#coding=utf-8
#
from nntplib import NNTP
from time import strftime, time, localtime
day = 24 * 60 * 60 # Number of seconds in one day
yesterday = localtime(time() - day)
date = strftime('%y%m%d', yesterday)
hour = strftime('%H%M%S', yesterday)
servername = 'news.mixmin.net'
group = 'talk.euthanasia'
server = NNTP(servername)
ids = server.newnews(group, date, hour)[1]
for id in ids:
head = server.head(id)[3]
for line in head:
if line.lower().startswith('subject:'):
subject = line[9:]
break
body = server.body(id)[3]
print subject
print '-'*len(subject)
print '\n'.join(body)
server.quit()
def gmane(self):
try:
gmane = NNTP("news.gmane.org")
except:
return self.gmane
gmane.group(self.group)
return gmane
def download_group(name):
if not os.path.exists(name):
os.mkdir(name)
s = NNTP('news.gmane.org')
resp, count, first, last, name = s.group(name)
print 'Group', name, 'has', count, 'articles, range', first, 'to', last
resp, subs = s.xhdr('subject', first + '-' + last)
for id, sub in subs:
print id
with open(os.path.join(name, str(id)), 'wb') as fp:
pprint.pprint(s.article(id), stream=fp)
def add_new_jobs(group_name):
db = Connection().usenet
max_h = db.control.find({"group": group_name}).sort('end', DESCENDING).limit(1)[0]['end'] + 1
if not max_h: max_h = 0
news = NNTP('eu.news.astraweb.com', user='******', password='******')
group = dict_group(news, group_name)
news.quit()
i = max(group['first'], max_h)
if max_h > group['last']: return
while(i+100000 < group['last']):
db.control.insert({'init': i, 'end': i+99999, 'done':False, "group": group_name})
i += 100000
db.control.insert({'init': i, 'end': group['last'], 'done':False, "group": group_name})
def __init__(self, group, server):
self.conn = NNTP(server)
resp, count, first, last, name = self.conn.group(group)
self.group = group
self.server = server
self.first = int(first)
self.last = int(last)
def getItems(self):
start = localtime(time()-self.window*day)
date = strftime('%y%m%d',start)
hour = strftime('%H%M%S',start)
server = NNTP(self.servername)
ids = server.newnews(self.group,date,hour)[1]
for id in ids:
lines = server.article(id)[3]
message = message_from_string('\n'.join(lines))
title = memssage['subject']
body = message.get_payload()
if message.is_multipart():
body = body[0]
yield NewsItem(title,body)
server.quit()
class NewsGrep:
def __init__(self,server,username,password):
self.server = NNTP(server, 119,username,password)
def __del__(self):
pass
def __str__(self):
pass
def list(self):
resp, groups = self.server.list()
for group, last, first, flag in groups:
print group
def ls(self,group_name):
resp, count, first, last, name = self.server.group(group_name)
print 'Group', name, 'has', count, 'articles, range', first, 'to', last
resp, subs = self.server.xhdr('subject', first + '-' + last)
for id, sub in subs[-10:]:
print id, sub
def main():
tree = {}
# Check that the output directory exists
checkopdir(pagedir)
try:
print('Connecting to %s...' % newshost)
if sys.version[0] == '0':
s = NNTP.init(newshost)
else:
s = NNTP(newshost)
connected = True
except (nntplib.error_temp, nntplib.error_perm) as x:
print('Error connecting to host:', x)
print('I\'ll try to use just the local list.')
connected = False
# If -a is specified, read the full list of groups from server
if connected and len(sys.argv) > 1 and sys.argv[1] == '-a':
groups = getallgroups(s)
# Otherwise just read the local file and then add
# groups created since local file last modified.
else:
(tree, treedate) = readlocallist(treefile)
if connected:
groups = getnewgroups(s, treedate)
if connected:
addtotree(tree, groups)
writelocallist(treefile,tree)
# Read group descriptions
readdesc(descfile)
print('Creating pages...')
createpage(rootpage, tree, '')
print('Done')
class NewsGrep:
def __init__(self, server, username, password):
self.server = NNTP(server, 119, username, password)
def __del__(self):
pass
def __str__(self):
pass
def list(self):
resp, groups = self.server.list()
for group, last, first, flag in groups:
print group
def ls(self, group_name):
resp, count, first, last, name = self.server.group(group_name)
print 'Group', name, 'has', count, 'articles, range', first, 'to', last
resp, subs = self.server.xhdr('subject', first + '-' + last)
for id, sub in subs[-10:]:
print id, sub
def main():
s = NNTP(settings.nntp_hostname, settings.nntp_port)
resp, groups = s.list()
# check all of the groups, just in case
for group_name, last, first, flag in groups:
resp, count, first, last, name = s.group(group_name)
print "\nGroup", group_name, 'has', count, 'articles, range', first, 'to', last
resp, subs = s.xhdr('subject', first + '-' + last)
for id, sub in subs[-10:]:
print id, sub
s.quit()
def get_items(self): #新闻生成器
server = NNTP(self.servername)
resp, count, first, last, name = server.group(self.group) #新闻组信息列表
start = last - self.howmany + 1
resp, overviews = server.over((start, last))
for id, over in overviews:
title = decode_header(over['subject'])
resp, info = server.body(id)
body = '\n'.join(line.decode() for line in info.lines) + '\n\n'
yield NewsItem(title, body)
server.quit()
def get_items(self):
server = NNTP(self.servername)
resp, count, first, last, name = server.group(self.group)
start = last - self.howmany + 1
resp, overviews = server.over((start, last))
for id, over in overviews:
title = decode_header(over["subject"])
resp, info = server.body(id)
body = "\n".join(line.decode("latin")
for line in info.lines) + "\n\n"
yield NewsItem(title, body)
server.quit()
def start(self):
port = self.port
if not port:
port = NNTP_PORT
self.nntp = NNTP(self.server, port, self.user, self.pw,
readermode=1)
# only look for messages that appear after we start. Usenet is big.
if not self.last: # only do this the first time
for g in self.groups:
resp, count, first, last, name = self.nntp.group(g)
self.last[g] = int(last)
if self.debug: print "last[%s]: %d" % (g, self.last[g])
self.timeout = gtk.timeout_add(self.pollInterval*1000,
self.doTimeout)
def get_items(self):
server = NNTP(self.servername)
_, count, first, last, name = server.group(self.group)
start = last - self.how_many + 1
_, overviews = server.over((start, last))
for ID, over in overviews:
title = decode_header(over['subject'])
_, info = server.body(ID)
body = '\n'.join(line.decode('latin') for line in info.lines)
yield NewsItem(title, body)
server.quit()
def whatsnew(date_last_check, group="*", **server):
fill = dict()
if "user" in server: fill["user"] = server["user"]
if "password" in server: fill["password"] = server["password"]
if "host" in server: fill["host"] = server["host"]
if "port" in server: fill["port"] = server["port"]
with NNTP(**fill) as srv:
response, groups = srv.newgroups(date_last_check)
for g in groups:
yield g
response, articles = srv.newnews(group, date_last_check)
for msg_id in articles:
response, info = srv.article(msg_id)
yield email.message_from_bytes(b"\r\n".join(info.lines))
def get_items(self):
server = NNTP(self.servername)
#服务器响应、新闻组包含的消息数、第一条和最后一条消息编号、新闻组名称
resp, count, first, last, name = server.group(self.group)
#确定要获取的文章编号区间的起始位置
start = last - self.howmany + 1
resp, overviews = server.over((start, last))
for id, over in overviews:
title = decode_header(over['subject'])
resp, info = server.body(id)
body = '\n'.join(line.decode('latin')
for line in info.lines) + '\n\n'
yield NewsItem(title, body)
server.quit()
def main():
s = NNTP(settings.nntp_hostname, settings.nntp_port)
resp, groups = s.list()
# check all of the groups, just in case
for group_name, last, first, flag in groups:
resp, count, first, last, name = s.group(group_name)
print "\nGroup", group_name, 'has', count, 'articles, range', first, 'to', last
resp, subs = s.xhdr('subject', first + '-' + last)
for id, sub in subs[-10:]:
print id, sub
s.quit()
def main():
tree = {}
# Check that the output directory exists
checkopdir(pagedir)
try:
print 'Connecting to %s...' % newshost
if sys.version[0] == '0':
s = NNTP.init(newshost)
else:
s = NNTP(newshost)
connected = True
except (nntplib.error_temp, nntplib.error_perm), x:
print 'Error connecting to host:', x
print 'I\'ll try to use just the local list.'
connected = False
def get_items(self):
server = NNTP(self.servername)
resp, count, first, last, name = server.group(self.group)
start = last - self.howmany + 1
resp, overviews = server.over((start, last))
for id, over in overviews:
title = decode_header(over['subject'])
resp, info = server.body(id)
body = '\n'.join(line.decode('latin')
for line in info.lines) + '\n\n'
yield NewsItem(title, body)
server.quit()
def getItems(self):
server = NNTP(self.servername)
(resp, count, first, last, name) = server.group(self.group)
(resp, subs) = server.xhdr('subject', (str(first) + '-' + str(last)))
for subject in subs[-10:]:
title = subject[1]
(reply, (num, id, list)) = server.body(subject[0])
# list是一个列表，但是是bytes编码的，需要把每一个元素都解码成string
body = []
#print(list)
for l in list:
body.append(l.decode('gbk')) # 注意，这里用utf-8解码会出现解码错误
#print(body)
body = ''.join(body)
yield NewsItem(title, body)
server.quit()
def __init__(self, article_cache_size=300, cache_file=None):
"""Initialize local variables"""
# Connect to news.gmane.org
self.nntp = NNTP('news.gmane.org')
# Setting the group returns information, which right now we ignore
self.nntp.group('gmane.comp.internationalization.dansk')
# Keep a local cache in an OrderedDict, transferred across session
# in a pickled version in a file
self.article_cache_size = article_cache_size
self.cache_file = cache_file
if cache_file and path.isfile(cache_file):
with open(cache_file, 'rb') as file_:
self.article_cache = pickle.load(file_)
logging.info('Loaded %i items from file cache',
len(self.article_cache))
else:
self.article_cache = OrderedDict()
def getItems(self):
server = NNTP(self.servername)
(resp, count, frist, last, name) = server.group(self.group)
(resp, subs) = server.xhdr('subject', (str(frist) + '-' + (last)))
for subject in subs[-10:]:
title = subject[1]
(reply, num, id, list) = server.body(subject[0])
body = ''.join(list)
#print(num) #186919
#print(title) #Re: Find out which module a class came from
#print(''.join(list))#prano wrote:> But for merely ordinary obfuscation caused by poor...
yield NewsItem(title, body)
server.quit()
def main():
global desc
tree={}
# Check that the output directory exists
checkopdir(pagedir)
try:
print('Connecting to '+newshost+'...')
if sys.version[0] == '0':
s = NNTP.init(newshost)
else:
s = NNTP(newshost)
connected = 1
except (nntplib.error_temp, nntplib.error_perm) as x:
print('Error connecting to host:', x)
print('I\'ll try to use just the local list.')
connected = 0
# If -a is specified, read the full list of groups from server
if connected and len(sys.argv) > 1 and sys.argv[1] == '-a':
groups = getallgroups(s)
# Otherwise just read the local file and then add
# groups created since local file last modified.
else:
(tree, treedate) = readlocallist(treefile)
if connected:
groups = getnewgroups(s, treedate)
if connected:
addtotree(tree, groups)
writelocallist(treefile,tree)
# Read group descriptions
readdesc(descfile)
print('Creating pages...')
createpage(rootpage, tree, '')
print('Done')
def __init__(self):
try:
self.news = NNTP(NEWS_SERVER, NNTP_PORT, NNTP_USERNAME,
NNTP_PASSWORD)
except NNTPTemporaryError as e:
raise SpotError('NNTP', e)
except socket.error as e:
raise SpotError('Connection', e)
self.conn = sqlite3.connect(NEWS_SERVER + '.db')
self.conn.row_factory = sqlite3.Row
self.cur = self.conn.cursor()
self.cur.executescript('''\
PRAGMA synchronous = OFF;
PRAGMA journal_mode = MEMORY;
PRAGMA temp_store = MEMORY;
PRAGMA count_changes = OFF;
''')
def get_items(self):
for servername in KNOWN_NNTP_SERVERS:
try:
server = NNTP(servername)
resp, count, first, last, name = server.group(self.group)
start = last - self.howmany + 1
resp, overviews = server.over((start, last))
for id, over in overviews:
title = decode_header(over['subject'])
resp, info = server.body(id)
body = '\n'.join(
line.decode('latin1') for line in info.lines) + '\n\n'
yield NewsItem(title, body, "NNTP NewsGroup " + self.group)
server.quit()
break
except:
continue
return []
def getItems(self):
# yesterday = localtime(time()-self.window*day)
# date = strftime('%y%m%d',yesterday)
# time = strftime('%H%M%S',yesterday)
# create a nntp server
s = NNTP(self.servername)
resp,count,first,last,name = s.group(self.groupname)
resp,overviews = s.over((last-1,last))
for num,over in overviews:
title = over.get('subject')
resp,body = s.body(num)
# create a generator to iterate news
if title and body:
yield NewsItem(title,body)
s.quit()
def getItems(self):
start = localtime(time() - self.window * day)
date = strftime('%y%m%d', start)
hour = strftime('%H%M%S', start)
server = NNTP(self.servername)
ids = server.newnews(self.group, date, hour)[1]
for id in ids:
lines = server.article(id)[3]
message = message_from_string('\n'.join(lines))
title = message['subject']
body = message.get_payload()
if message.is_multipart():
body = body[0]
yield NewsItem(title, body)
server.quit()
def connect(self):
address = net.format_addr((self.hostname, self.port))
self.log.write("Connecting to {}\n".format(address))
if self.port is None:
port = ()
else:
port = (self.port,)
self.connect_time = time.monotonic()
self.nntp = NNTP(self.hostname, *port, **self.timeout)
with ExitStack() as cleanup:
cleanup.push(self)
if self.debuglevel is not None:
self.nntp.set_debuglevel(self.debuglevel)
self.log.write("{}\n".format(self.nntp.getwelcome()))
if self.username is not None:
self.log.write("Logging in as {}\n".format(self.username))
with self.handle_abort():
self.nntp.login(self.username, self.password)
self.log.write("Logged in\n")
cleanup.pop_all()
def fetch(self):
"""
Fetches all the messages for a given news group uri and return Fetched staus depending
on the success and faliure of the task
"""
try:
#eg. self.currenturi = nntp://msnews.microsoft.com/microsoft.public.exchange.setup
#nntp_server = 'msnews.microsoft.com'
#nntp_group = 'microsoft.public.exchange.setup'
self.genre = 'review'
try:
nntp_server = urlparse(self.currenturi)[1]
except:
log.exception(self.log_msg("Exception occured while connecting to NNTP server %s"%self.currenturi))
return False
nntp_group = urlparse(self.currenturi)[2][1:]
self.server = NNTP(nntp_server)
try:
self.__updateParentSessionInfo()
resp, count, first, last, name = self.server.group(nntp_group)
last_id = int(last)
first_id = self.__getMaxCrawledId(last_id)+1
log.debug("first_id is %d:"%first_id)
log.debug("last_id is %d:"%last_id)
if last_id >= first_id:
resp, items = self.server.xover(str(first_id), str(last_id))
log.debug(self.log_msg("length of items:%s"%str(len(items))))
for self.id, self.subject, self.author, self.date, self.message_id,\
self.references, size, lines in items:
self.__getMessages(self.task.instance_data['uri'])
self.server.quit()
return True
except:
log.exception(self.log_msg("Exception occured in fetch()"))
self.server.quit()
return False
except Exception,e:
log.exception(self.log_msg("Exception occured in fetch()"))
return False
def getItems(self):
server = NNTP(self.servername)
_, count, first, last, name = server.group(self.group)
_, subs = server.xhdr(
'subject', (str(first) + '-' + str(last)))
for sub in subs[:10]: # default last ten
id = sub[0]
lines = server.article(id)[3]
message = message_from_string('\n'.join(lines))
title = message['subject']
body = message.get_payload()
if message.is_multipart():
body = body[0]
yield NewsItem(title, body)
server.quit()
def getItems(self):
"""
书中原例getItems()方法
返回 nntplib.NNTPTemporaryError: 480 NEWNEWS command disabled by administrator
#480管理员禁用NEWNEWS命令
def getItems(self):
start = localtime(time() - self.window*day)
date = strftime('%y%m%d', start)
hour = strftime('%H%M%S', start)
server = NNTP(self.servername)
ids = server.newnews(self.group, date, hour)[1]
for id in ids:
lines = serverarticle(id)[3]
message = message_from_string('\n'.join(lines))
title = message['subject']
body = message.get_payload()
if message.is_multipat():
body = body[0]
yield NewsItem(title, body)
server.quit()
"""
server = NNTP(self.servername)
(resp, count, frist, last, name) = server.group(self.group)
(resp, subs) = server.xhdr('subject', (str(frist) + '-' + (last)))
for subject in subs[-10:]:
title = subject[1]
(reply, num, id, list) = server.body(subject[0])
body = ''.join(list)
#print(num) #186919
#print(title) #Re: Find out which module a class came from
#print(''.join(list))#prano wrote:> But for merely ordinary obfuscation caused by poor...
yield NewsItem(title, body)
server.quit()
def getItems(self): # 新闻生成器
yesterday = date.today() - timedelta(days=self.window) # 计算新闻获取的起始时间
server = NNTP(self.server_name) # 创建服务器连接对象
ids = server.newnews(self.group, yesterday)[1] # 获取新闻id列表
count = 0 # 创建计数变量
for id in ids: # 循环获取新闻id
count += 1 # 计数递增
if count <= 10: # 如果计数小于10
article = server.article(id)[1][2] # 获取指定id的新闻文章
lines = [] # 创建每行新闻内容的列表
for line in article: # 从新闻文章中读取每一行内容
lines.append(line.decode()) # 将每行新闻内容解码，添加到新闻内容列表。
message = message_from_string('\n'.join(lines)) # 合并新闻列表内容为字符串并转为消息对象
title = message['subject'].replace('\n', '') # 从消息对象中获取标题
body = message.get_payload() # 从消息对象中获取到新闻主体内容
if message.is_multipart(): # 如果消息对象包含多个部分
body = body[0] # 获取到的内容中第1个部分获取新闻主体内容
yield NewsItem(title, body) # 生成1个新闻内容对象
else: # 如果超出10条内容
break # 跳出循环
server.quit() # 关闭连接
#!/usr/local/bin/python3
from nntplib import NNTP
server = NNTP('news.aioe.org')
resp, count, first, last, name = server.group('sci.logic')
print('Group', name, 'has', count, 'articles, range', first, 'to', last)
resp, subs = server.xhdr('subject', str(first) + '-' + str(last))
for id, text in subs[-10:]:
print(id, text)
server.quit()
listonly = 0
showhdrs = ['From', 'Subject', 'Date', 'Newsgroups', 'Lines']
try:
import sys
servername, groupname, showcount = sys.argv[1:]
showcount = int(showcount)
except:
servername = 'news.rmi.net'
groupname = 'comp.lang.python' # cmd line args or defaults
showcount = 10 # show last showcount posts
# connect to nntp server
print 'Connecting to', servername, 'for', groupname
from nntplib import NNTP
connection = NNTP(servername)
(reply, count, first, last, name) = connection.group(groupname)
print '%s has %s articles: %s-%s' % (name, count, first, last)
# get request headers only
fetchfrom = str(int(last) - (showcount-1))
(reply, subjects) = connection.xhdr('subject', (fetchfrom + '-' + last))
# show headers, get message hdr+body
for (id, subj) in subjects: # [-showcount:] if fetch all hdrs
print 'Article %s [%s]' % (id, subj)
if not listonly and raw_input('=> Display?') in ['y', 'Y']:
reply, num, tid, list = connection.head(id)
for line in list:
for prefix in showhdrs:
if line[:len(prefix)] == prefix:
class Archive(object):
@staticmethod
def is_diff(body):
return bool([line for line in body if line.startswith("diff ")])
def __init__(self, group, server):
self.conn = NNTP(server)
resp, count, first, last, name = self.conn.group(group)
self.group = group
self.server = server
self.first = int(first)
self.last = int(last)
def get_number_from_user(self, msg_id):
"""
Convert something the user might input into a message id.
These are:
# An NNTP message number
# A gmane link that includes the NNTP message number
# The original Message-Id header of the message.
NOTE: gmane's doesn't include the message number in STAT requests
that involve only the Message-Id (hence the convolution of getting
all the headers).
"""
msg_id = re.sub(r".*gmane.org/gmane.comp.version-control.git/([0-9]+).*", r"\1", str(msg_id))
_, n, id, result = self.conn.head(msg_id)
for header in result:
m = re.match(r"Xref: .*:([0-9]+)\s*$", header, re.I)
if m:
return int(m.group(1))
else:
raise FatalError("No (or bad) Xref header for message '%s'" % msg_id)
def get_patch_series(self, user_input, search_limit=100):
"""
Given an NNTP message number or a Message-Id header return
an mbox containing the patches introduced by the author of that message.
This handles the case where the threading is right *and* the patches
are numbered in a simple scheme:
[PATCH] this patch has no replies and stands on its own
[PATCH 0/2] this is an introduction to the series
|- [PATCH 1/2] the first commit
|- [PATCH 2/2] the second commit
[PATCH 1/3] this is the first commit
|- [PATCH 2/3] and this is the second
|- [PATCH 3/3] and this is the third
TODO: it would be nice to make the search more efficient, we can
use the numbers in [PATCH <foo>/<bar>] to stop early.
"""
start_id = self.get_number_from_user(user_input)
messages = limit(self.messages_starting_from(start_id), search_limit)
try:
thread = Thread(messages.next())
except StopIteration:
raise FatalError("No message at id '%s' using XOVER")
n_since_last = 0
for message in messages:
if n_since_last > 5:
break
elif thread.should_include(message):
n_since_last = 0
thread.append(message)
else:
n_since_last += 1
else:
raise FatalError('did not find end of series within %s messages', search_limit)
for message in self.xover(start_id - 5, start_id -1):
if thread.should_include(message):
thread.append(message)
return self.mboxify(thread)
def mboxify(self, thread):
"""
Convert a thread into an mbox for application via git-am.
"""
lines = []
for message in thread.in_order():
_, number, msg_id, body = self.conn.body(str(message.number))
# git-am doesn't like empty patches very much, and the 0/X'th patch is
# often not a patch, we skip it here. (TODO, warn the user about this)
if re.search(r" 0+/[0-9]+", message.subject) and not self.is_diff(body):
continue
poster = parseaddr(message.poster)[0]
date = ctime(mktime(parsedate(message.date)))
lines.append("From %s %s" % (poster, date))
lines.append("From: %s" % message.poster)
lines.append("Subject: %s" % message.subject)
lines.append("Date: %s" % message.date)
lines.append("Message-Id: %s" % message.msg_id)
lines.append("Xref: %s %s:%s" % (self.server, self.group, message.number))
lines.append("References: %s" % "\n\t".join(message.references))
lines.append("")
lines += body
lines.append("")
return "\n".join(lines)
def messages_starting_from(self, start_id):
"""
Generate all message headers starting from the given id and working upwards.
"""
while start_id < self.last:
next_id = min(start_id + 20, self.last)
for message in self.xover(start_id, next_id):
yield message
start_id = next_id + 1
def xover(self, begin, end):
"""
Get the headers for the messages with numbers between begin and end.
"""
if begin == end:
return []
_, result = self.conn.xover(str(min(begin, end)), str(max(begin, end)))
result = [Message(int(number), subject, poster, date, msg_id, references) for
(number, subject, poster, date, msg_id, references, size, lines) in result]
return sorted(result, key=lambda x: x.number)
# -*-coding:gbk-*-
from nntplib import NNTP
server = NNTP('news.foo.bar')
print server.group('comp.lang.python.announce')[1]
formatter = logging.Formatter('%(name)-12s: %(levelname)-8s %(message)s')
console.setFormatter(formatter)
logging.getLogger('').addHandler(console)
day = 24 * 60 * 60
yesterday = localtime(time() - day)
date = strftime('%y%m%d', yesterday)
hour = strftime('%H%M%S', yesterday)
servername = 'news.aioe.org'
group = 'comp.lang.python'
server = NNTP(servername)
ids = server.newnews(group, date, hour)[1]
logging.info('this is ids')
logging.info(ids)
for id in ids:
print 'this is id', id
head = server.head(id)[3]
for line in head:
if line.lower().startswith('subject:'):
subject = line[9:]
break
body = server.body(id)[3]
import sqlite3
from nntplib import NNTP
group = 'alt.binaries.movies.x264'
chunk_size = 100000
sql = sqlite3.connect('usenet.db')
print "About to start dumping articles from " + group
serv = NNTP('news.astraweb.com', 119, 'arealmuto', 'stock1114')
resp = serv.group(group)
count = int(resp[1])
first = int(resp[2])
last = int(resp[3])
print "There are " + str(count) + " articles to get"
print "First: " + str(first)
print "Last: " + str(last)
print "Using chunks size of: " + str(chunk_size)
print "It should take " + str(count/chunk_size) + " requests to finish"
id = int(first)
i = 0
master_list = []
while id < last:
print str(i) +": Getting id's " + str(id) + " - " + str(id + chunk_size)
resp, list = serv.xover(str(id), str(id+ chunk_size))
print "Done fetching"
print "Adding to master list"
for line in list:
from codeTransfer import *
import textwrap
import re
# print strftime('%y%m%d')
# start = localtime(time()-60*60*24*365)
# print strftime('%y%m%d',start)
class SimpleWebSource:
def __init__(self, url, titlePattern, bodyPattern):
self.url = url
self.titlePattern = re.compile(titlePattern)
self.bodyPattern = re.compile(bodyPattern)
def getItems(self):
text = urlopen(self.url).read()
titles = self.titlePattern.findall(text)
bodies = self.bodyPattern.findall(text)
for title in titles:
print title[1].decode('utf-8')
print bodies
bbc_url = 'http://news.sina.com.cn'
bbc_title = r'<a target="_blank" href="(.*?)">(.*?)</a>'
bbc_body = r'(?s)</a>\s*<br />\s*(.*?)\s*<'
# bbc = SimpleWebSource(bbc_url,bbc_title,bbc_body)
# bbc.getItems()
server = NNTP('129.69.1.59')
server.group('camp.lang.python')[0]
#! /usr/bin/python from sys import stdin from nntplib import NNTP from os import environ s = NNTP(environ["NNTPSERVER"]) s.post(stdin) s.quit()
#!/usr/bin/env python
# -*- coding: UTF-8 *-*
from nntplib import NNTP
n = NNTP('your.nntp.server')
rsp, ct, fst, lst, grp = n.group('comp.lang.python')
rsp, anum, mid, data = n.article('110457')
for eachLine in data:
print eachLine
From: "Alex Martelli" <alex@...> Subject: Re: Rounding Question
Date: Wed, 21 Feb 2001 17:05:36 +0100
"Remco Gerlich" <remco@...> wrote:
Jacob Kaplan-Moss <jacob@...> wrote in comp.lang.python:
So I've got a number between 40 and 130 that I want to round up to
the nearest 10. That is:
40 --> 40, 41 --> 50, ..., 49 --> 50, 50 --> 50, 51 --> 60
Rounding like this is the same as adding 5 to the number and then
rounding down. Rounding down is substracting the remainder if you were
to divide by 10, for which we use the % operator in Python.
This will work if you use +9 in each case rather than +5 (note that he doesn't
really want rounding -- he wants 41 to 'round' to 50, for ex).
Alex
>>> n.quit()
'205 closing connection - goodbye!'
from nntplib import NNTP
servername = 'news.foo.bar'
group = 'comp.lang.python.announce'
server = NNTP(servername)
howmany = 10
resp, count, first, last, name = server.group(group)
start = last - howmany + 1
resp, overviews = server.over((start, last))
for id, over in overviews:
subject = over['subject']
resp, info = server.body(id)
print(subject)
print('-' * len(subject))
for line in info.lines:
print(line.decode('latin1'))
print()
server.quit()
#__author: ZhengNengjin
#__date: 2018/10/25
from nntplib import NNTP
n = NNTP('your.nntp.server')
rsp, ct, fst, lst, grp = n.group('comp,lang.python')
rsp, anum, mid, data = n.article('110457')
for eachLine in data:
print(eachLine)
n.quit()
class DanskGruppenArchive(object):
"""Class that provides an interface to Dansk-gruppens emails archive on
gmane
"""
def __init__(self, article_cache_size=300, cache_file=None):
"""Initialize local variables"""
# Connect to news.gmane.org
self.nntp = NNTP('news.gmane.org')
# Setting the group returns information, which right now we ignore
self.nntp.group('gmane.comp.internationalization.dansk')
# Keep a local cache in an OrderedDict, transferred across session
# in a pickled version in a file
self.article_cache_size = article_cache_size
self.cache_file = cache_file
if cache_file and path.isfile(cache_file):
with open(cache_file, 'rb') as file_:
self.article_cache = pickle.load(file_)
logging.info('Loaded %i items from file cache',
len(self.article_cache))
else:
self.article_cache = OrderedDict()
def close(self):
"""Quit the NNTP session and save the cache"""
self.nntp.quit()
if self.cache_file:
with open(self.cache_file, 'wb') as file_:
pickle.dump(self.article_cache, file_)
logging.info('Wrote %i items to cache file',
len(self.article_cache))
@property
def last(self):
"""Return the last NNTP ID as an int"""
return self.nntp.group('gmane.comp.internationalization.dansk')[3]
def _get_article(self, message_id):
"""Get an article (cached)
Args:
message_id (int): The NNTP ID of the message
Returns:
list: List of byte strings in the message
"""
# Clear excess cache
if len(self.article_cache) > self.article_cache_size:
self.article_cache.popitem(last=False)
# Check if article is in cache and if not, put it there
if message_id not in self.article_cache:
# nntp.article() returns: response, information
# pylint: disable=unbalanced-tuple-unpacking
_, info = self.nntp.article(message_id)
self.article_cache[message_id] = info
return self.article_cache[message_id]
@staticmethod
def _article_to_email(article):
"""Convert a raw article to an email object
Args:
article (namedtuple): An article named tuple as returned by NNTP
Returns:
email.message: An email message object
"""
# article lines are a list of byte strings
decoded_lines = [line.decode('ascii') for line in article.lines]
article_string = '\n'.join(decoded_lines)
# Make an email object
return email.message_from_string(article_string)
def get_subject(self, message_id):
"""Get the subject of an message
Args:
message_id (int): The NNTP ID of the the message
Returns:
str: The subject of the article
"""
article = self._get_article(message_id)
mail = self._article_to_email(article)
# The subject may be encoded by NNTP, so decode it
return decode_header(mail['Subject'])
def get_body(self, message_id):
"""Get the body of a message
Args:
message_id (int): The NNTP ID of the the message
Returns:
str: The body of the article as a str or None if no body could be
found or succesfully decoded
"""
article = self._get_article(message_id)
mail = self._article_to_email(article)
# Walk parts of the email and look for text/plain content type
for part in mail.walk():
if part.get_content_type() == 'text/plain':
body = part.get_payload(decode=True)
# Find the text encoding from lines like:
# text/plain; charset=UTF-8
# text/plain; charset=utf-8; format=flowed
# Encoding sometimes has "" around it, decode is OK with that
for type_part in part['Content-Type'].split(';'):
if type_part.strip().startswith('charset='):
encoding = type_part.replace('charset=', '')
break
else:
message = 'Looking for the character encoding in the '\
'string "%s" went wrong'
logging.warning(message, part['Content-Type'])
return None
# Decode and return the body
try:
body = body.decode(encoding)
except LookupError:
message = 'Do not know how to handle a body with '\
'charset: %s'
logging.warning(message, encoding)
return None
return body
def get_attachment(self, message_id, filename):
"""Get attachment by filename
Args:
message_id (int): The NNTP ID of the the message
filename (str): The filename for the attachment
Returns:
bytes: The binary content of the attachment
"""
return self.get_attachments(message_id).get(filename)
def get_attachments(self, message_id):
"""Get attachments
Args:
message_id (int): The NNTP ID of the the message
Returns:
dict: Dict with attachments where keys are filenames and values are
their binary content
"""
article = self._get_article(message_id)
mail = self._article_to_email(article)
attachments = {}
# Walk parts of the email and look for application/octet-stream
# content type
for part in mail.walk():
content_disp = part['Content-Disposition']
if not (content_disp and content_disp.startswith('attachment')):
continue
# Get the filename from a line like: Content-Disposition:
# attachment; filename="hitori.master.da.podiff"
filename = None
for disp_part in content_disp.split(';'):
if disp_part.strip().startswith('filename='):
filename = disp_part.strip().replace('filename=', '')
# Strip " from filename
filename = filename.strip('"')
if filename is None:
message = 'Unable to extract filename from '\
'Content-Disposition: %s'
logging.warning(message, part['Content-Disposition'])
raise Exception('Unable to extract filename')
attachments[filename] = part.get_payload(decode=True)
return attachments
#date: 06-26-2018
from nntplib import NNTP
import nntplib
from time import strftime, time , localtime
from datetime import datetime, timedelta
oneDay = 24 * 60 * 60
yesterday = datetime.now() - timedelta(days=1)
#date = strftime('%y%m%d', yesterday)
#hour = strftime('%H%M%S', yesterday)
servername = 'news.gmane.org'
groupname = 'gmane.comp.python.committers'
server = NNTP(servername)
resp, count, first, last, name = server.group(groupname)
resp, overviews = server.over((last -9, last))
for id, over in overviews:
print(id, nntplib.decode_header(over['subject']))
'''
ids = server.newnews(group, yesterday)[1]
for id in ids:
head = server.head(id)[3]
for line in head:
if line.lower().startswith('subject:'):
subject = line[9:]
break
body = server.body(id)[3]
#!/usr/bin/python
from nntplib import NNTP
from time import time, localtime, strftime
day = 24 * 60 * 60
yesterday = localtime(time() - day)
date = strftime('%y%m%d', yesterday)
t = strftime('%H%M%S', yesterday)
s = NNTP('web.aioe.org')
g = 'comp.lang.python.announce'
ids = s.newnews(g, date, t)[1]
for id in ids:
head = s.head(id)[3]
for line in head:
if line.lower().startswith('subject:'):
subject = line[9:]
break
body = s.body(id)[3]
print subject
print '-' * len(subject)
print '\n'.join(body)
s.quit()
#/usr/bin/python
# *-*coding:utf-8 *-*
#python NNTP
# group组返回响应信息
from nntplib import NNTP
with NNTP('news.gmane.org') as n:
print(n.group('gmane.comp.python.committers'))
server = NNTP('web.aioe.org')
print(server.group('comp.lang.python.announce')[0])
#('211 4419 1 4419 gmane.comp.python.committers', 4419, 1, 4419, 'gmane.comp.python.committers')
#211 100 3923 4023 comp.lang.python.announce
'''
('211 4371 1 4371 gmane.comp.python.committers', 4371, 1, 4371, 'gmane.comp.python.committers')
411 开头意味着服务器没有这个组
nntplib.NNTPTemporaryError: 411 No such group comp.lang.python.announce
211开头 基本上意味着服务器拥有你所请求的组
('211 98 3911 4008 comp.lang.python.announce', 98, 3911, 4008, 'comp.lang.python.announce')
还有可能得到一个带有类似错误信息的的异常 如果引发了异常 可能是服务器的名字写错了
另外一种可能是在创建服务器对象和调用group方法之间 '超时了'， 服务器允许用户保持连接的时间很短(比如10秒)
如果输入速度不够快 把代码放到脚本里， 或着将服务器对象的创建和方法的调用放在同一行内 (以分号隔开)
class DanskGruppenArchive(object):
"""Class that provides an interface to Dansk-gruppens emails archive on
gmane
"""
def __init__(self, article_cache_size=300, cache_file=None):
"""Initialize local variables"""
# Connect to news.gmane.org
self.nntp = NNTP('news.gmane.org')
# Setting the group returns information, which right now we ignore
self.nntp.group('gmane.comp.internationalization.dansk')
# Keep a local cache in an OrderedDict, transferred across session
# in a pickled version in a file
self.article_cache_size = article_cache_size
self.cache_file = cache_file
if cache_file and path.isfile(cache_file):
with open(cache_file, 'rb') as file_:
self.article_cache = pickle.load(file_)
logging.info('Loaded %i items from file cache',
len(self.article_cache))
else:
self.article_cache = OrderedDict()
def close(self):
"""Quit the NNTP session and save the cache"""
self.nntp.quit()
if self.cache_file:
with open(self.cache_file, 'wb') as file_:
pickle.dump(self.article_cache, file_)
logging.info('Wrote %i items to cache file',
len(self.article_cache))
@property
def last(self):
"""Return the last NNTP ID as an int"""
return self.nntp.group('gmane.comp.internationalization.dansk')[3]
def _get_article(self, message_id):
"""Get an article (cached)
Args:
message_id (int): The NNTP ID of the message
Returns:
list: List of byte strings in the message
"""
# Clear excess cache
if len(self.article_cache) > self.article_cache_size:
self.article_cache.popitem(last=False)
# Check if article is in cache and if not, put it there
if message_id not in self.article_cache:
# nntp.article() returns: response, information
# pylint: disable=unbalanced-tuple-unpacking
_, info = self.nntp.article(message_id)
self.article_cache[message_id] = info
return self.article_cache[message_id]
@staticmethod
def _article_to_email(article):
"""Convert a raw article to an email object
Args:
article (namedtuple): An article named tuple as returned by NNTP
Returns:
email.message: An email message object
"""
# article lines are a list of byte strings
decoded_lines = [line.decode('ascii') for line in article.lines]
article_string = '\n'.join(decoded_lines)
# Make an email object
return email.message_from_string(article_string)
def get_subject(self, message_id):
"""Get the subject of an message
Args:
message_id (int): The NNTP ID of the the message
Returns:
str: The subject of the article
"""
article = self._get_article(message_id)
mail = self._article_to_email(article)
# The subject may be encoded by NNTP, so decode it
return decode_header(mail['Subject'])
def get_body(self, message_id):
"""Get the body of a message
Args:
message_id (int): The NNTP ID of the the message
Returns:
str: The body of the article as a str or None if no body could be
found or succesfully decoded
"""
article = self._get_article(message_id)
mail = self._article_to_email(article)
# Walk parts of the email and look for text/plain content type
for part in mail.walk():
if part.get_content_type() == 'text/plain':
body = part.get_payload(decode=True)
# Find the text encoding from lines like:
# text/plain; charset=UTF-8
# text/plain; charset=utf-8; format=flowed
# Encoding sometimes has "" around it, decode is OK with that
for type_part in part['Content-Type'].split(';'):
if type_part.strip().startswith('charset='):
encoding = type_part.replace('charset=', '')
break
else:
message = 'Looking for the character encoding in the '\
'string "%s" went wrong'
logging.warning(message, part['Content-Type'])
return None
# Decode and return the body
try:
body = body.decode(encoding)
except LookupError:
message = 'Do not know how to handle a body with '\
'charset: %s'
logging.warning(message, encoding)
return None
return body
def get_attachment(self, message_id, filename):
"""Get attachment by filename
Args:
message_id (int): The NNTP ID of the the message
filename (str): The filename for the attachment
Returns:
bytes: The binary content of the attachment
"""
return self.get_attachments(message_id).get(filename)
def get_attachments(self, message_id):
"""Get attachments
Args:
message_id (int): The NNTP ID of the the message
Returns:
dict: Dict with attachments where keys are filenames and values are
their binary content
"""
article = self._get_article(message_id)
mail = self._article_to_email(article)
attachments = {}
# Walk parts of the email and look for application/octet-stream
# content type
for part in mail.walk():
content_disp = part['Content-Disposition']
if not (content_disp and content_disp.startswith('attachment')):
continue
# Get the filename from a line like: Content-Disposition:
# attachment; filename="hitori.master.da.podiff"
filename = None
for disp_part in content_disp.split(';'):
if disp_part.strip().startswith('filename='):
filename = disp_part.strip().replace('filename=', '')
# Strip " from filename
filename = filename.strip('"')
if filename is None:
message = 'Unable to extract filename from '\
'Content-Disposition: %s'
logging.warning(message, part['Content-Disposition'])
raise Exception('Unable to extract filename')
attachments[filename] = part.get_payload(decode=True)
return attachments
############################################################################
listonly = 0
showhdrs = ['From', 'Subject', 'Date', 'Newsgroups', 'Lines']
try:
import sys
servername, groupname, showcount = sys.argv[1:]
showcount = int(showcount)
except:
servername = 'news.gmane.org'
groupname = 'gmane.comp.python.general' # cmd line args or defaults
showcount = 10 # show last showcount posts
# connect to nntp server
print 'Connecting to', servername, 'for', groupname
from nntplib import NNTP
connection = NNTP(servername)
(reply, count, first, last, name) = connection.group(groupname)
print '%s has %s articles: %s-%s' % (name, count, first, last)
# get request headers only
fetchfrom = str(int(last) - (showcount-1))
(reply, subjects) = connection.xhdr('subject', (fetchfrom + '-' + last))
# show headers, get message hdr+body
for (id, subj) in subjects: # [-showcount:] if fetch all hdrs
print 'Article %s [%s]' % (id, subj)
if not listonly and raw_input('=> Display?') in ['y', 'Y']:
reply, num, tid, list = connection.head(id)
for line in list:
for prefix in showhdrs:
if line[:len(prefix)] == prefix:
import nntplib
from nntplib import NNTP
s = NNTP('news.gmane.org')
resp, count, first, last, name = s.group('gmane.comp.python.committers')
print ('Group', name, 'has', count, 'articles, range', first, 'to', last)
resp, subs = s.xhdr('subject',first)
for id, sub in subs[-10:]: print (id, sub)
try :
for id, sub in subs[-10:]: print (id, sub)
except TypeError as e:
print(e)
print(s.quit())
# NNTP.
self._file_str.write(str)
def __str__(self):
return self._file_str.getvalue()
week = 7 * 24 * 60 * 60 # Number of seconds in one day
start = localtime(time() - week)
date = strftime('%y%m%d', start)
time = strftime('%H%M%S', start)
full_date = date + time
servername = 'news.aioe.org'
group = 'comp.lang.python.announce'
server = NNTP(servername)
ids = server.newnews(group,
datetime.datetime.strptime(full_date, '%y%m%d%H%M%S'))[1]
content = StringBuilder()
content.Append('''
<html>
<head>
<title>Week's News - Python Announce</title>
</head>
<body>
<h1>Week's News - Python Announce</h1>
''')
args = sys.argv if len(args) == 2: print "Resetting lastread and seen.." resetLastread() exit seen = [] newdate = None print "Reading date and seen files" date,seen = loadLastread() for serverentry in servers: server = serverentry[0] newsgroups = serverentry[2] print "Connecting to: " + server s = NNTP(server) for newsgroup in newsgroups: feedGroup(server, newsgroup, date, seen) serverdate = s.date() date = serverdate[1] time = serverdate[2] year = 2000 + int(serverdate[1][0:2]) ## So I got a Y3K problem here. Deal. month = int(serverdate[1][2:4]) day = int(serverdate[1][4:]) hour = int(serverdate[2][0:2]) minute = int(serverdate[2][2:4]) second = int(serverdate[2][4:]) newdate = datetime.datetime(year,month,day,hour,minute,second) print "Server time is " + str(newdate)
from nntplib import NNTP
#server = NNTP('news.easynews.com')
#server = NNTP('news.giganews.com')
#server = NNTP('news.mozilla.org')
server = NNTP('news.kornet.net')
print server.group('comp.lang.python.announce')[0]
"""
| group(self, name)
| Process a GROUP command. Argument:
| - group: the group name
| Returns:
| - resp: server response if successful
| - count: number of articles (string)
| - first: first article number (string)
| - last: last article number (string)
| - name: the group name
"""
group = server.group('han.test')
print repr(group)
first = group[2]
last = group[3]
print "first ", first
print "last ", last
i = 0
for id in range(int(first), int(last)):
i += 1
print(server.article(str(id)))
#! /usr/bin/env python
# -*- coding:utf-8 -*-
from nntplib import NNTP
servername = 'web.aioe.org'
group = 'comp.lang.python.announce'
server = NNTP(servername)
howmany = 10
resp, count, first, last, name = server.group(group)
start = last - howmany + 1
resp, overviews = server.over((start, last))
for id, over in overviews:
subject = over['subject']
resp, info = server.body(id)
print('subject:', subject)
print('-' * len(subject))
for line in info.lines:
print(line.decode('latin1'))
print()
server.quit()
from nntplib import NNTP
server = NNTP('news2.neva.ru')
print server.group('alt.sex.telephone')
class NewsWatcher(MessageWatcher):
def __init__(self, server, groups,
user=None, pw=None, port=None, tag=None):
MessageWatcher.__init__(self)
self.server = server
self.groups = groups
self.nntp = None # the NNTP connection object
self.user = user
self.pw = pw
self.port = port
self.tag = tag
self.last = {}
self.timeout = None
self.pollInterval = 60
self.debug = 0
def __repr__(self):
return "<NewsWatcher %s:%s (%s)>" % (self.server, self.port,
",".join(self.groups))
def __getstate__(self):
d = MessageWatcher.__getstate__(self)
d['nntp'] = None # just in case
return d
def start(self):
port = self.port
if not port:
port = NNTP_PORT
self.nntp = NNTP(self.server, port, self.user, self.pw,
readermode=1)
# only look for messages that appear after we start. Usenet is big.
if not self.last: # only do this the first time
for g in self.groups:
resp, count, first, last, name = self.nntp.group(g)
self.last[g] = int(last)
if self.debug: print "last[%s]: %d" % (g, self.last[g])
self.timeout = gtk.timeout_add(self.pollInterval*1000,
self.doTimeout)
def stop(self):
self.nntp.quit()
self.nntp = None
if self.timeout:
gtk.timeout_remove(self.timeout)
self.timeout = None
def doTimeout(self):
self.poll()
return gtk.TRUE # keep going
def poll(self):
#print "polling", self
for g in self.groups:
resp, count, first, last, name = self.nntp.group(g)
for num in range(self.last[g]+1, int(last)+1):
try:
resp, num, id, lines = self.nntp.article("%d" % num)
except NNTPError:
continue
name = "%s:%d" % (g, int(num))
if self.debug: print "got", name
if self.tag:
if not filter(lambda line, tag=tag: line.find(tag) != -1,
lines):
continue
self.parseMessage(name, name, time.time(), lines)
self.last[g] = int(last)
def read_article(msg_id, **server):
with NNTP(**server) as srv:
response, info = srv.article(msg_id)
return email.message_from_bytes(b"\r\n".join(info.lines),
policy=email.policy.SMTPUTF8)
#!/usr/bin/python # nntptest from nntplib import NNTP import datetime import os import sys args = sys.argv if not len(args) == 2: print "usage nntpout.py <hostname>" else: print "Connecting to " + args[1] s = NNTP(args[1],user="******",password="******") print "Posting" rv = s.post(sys.stdin) print "Posted" print "Server said: " + rv
# ids = server.newnews(group, date,hour)[1] # 该方法有问题
# for id in ids:
# print(id)
# head = server.head(id)[3]
# for line in head:
# if line.lower().startswith('subject:'):
# subjucet = line[9:]
# break
# body = server.body(id)[3]
#
# print(subjucet)
# print('-' * len(subjucet))
# print('\n'.join(body))
servername = 'web.aioe.org'
group = 'comp.lang.python.announce'
server = NNTP(servername)
(resp, count, first, last, name) = server.group(group)
(resp, subs) = server.xhdr('subject', (str(first) + '-' + (last)))
for subject in subs[-10:]:
title = subject[1]
(reply, num, id, list) = server.body(subject[0])
body = ''.join(list)
print(num) #186919
print(title) #Re: Find out which module a class came from
print(
''.join(list)
) #prano wrote:> But for merely ordinary obfuscation caused by poor...
server.quit()
