500 and status <= 599:
msg = T('Server side error (server code %s); could not get %s on %s') % (status, feed, uri)
logging.info(msg)
entries = feed_parsed.get('entries')
if 'bozo_exception' in feed_parsed and not entries:
msg = str(feed_parsed['bozo_exception'])
if 'CERTIFICATE_VERIFY_FAILED' in msg:
msg = T('Server %s uses an untrusted HTTPS certificate') % get_urlbase(uri)
msg += ' - https://sabnzbd.org/certificate-errors'
logging.error(msg)
else:
msg = T('Failed to retrieve RSS from %s: %s') % (uri, xml_name(msg))
logging.info(msg)
if not entries:
msg = T('RSS Feed %s was empty') % uri
logging.info(msg)
all_entries.extend(entries)
entries = all_entries
if feed not in self.jobs:
self.jobs[feed] = {}
jobs = self.jobs[feed]
if readout:
if not entries:
return unicoder(msg)
else:
entries = jobs.keys()
# Sort in the order the jobs came from the feed
entries.sort(lambda x, y: jobs[x].get('order', 0) - jobs[y].get('order', 0))
order = 0
# Filter out valid new links
for entry in entries:
if self.shutdown:
return
if readout:
try:
link, category, size, age, season, episode = _get_link(uri, entry)
except (AttributeError, IndexError):
link = None
category = u''
size = 0L
age = None
logging.info(T('Incompatible feed') + ' ' + uri)
logging.info("Traceback: ", exc_info=True)
return T('Incompatible feed')
title = entry.title
# If there's multiple feeds, remove the duplicates based on title and size
if len(uris) > 1:
skip_job = False
for job_link, job in jobs.items():
# Allow 5% size deviation because indexers might have small differences for same release
if job.get('title') == title and link != job_link and (job.get('size')*0.95) < size < (job.get('size')*1.05):
logging.info("Ignoring job %s from other feed", title)
skip_job = True
break
if skip_job:
continue
else:
link = entry
category = jobs[link].get('orgcat', '')
if category in ('', '*'):
category = None
title = jobs[link].get('title', '')
size = jobs[link].get('size', 0L)
age = jobs[link].get('age')
season = jobs[link].get('season', 0)
episode = jobs[link].get('episode', 0)
if link:
# Make sure spaces are quoted in the URL
link = link.strip().replace(' ', '%20')
newlinks.append(link)
if link in jobs:
jobstat = jobs[link].get('status', ' ')[0]
else:
jobstat = 'N'
if jobstat in 'NGB' or (jobstat == 'X' and readout):
# Match this title against all filters
logging.debug('Trying title %s', title)
result = False
myCat = defCat
myPP = defPP
myScript = defScript
myPrio = defPrio
n = 0
if ('F' in reTypes or 'S' in reTypes) and (not season or not episode):
season, episode = sabnzbd.newsunpack.analyse_show(title)[1:3]
season = int_conv(season)
episode = int_conv(episode)
# Match against all filters until an positive or negative match
logging.debug('Size %s for %s', size, title)
for n in xrange(regcount):
if reEnabled[n]:
if category and reTypes[n] == 'C':
found = re.search(regexes[n], category)
if not found:
logging.debug("Filter rejected on rule %d", n)
result = False
break
elif reTypes[n] == '<' and size and from_units(regexes[n]) < size:
# "Size at most" : too large
logging.debug('Filter rejected on rule %d', n)
result = False
break
elif reTypes[n] == '>' and size and from_units(regexes[n]) > size:
# "Size at least" : too small
logging.debug('Filter rejected on rule %d', n)
result = False
break
elif reTypes[n] == 'F' and not ep_match(season, episode, regexes[n]):
# "Starting from SxxEyy", too early episode
logging.debug('Filter requirement match on rule %d', n)
result = False
break
elif reTypes[n] == 'S' and season and episode and ep_match(season, episode, regexes[n], title):
logging.debug('Filter matched on rule %d', n)
result = True
break
else:
if regexes[n]:
found = re.search(regexes[n], title)
else:
found = False
if reTypes[n] == 'M' and not found:
logging.debug("Filter rejected on rule %d", n)
result = False
break
if found and reTypes[n] == 'A':
logging.debug("Filter matched on rule %d", n)
result = True
break
if found and reTypes[n] == 'R':
logging.debug("Filter rejected on rule %d", n)
result = False
break
if len(reCats):
if not result and defCat:
# Apply Feed-category on non-matched items
myCat = defCat
elif result and notdefault(reCats[n]):
# Use the matched info
myCat = reCats[n]
elif category and not defCat:
# No result and no Feed-category
myCat = cat_convert(category)
if myCat:
myCat, catPP, catScript, catPrio = cat_to_opts(myCat)
else:
myCat = catPP = catScript = catPrio = None
if notdefault(rePPs[n]):
myPP = rePPs[n]
elif not (reCats[n] or category):
myPP = catPP
if notdefault(reScripts[n]):
myScript = reScripts[n]
elif not (notdefault(reCats[n]) or category):
myScript = catScript
if rePrios[n] not in (str(DEFAULT_PRIORITY), ''):
myPrio = rePrios[n]
elif not ((rePrios[n] != str(DEFAULT_PRIORITY)) or category):
myPrio = catPrio
if cfg.no_dupes() and self.check_duplicate(title):
if cfg.no_dupes() == 1:
# Dupe-detection: Discard
logging.info("Ignoring duplicate job %s", title)
continue
elif cfg.no_dupes() == 3:
# Dupe-detection: Fail
# We accept it so the Queue can send it to the History
logging.info("Found duplicate job %s", title)
else:
# Dupe-detection: Pause
myPrio = DUP_PRIORITY
act = download and not first
if link in jobs:
act = act and not jobs[link].get('status', '').endswith('*')
act = act or force
star = first or jobs[link].get('status', '').endswith('*')
else:
star = first
if result:
_HandleLink(jobs, link, title, size, age, season, episode, 'G', category, myCat, myPP, myScript,
act, star, order, priority=myPrio, rule=str(n))
if act:
new_downloads.append(title)
else:
_HandleLink(jobs, link, title, size, age, season, episode, 'B', category, myCat, myPP, myScript,
False, star, order, priority=myPrio, rule=str(n))
order += 1
# Send email if wanted and not "forced"
if new_downloads and cfg.email_rss() and not force:
emailer.rss_mail(feed, new_downloads)
remove_obsolete(jobs, newlinks)
return msg
def run_feed(self,
feed=None,
download=False,
ignoreFirst=False,
force=False,
readout=True):
""" Run the query for one URI and apply filters """
self.shutdown = False
def dup_title(title):
""" Check if this title was in this or other feeds
Return matching feed name
"""
title = title.lower()
for fd in self.jobs:
for lk in self.jobs[fd]:
item = self.jobs[fd][lk]
if item.get('status', ' ')[0] == 'D' and \
item.get('title', '').lower() == title:
return fd
return ''
if not feed:
return 'No such feed'
newlinks = []
new_downloads = []
# Preparations, get options
try:
feeds = config.get_rss()[feed]
except KeyError:
logging.error(Ta('Incorrect RSS feed description "%s"'), feed)
logging.info("Traceback: ", exc_info=True)
return T('Incorrect RSS feed description "%s"') % feed
uri = feeds.uri()
defCat = feeds.cat()
if not notdefault(defCat):
defCat = None
defPP = feeds.pp()
if not notdefault(defPP):
defPP = None
defScript = feeds.script()
if not notdefault(defScript):
defScript = None
defPrio = feeds.priority()
if not notdefault(defPrio):
defPrio = None
# Preparations, convert filters to regex's
regexes = []
reTypes = []
reCats = []
rePPs = []
rePrios = []
reScripts = []
reEnabled = []
for filter in feeds.filters():
reCat = filter[0]
if defCat in ('', '*'):
reCat = None
reCats.append(reCat)
rePPs.append(filter[1])
reScripts.append(filter[2])
reTypes.append(filter[3])
regexes.append(convert_filter(filter[4]))
rePrios.append(filter[5])
reEnabled.append(filter[6] != '0')
regcount = len(regexes)
# Set first if this is the very first scan of this URI
first = (feed not in self.jobs) and ignoreFirst
# Add sabnzbd's custom User Agent
feedparser.USER_AGENT = 'SABnzbd+/%s' % sabnzbd.version.__version__
# Check for nzbs.org
if 'nzbs.org/' in uri and not ('&dl=1' in uri):
uri += '&dl=1'
# Read the RSS feed
msg = None
entries = None
if readout:
uri = uri.replace(' ', '%20')
logging.debug("Running feedparser on %s", uri)
d = feedparser.parse(uri.replace('feed://', 'http://'))
logging.debug("Done parsing %s", uri)
if not d:
msg = Ta('Failed to retrieve RSS from %s: %s') % (uri, '?')
logging.info(msg)
return unicoder(msg)
status = d.get('status', 999)
if status in (401, 402, 403):
msg = Ta('Do not have valid authentication for feed %s') % feed
logging.info(msg)
return unicoder(msg)
entries = d.get('entries')
if 'bozo_exception' in d and not entries:
msg = Ta('Failed to retrieve RSS from %s: %s') % (
uri, xml_name(str(d['bozo_exception'])))
logging.info(msg)
return unicoder(msg)
if not entries:
msg = Ta('RSS Feed %s was empty') % uri
logging.info(msg)
if feed not in self.jobs:
self.jobs[feed] = {}
jobs = self.jobs[feed]
if readout:
if not entries:
return unicoder(msg)
else:
entries = jobs.keys()
order = 0
# Filter out valid new links
for entry in entries:
if self.shutdown: return
if readout:
try:
link, category = _get_link(uri, entry)
except (AttributeError, IndexError):
link = None
category = ''
logging.info(Ta('Incompatible feed') + ' ' + uri)
logging.info("Traceback: ", exc_info=True)
return T('Incompatible feed')
category = latin1(category)
# Make sure only latin-1 encodable characters occur
atitle = latin1(entry.title)
title = unicoder(atitle)
else:
link = entry
category = jobs[link].get('orgcat', '')
if category in ('', '*'):
category = None
atitle = latin1(jobs[link].get('title', ''))
title = unicoder(atitle)
if link:
# Make sure spaces are quoted in the URL
if 'nzbclub.com' in link:
link, path = os.path.split(link.strip())
link = '%s/%s' % (link, urllib.quote(path))
else:
link = link.strip().replace(' ', '%20')
newlinks.append(link)
if link in jobs:
jobstat = jobs[link].get('status', ' ')[0]
else:
jobstat = 'N'
if jobstat in 'NGB' or (jobstat == 'X' and readout):
# Match this title against all filters
logging.debug('Trying title %s', atitle)
result = False
myCat = defCat
myPP = defPP
myScript = defScript
myPrio = defPrio
n = 0
# Match against all filters until an postive or negative match
for n in xrange(regcount):
if reEnabled[n]:
if category and reTypes[n] == 'C':
found = re.search(regexes[n], category)
if not found:
logging.debug("Filter rejected on rule %d",
n)
result = False
break
else:
if regexes[n]:
found = re.search(regexes[n], title)
else:
found = False
if reTypes[n] == 'M' and not found:
logging.debug("Filter rejected on rule %d",
n)
result = False
break
if found and reTypes[n] == 'A':
logging.debug("Filter matched on rule %d",
n)
result = True
break
if found and reTypes[n] == 'R':
logging.debug("Filter rejected on rule %d",
n)
result = False
break
if len(reCats):
if notdefault(reCats[n]):
myCat = reCats[n]
elif category and not defCat:
myCat = cat_convert(category)
if myCat:
myCat, catPP, catScript, catPrio = cat_to_opts(
myCat)
else:
myCat = catPP = catScript = catPrio = None
if notdefault(rePPs[n]):
myPP = rePPs[n]
elif not (reCats[n] or category):
myPP = catPP
if notdefault(reScripts[n]):
myScript = reScripts[n]
elif not (notdefault(reCats[n]) or category):
myScript = catScript
if rePrios[n] not in (str(DEFAULT_PRIORITY), ''):
myPrio = rePrios[n]
elif not ((rePrios[n] != str(DEFAULT_PRIORITY))
or category):
myPrio = catPrio
if cfg.no_dupes() and dup_title(title):
if cfg.no_dupes() == 1:
logging.info("Ignoring duplicate job %s", atitle)
continue
else:
myPrio = DUP_PRIORITY
act = download and not first
if link in jobs:
act = act and not jobs[link].get('status',
'').endswith('*')
act = act or force
star = first or jobs[link].get('status',
'').endswith('*')
else:
star = first
if result:
_HandleLink(jobs,
link,
title,
'G',
category,
myCat,
myPP,
myScript,
act,
star,
order,
priority=myPrio,
rule=str(n))
if act:
new_downloads.append(title)
else:
_HandleLink(jobs,
link,
title,
'B',
category,
myCat,
myPP,
myScript,
False,
star,
order,
priority=myPrio,
rule=str(n))
order += 1
# Send email if wanted and not "forced"
if new_downloads and cfg.email_rss() and not force:
emailer.rss_mail(feed, new_downloads)
remove_obsolete(jobs, newlinks)
return ''
def run_feed(self, feed=None, download=False, ignoreFirst=False, force=False, readout=True):
""" Run the query for one URI and apply filters """
self.shutdown = False
def dup_title(title):
""" Check if this title was in this or other feeds
Return matching feed name
"""
title = title.lower()
for fd in self.jobs:
for lk in self.jobs[fd]:
item = self.jobs[fd][lk]
if item.get('status', ' ')[0] == 'D' and \
item.get('title', '').lower() == title:
return fd
return ''
if not feed:
return 'No such feed'
newlinks = []
new_downloads = []
# Preparations, get options
try:
feeds = config.get_rss()[feed]
except KeyError:
logging.error(Ta('Incorrect RSS feed description "%s"'), feed)
logging.info("Traceback: ", exc_info = True)
return T('Incorrect RSS feed description "%s"') % feed
uri = feeds.uri()
defCat = feeds.cat()
if not notdefault(defCat):
defCat = None
defPP = feeds.pp()
if not notdefault(defPP):
defPP = None
defScript = feeds.script()
if not notdefault(defScript):
defScript = None
defPrio = feeds.priority()
if not notdefault(defPrio):
defPrio = None
# Preparations, convert filters to regex's
regexes = []
reTypes = []
reCats = []
rePPs = []
rePrios = []
reScripts = []
reEnabled = []
for filter in feeds.filters():
reCat = filter[0]
if defCat in ('', '*'):
reCat = None
reCats.append(reCat)
rePPs.append(filter[1])
reScripts.append(filter[2])
reTypes.append(filter[3])
regexes.append(convert_filter(filter[4]))
rePrios.append(filter[5])
reEnabled.append(filter[6] != '0')
regcount = len(regexes)
# Set first if this is the very first scan of this URI
first = (feed not in self.jobs) and ignoreFirst
# Add sabnzbd's custom User Agent
feedparser.USER_AGENT = 'SABnzbd+/%s' % sabnzbd.version.__version__
# Check for nzbs.org
if 'nzbs.org/' in uri and not ('&dl=1' in uri):
uri += '&dl=1'
# Read the RSS feed
msg = None
entries = None
if readout:
uri = uri.replace(' ', '%20')
logging.debug("Running feedparser on %s", uri)
d = feedparser.parse(uri.replace('feed://', 'http://'))
logging.debug("Done parsing %s", uri)
if not d:
msg = Ta('Failed to retrieve RSS from %s: %s') % (uri, '?')
logging.info(msg)
return unicoder(msg)
status = d.get('status', 999)
if status in (401, 402, 403):
msg = Ta('Do not have valid authentication for feed %s') % feed
logging.info(msg)
return unicoder(msg)
entries = d.get('entries')
if 'bozo_exception' in d and not entries:
msg = Ta('Failed to retrieve RSS from %s: %s') % (uri, xml_name(str(d['bozo_exception'])))
logging.info(msg)
return unicoder(msg)
if not entries:
msg = Ta('RSS Feed %s was empty') % uri
logging.info(msg)
if feed not in self.jobs:
self.jobs[feed] = {}
jobs = self.jobs[feed]
if readout:
if not entries:
return unicoder(msg)
else:
entries = jobs.keys()
order = 0
# Filter out valid new links
for entry in entries:
if self.shutdown: return
if readout:
try:
link, category = _get_link(uri, entry)
except (AttributeError, IndexError):
link = None
category = ''
logging.info(Ta('Incompatible feed') + ' ' + uri)
logging.info("Traceback: ", exc_info = True)
return T('Incompatible feed')
category = latin1(category)
# Make sure only latin-1 encodable characters occur
atitle = latin1(entry.title)
title = unicoder(atitle)
else:
link = entry
category = jobs[link].get('orgcat', '')
if category in ('', '*'):
category = None
atitle = latin1(jobs[link].get('title', ''))
title = unicoder(atitle)
if link:
# Make sure spaces are quoted in the URL
if 'nzbclub.com' in link:
link, path = os.path.split(link.strip())
link = '%s/%s' % (link, urllib.quote(path))
else:
link = link.strip().replace(' ','%20')
newlinks.append(link)
if link in jobs:
jobstat = jobs[link].get('status', ' ')[0]
else:
jobstat = 'N'
if jobstat in 'NGB' or (jobstat == 'X' and readout):
# Match this title against all filters
logging.debug('Trying title %s', atitle)
result = False
myCat = defCat
myPP = defPP
myScript = defScript
myPrio = defPrio
n = 0
# Match against all filters until an postive or negative match
for n in xrange(regcount):
if reEnabled[n]:
if category and reTypes[n] == 'C':
found = re.search(regexes[n], category)
if not found:
logging.debug("Filter rejected on rule %d", n)
result = False
break
else:
if regexes[n]:
found = re.search(regexes[n], title)
else:
found = False
if reTypes[n] == 'M' and not found:
logging.debug("Filter rejected on rule %d", n)
result = False
break
if found and reTypes[n] == 'A':
logging.debug("Filter matched on rule %d", n)
result = True
break
if found and reTypes[n] == 'R':
logging.debug("Filter rejected on rule %d", n)
result = False
break
if len(reCats):
if notdefault(reCats[n]):
myCat = reCats[n]
elif category and not defCat:
myCat = cat_convert(category)
if myCat:
myCat, catPP, catScript, catPrio = cat_to_opts(myCat)
else:
myCat = catPP = catScript = catPrio = None
if notdefault(rePPs[n]):
myPP = rePPs[n]
elif not (reCats[n] or category):
myPP = catPP
if notdefault(reScripts[n]):
myScript = reScripts[n]
elif not (notdefault(reCats[n]) or category):
myScript = catScript
if rePrios[n] not in (str(DEFAULT_PRIORITY), ''):
myPrio = rePrios[n]
elif not ((rePrios[n] != str(DEFAULT_PRIORITY)) or category):
myPrio = catPrio
if cfg.no_dupes() and dup_title(title):
if cfg.no_dupes() == 1:
logging.info("Ignoring duplicate job %s", atitle)
continue
else:
myPrio = DUP_PRIORITY
act = download and not first
if link in jobs:
act = act and not jobs[link].get('status', '').endswith('*')
act = act or force
star = first or jobs[link].get('status', '').endswith('*')
else:
star = first
if result:
_HandleLink(jobs, link, title, 'G', category, myCat, myPP, myScript,
act, star, order, priority=myPrio, rule=str(n))
if act:
new_downloads.append(title)
else:
_HandleLink(jobs, link, title, 'B', category, myCat, myPP, myScript,
False, star, order, priority=myPrio, rule=str(n))
order += 1
# Send email if wanted and not "forced"
if new_downloads and cfg.email_rss() and not force:
emailer.rss_mail(feed, new_downloads)
remove_obsolete(jobs, newlinks)
return ''
def run_feed(self, feed=None, download=False, ignoreFirst=False, force=False, readout=True):
""" Run the query for one URI and apply filters """
self.shutdown = False
if not feed:
return 'No such feed'
newlinks = []
new_downloads = []
# Preparations, get options
try:
feeds = config.get_rss()[feed]
except KeyError:
logging.error(T('Incorrect RSS feed description "%s"'), feed)
logging.info("Traceback: ", exc_info=True)
return T('Incorrect RSS feed description "%s"') % feed
uris = feeds.uri()
defCat = feeds.cat()
import sabnzbd.api
if not notdefault(defCat) or defCat not in sabnzbd.api.list_cats(default=False):
defCat = None
defPP = feeds.pp()
if not notdefault(defPP):
defPP = None
defScript = feeds.script()
if not notdefault(defScript):
defScript = None
defPrio = feeds.priority()
if not notdefault(defPrio):
defPrio = None
# Preparations, convert filters to regex's
regexes = []
reTypes = []
reCats = []
rePPs = []
rePrios = []
reScripts = []
reEnabled = []
for filter in feeds.filters():
reCat = filter[0]
if defCat in ('', '*'):
reCat = None
reCats.append(reCat)
rePPs.append(filter[1])
reScripts.append(filter[2])
reTypes.append(filter[3])
if filter[3] in ('<', '>', 'F', 'S'):
regexes.append(filter[4])
else:
regexes.append(convert_filter(filter[4]))
rePrios.append(filter[5])
reEnabled.append(filter[6] != '0')
regcount = len(regexes)
# Set first if this is the very first scan of this URI
first = (feed not in self.jobs) and ignoreFirst
# Add sabnzbd's custom User Agent
feedparser.USER_AGENT = 'SABnzbd+/%s' % sabnzbd.version.__version__
# Read the RSS feed
msg = None
entries = None
if readout:
all_entries = []
for uri in uris:
uri = uri.replace(' ', '%20')
logging.debug("Running feedparser on %s", uri)
feed_parsed = feedparser.parse(uri.replace('feed://', 'http://'))
logging.debug("Done parsing %s", uri)
if not feed_parsed:
msg = T('Failed to retrieve RSS from %s: %s') % (uri, '?')
logging.info(msg)
status = feed_parsed.get('status', 999)
if status in (401, 402, 403):
msg = T('Do not have valid authentication for feed %s') % feed
logging.info(msg)
if 500 <= status <= 599:
msg = T('Server side error (server code %s); could not get %s on %s') % (status, feed, uri)
logging.info(msg)
entries = feed_parsed.get('entries')
if 'bozo_exception' in feed_parsed and not entries:
msg = str(feed_parsed['bozo_exception'])
if 'CERTIFICATE_VERIFY_FAILED' in msg:
msg = T('Server %s uses an untrusted HTTPS certificate') % get_urlbase(uri)
msg += ' - https://sabnzbd.org/certificate-errors'
logging.error(msg)
else:
msg = T('Failed to retrieve RSS from %s: %s') % (uri, xml_name(msg))
logging.info(msg)
if not entries:
msg = T('RSS Feed %s was empty') % uri
logging.info(msg)
all_entries.extend(entries)
entries = all_entries
# In case of a new feed
if feed not in self.jobs:
self.jobs[feed] = {}
jobs = self.jobs[feed]
# Error in readout or now new readout
if readout:
if not entries:
return unicoder(msg)
else:
entries = jobs.keys()
# Filter out valid new links
for entry in entries:
if self.shutdown:
return
if readout:
try:
link, category, size, age, season, episode = _get_link(entry)
except (AttributeError, IndexError):
logging.info(T('Incompatible feed') + ' ' + uri)
logging.info("Traceback: ", exc_info=True)
return T('Incompatible feed')
title = entry.title
# If there's multiple feeds, remove the duplicates based on title and size
if len(uris) > 1:
skip_job = False
for job_link, job in jobs.items():
# Allow 5% size deviation because indexers might have small differences for same release
if job.get('title') == title and link != job_link and (job.get('size')*0.95) < size < (job.get('size')*1.05):
logging.info("Ignoring job %s from other feed", title)
skip_job = True
break
if skip_job:
continue
else:
link = entry
category = jobs[link].get('orgcat', '')
if category in ('', '*'):
category = None
title = jobs[link].get('title', '')
size = jobs[link].get('size', 0L)
age = jobs[link].get('age')
season = jobs[link].get('season', 0)
episode = jobs[link].get('episode', 0)
if link:
# Make sure spaces are quoted in the URL
link = link.strip().replace(' ', '%20')
newlinks.append(link)
if link in jobs:
jobstat = jobs[link].get('status', ' ')[0]
else:
jobstat = 'N'
if jobstat in 'NGB' or (jobstat == 'X' and readout):
# Match this title against all filters
logging.debug('Trying title %s', title)
result = False
myCat = defCat
myPP = defPP
myScript = defScript
myPrio = defPrio
n = 0
if ('F' in reTypes or 'S' in reTypes) and (not season or not episode):
season, episode = sabnzbd.newsunpack.analyse_show(title)[1:3]
# Match against all filters until an positive or negative match
logging.debug('Size %s', size)
for n in xrange(regcount):
if reEnabled[n]:
if category and reTypes[n] == 'C':
found = re.search(regexes[n], category)
if not found:
logging.debug("Filter rejected on rule %d", n)
result = False
break
elif reTypes[n] == '<' and size and from_units(regexes[n]) < size:
# "Size at most" : too large
logging.debug('Filter rejected on rule %d', n)
result = False
break
elif reTypes[n] == '>' and size and from_units(regexes[n]) > size:
# "Size at least" : too small
logging.debug('Filter rejected on rule %d', n)
result = False
break
elif reTypes[n] == 'F' and not ep_match(season, episode, regexes[n]):
# "Starting from SxxEyy", too early episode
logging.debug('Filter requirement match on rule %d', n)
result = False
break
elif reTypes[n] == 'S' and season and episode and ep_match(season, episode, regexes[n], title):
logging.debug('Filter matched on rule %d', n)
result = True
break
else:
if regexes[n]:
found = re.search(regexes[n], title)
else:
found = False
if reTypes[n] == 'M' and not found:
logging.debug("Filter rejected on rule %d", n)
result = False
break
if found and reTypes[n] == 'A':
logging.debug("Filter matched on rule %d", n)
result = True
break
if found and reTypes[n] == 'R':
logging.debug("Filter rejected on rule %d", n)
result = False
break
if len(reCats):
if not result and defCat:
# Apply Feed-category on non-matched items
myCat = defCat
elif result and notdefault(reCats[n]):
# Use the matched info
myCat = reCats[n]
elif category and not defCat:
# No result and no Feed-category
myCat = cat_convert(category)
if myCat:
myCat, catPP, catScript, catPrio = cat_to_opts(myCat)
else:
myCat = catPP = catScript = catPrio = None
if notdefault(rePPs[n]):
myPP = rePPs[n]
elif not (reCats[n] or category):
myPP = catPP
if notdefault(reScripts[n]):
myScript = reScripts[n]
elif not (notdefault(reCats[n]) or category):
myScript = catScript
if rePrios[n] not in (str(DEFAULT_PRIORITY), ''):
myPrio = rePrios[n]
elif not ((rePrios[n] != str(DEFAULT_PRIORITY)) or category):
myPrio = catPrio
if cfg.no_dupes() and self.check_duplicate(title):
if cfg.no_dupes() == 1:
# Dupe-detection: Discard
logging.info("Ignoring duplicate job %s", title)
continue
elif cfg.no_dupes() == 3:
# Dupe-detection: Fail
# We accept it so the Queue can send it to the History
logging.info("Found duplicate job %s", title)
else:
# Dupe-detection: Pause
myPrio = DUP_PRIORITY
act = download and not first
if link in jobs:
act = act and not jobs[link].get('status', '').endswith('*')
act = act or force
star = first or jobs[link].get('status', '').endswith('*')
else:
star = first
if result:
_HandleLink(jobs, feed, link, title, size, age, season, episode, 'G', category, myCat, myPP,
myScript, act, star, priority=myPrio, rule=str(n))
if act:
new_downloads.append(title)
else:
_HandleLink(jobs, feed, link, title, size, age, season, episode, 'B', category, myCat, myPP,
myScript, False, star, priority=myPrio, rule=str(n))
# Send email if wanted and not "forced"
if new_downloads and cfg.email_rss() and not force:
emailer.rss_mail(feed, new_downloads)
remove_obsolete(jobs, newlinks)
return msg