def sub_mytag(self, re):
"""Replacing tagname with attribute"""
try:
res = eval('self.' + re.group(1))
except:
res = eval(re.group(1))
return res
def sub_mytag(self, re):
"""Replacing tagname with attribute"""
try:
res = eval('self.' + re.group(1))
except:
res = eval(re.group(1))
return res
def _privmsg(self, msg):
msgs = msg.split()
fullnick = msgs[0][1:]
nick = fullnick.split("!")[0]
#ident = fullnick.split("!")[1].split("@")[0]
#hostname = fullnick.split("@")[1]
dest = msgs[2]
content = ' '.join(msgs[3:])
if dest.lower() == self.adminchan.lower():
tools.debug(msgs[3][1:])
cmd = { '%join': self._cmdJoin, '%part':self._cmdPart, '%quit':self._cmdQuit, '%say':self._cmdSay, '%raw':self._cmdRaw }
try:
cmd.get(msgs[3][1:])(msg)
except:
#self.send("PRIVMSG {0} :Message reçu de {1} pour {2} > {3}".format(adminchan, nick, dest, ' '.join(msgs[3:])[1:]))
pass
#else:
# self.send("PRIVMSG {0} :Message reçu de {1} pour {2} > {3}".format(self.adminchan, nick, dest, ' '.join(msgs[3:])[1:]))
if dest[0] == '#':
re=ytre.search(content)
if re:
print("Find YouTube video {}".format(re.group('videoid')))
stats=youtube.ytVideoStats(re.group('videoid'))
self.send("PRIVMSG {} :\002\00301,00You\00300,04Tube\017\002 {} \002{} | Durée : {} | Vues : {} | J'aime : {} | Je n'aime pas : {}".format(dest, stats['user'], stats['title'], str(datetime.timedelta(seconds=stats['duration'])), stats['view'], stats['like'], stats['dislike']))
else:
pass
def load_latest_cfg(dir_path, target=__C):
import re
cfg_count = None
source_cfg_path = None
for fname in os.listdir(dir_path):
ret = re.search('cfg(\d+)\.yml', fname)
if ret != None:
if cfg_count is None or (int(re.group(1)) > cfg_count):
cfg_count = int(re.group(1))
source_cfg_path = os.path.join(dir_path, ret.group(0))
cfg_from_file(file_name=source_cfg_path, target=target)
def check_none(re): ''' 當正則表達式搜尋不到回傳none以避免報錯即無法辨識 ''' if re: return re.group(1) else: return None
def corpus_files_iter(root_path):
file_pattern = os.path.join(root_path, glob_pattern)
for file_path in glob.iglob(file_pattern):
file_path = os.path.normpath(file_path)
re = lang_regex.search(file_path)
if not re:
continue
yield re.group(1), file_path
def email(self,value,errorMessage = ''):
value = re.group("\b[A-Z0-9._%+-]+@[A-Z0-9.-]+\.[A-Z]{2,}\b")
if errorMessage:
self.emailError = errorMessage
if value == "":
return self.emailError
else:
return True
def setVersion(self, version):
"""Sets the version of the reporter to version. Recognizes and parses CVS
revision strings.
"""
if version == None:
return
found = re.search('Revision: (.*) ', version)
if found:
self.version = re.group(1)
else:
self.version = version
def pinger(self):
while True:
try:
ln = self.ping.stdout.readline()
re = self.PING_RE.search(ln)
if re:
(cnt, rtt) = self.data["ping"] if self.data.has_key("ping") else (0, None)
self.data["ping"] = (cnt+1, float(re.group(1)))
self.update()
except IOError:
break
self.after(100, self.pinger)
def pinger(self):
while True:
try:
ln = self.ping.stdout.readline()
re = self.PING_RE.search(ln)
if re:
(cnt, rtt) = self.data["ping"] if self.data.has_key(
"ping") else (0, None)
self.data["ping"] = (cnt + 1, float(re.group(1)))
self.update()
except IOError:
break
self.after(100, self.pinger)
def get_file_name(self):
if self.html is None:
self.download_html()
match = re.search(r'<title[^>]+>([^<]+) - ', self.html)
if match:
name = re.group(1)
else:
matches = re.findall('<h1>(.*?)</h1>', self.html)
if len(matches) > 1:
name = matches[1]
else:
name = matches[0]
return name + '.flv'
def readSource(self, source, pos, controller):
re = self.endDeclRE
commentStart = re.search(source, pos)
if commentStart == -1:
self.source = 'No declarations found!'
controller.warning('missing end of declaration')
return pos
content = re.group(1)
if string.find(string.lower(content), 'enddecl') != -1:
self.source = source[pos:commentStart]
nextPos = re.regs[0][1]
else:
self.pos = 'No declarations found!'
nextPos = commentStart
return nextPos
def get_file_name(self):
if self.html is None:
self.download_html()
match = re.search(r'<title[^>]+>([^<]+) - ', self.html)
if match:
name = re.group(1)
else:
matches = re.findall('<h1>(.*?)</h1>', self.html)
if len(matches) > 1:
name = matches[1]
else:
name = matches[0]
return name + '.flv'
def parseFunctionDeclaration(self, text):
for re in [self.funcDclRE, self.operatorDclRE, self.operatorNewDclRE]:
matchPos = re.search(text)
if matchPos != -1:
break
else:
return None
funcName, paramString = re.group(1, 2)
paramNames = []
if string.strip(paramString) != '':
paramStrings = string.split(paramString, ',')
for str in paramStrings:
str = string.strip(str)
if self.paramRE.search(str) != -1:
paramNames.append(self.paramRE.group(1))
else:
paramNames.append('parse error')
return funcName, paramNames
repl:指定的用来替换的字符串
string：目标字符串
count：最多替换次数
flags：同re简介
功能：在目标字符串中以正则表达式的规则匹配字符串，再把他们替换成指定的字符串。可以指定替换的次数，如果不指定，替换所有的匹配字符串
区别：前者返回结果字符串，后者返回一个tuple，第一个元素是结果字符串，第二个元素是表示被替换的次数
'''
print("字符串的替换与修改\n")
str3 = "xcs is a good good good man!"
print(re.sub(r"(good)", "nice", str3))
print(re.subn(r"(good)", "nice", str3, count=2))
print(type(re.sub(r"(good)", "nice", str3))) #str
print(type(re.subn(r"(good)", "nice", str3))) # tuple
# 分组
'''
re.group()
概念：除了简单的判断是否匹配之外，正则表达式还有提取子串的功能，用()表示分组
'''
str2 = r"0739-8881510"
m = re.match(r"(?P<first>\d{4})-(\d{7})", str2)
print(m)
# 查看匹配的各组的情况,用序号获取对应组的信息
print(m.group())
print(m.group(1))
print(m.group("first"))
print(m.group(2))
print(m.groups())
def _check_phone_allowed_characters(self):
for record in self:
phone_disallowed_chars = "[^\d\-]"
if record.phone:
res = re.search(phone_disallowed_chars, record.phone)
if res:
raise ValidationError("The phone number contains an invalid character: "+ re.group(0))
if record.mobile:
res = re.search(phone_disallowed_chars, record.mobile)
if res:
raise ValidationError("The mobile phone number contains an invalid character: " + res.group(0))
import re
fh = open("techinfo.txt")
for line in fh:
if re.search("python|perl", line):
print(re.group())
fh.close()
def shape_element(element):
node = {}
# [Req.1] We will process only 2 types of top level tags: 'node' and 'way'
if element.tag == 'node' or element.tag == 'way' :
# [Req.2] Set 'type' with value = node type ('node' or 'way')
node['type']=element.tag
# For each attrib in node
for attrib in element.attrib:
# [Req.3] Attributes for latitude ('lat') and longitude ('lon') should be added to a 'pos' array as float
if attrib == 'lat':
if 'pos' not in node:
node['pos'] = [None,None]
node['pos'][0] = float (element.attrib['lat'])
elif attrib == 'lon':
if 'pos' not in node:
node['pos'] = [None,None]
node['pos'][1] = float (element.attrib['lon'])
# [Req.4] Attributes in the CREATED array should be grouped under a key 'created'
elif attrib in CREATED:
if 'created' not in node:
node['created'] = {}
node['created'][attrib]=element.attrib[attrib]
# [Req.5] All other attributes of 'node' and 'way' should be turned into regular key/value pairs
else:
node[attrib]=element.attrib[attrib]
# We need to look in 'k' for each 'tag' nodes to find the addr:xxx tags we have to group
for tag in element.iter('tag'):
if 'k' in tag.attrib:
# [Req.6] If 'k' in 'tag' node contain problematic char, it will be dropped
if problemchars.match(tag.attrib['k']):
continue
# [Req.7] If 'k' in 'tag' node in TAGDROP it will be dropped
elif tag.attrib['k'] in TAGDROP:
continue
else:
# If there are no problematic char and tag has not to be dropped
# [Req.8] If k attributes is in the form addr:x it will converted in an array 'address'
re = lower_colon.match(tag.attrib['k'])
# If it is in form xxx:xxx - we use group() to extract the part before the colon and the part after the colon
if re:
# Process all tags starting with addr:
first_key=re.group(1)
second_key=re.group(3)
# if there is a second ':' that separates the type/direction of a street, the tag should be ignored
if lower_colon.match(second_key):
continue
elif first_key == 'addr':
if not 'address' in node.keys():
node['address'] = {}
# [Req.17] Fix addr.street using STREETMAPPING
if second_key == 'street':
if tag.attrib['v'] in STREETMAPPING:
node['address']['street'] = STREETMAPPING[tag.attrib['v']]
else:
node['address']['street'] = tag.attrib['v']
# [Req.13] Fix postcodes 20100
if second_key == 'postcode' and tag.attrib['v'] == '20100':
continue
# [Req.13] Fix postcodes 2090
elif second_key == 'postcode' and tag.attrib['v'] == '2090':
node['address'][second_key] = '20090'
# [Req.14] Fix addr:city
elif second_key == 'city' and tag.attrib['v'] == 'milano':
node['address'][second_key] = 'Milano'
# [Req.15] Fix addr:province
elif second_key == 'city' and tag.attrib['v'] == 'MI':
node['address'][second_key] = 'Milano'
else:
node['address'][second_key] = tag.attrib['v']
# there is a lower_colon.match for something different from 'addr'
else:
# replace ':'' with '__'
node[first_key + '__' + second_key] = tag.attrib['v']
else:
# other k values (except type that we import renamed in k_type)
# [Req.9] If k attributes is named 'type', rename it with 'k_type'
if tag.attrib['k'] == 'type':
node['k_type'] = tag.attrib['v']
# [Req.10] If k attribute is named 'comment.it:2', rename it with 'comment:it:2'
elif tag.attrib['k'] == 'comment.it:2':
node['comment:it:2'] = tag.attrib['v']
# [Req.11] If k attribute is named 'step.condition', rename it with 'step_condition'
elif tag.attrib['k'] == 'step.condition':
node['step_condition'] = tag.attrib['v']
else:
node[tag.attrib['k']] = tag.attrib['v']
# [Req.12] If node contains nd tag, there will be transformed into an array
for tag in element.iter('nd'):
if not 'node_refs' in node.keys():
node['node_refs'] = []
if 'ref' in tag.attrib:
node['node_refs'].append(tag.attrib['ref'])
return node
else:
return None
for segment in segments:
print segment['file']
segmenthandle = open(segment['file'], "r", -1)
while 1:
buffer = segmenthandle.read()
if len(buffer) == 0:
break
tshandle.write(buffer)
segmenthandle.close()
tshandle.close()
try:
#mkvmerge v5.8.0 ('No Sleep / Pillow') built on Sep 11 2012 21:46:00
mkvmerge = subprocess.check_output(["mkvmerge", "-V"], stderr=subprocess.STDOUT)
mkversion = re.search("(mkvmerge v(\d+)\.(\d+).(\d+) [^\n]+)", mkvmerge)
if mkversion.group(2) < 5 or mkversion.group(3) < 8:
print "mkvmerge >= 5.8.0 required (you have %s)" % re.group(1)
sys.exit(1)
except CalledProcessError as e:
print e.output
sys.exit(1)
mkv = "%s/final.mkv" % options.scratch
if not os.path.isfile(mkv):
try:
print "remuxing from MPEG-TS -> MKV"
evideo = subprocess.check_output(["mkvmerge", "-o", mkv, tsfile], stderr=subprocess.STDOUT)
except CalledProcessError as e:
print e.output
process.maxEvents = cms.untracked.PSet(
input = cms.untracked.int32(-1)
)
# Define the input source
files = []
for f in args.files:
if re.match('file:', f):
files.append(f)
continue
m = re.match('root://([^/]+)/(.*)/', f)
if m:
host = m.group(1)
path = [ '' ]
for directory in re.group(2).split('/'):
if directory == '': continue
rd = re.compile(d + '$')
newpath = []
for p in path:
status, dirlist = XRootD.client.FileSystem(host).dirlist(p)
for x in dirlist:
if rd.match(x):
newpath.append(x)
if len(newpath) == 0:
if len(path) == 1:
raise Exception('Path root://%s/%s/%s does not exist' % host % path[0] % directory)
else:
msg = 'None of the pathes\n'
for p in path:
msg += 'root://%s/%s/%s\n' % host % p % directory
# Python regular expression grabbing a middle number import re m = re.search(r"-?\d+\.?\d+\s+(-?\d+\.?\d+)\s+-?\d+\.?\d+", "53.4 -63.2 433.2") print(re.group(1))
def hiduke2yyyymmdd_sub(datestr):
yyyymmdd_from = None
yyyymmdd_to = None
dfrom = None
dto = None
if datestr == None or (datestr and datestr.strip() == ""):
return None, None
datestr = datestr.strip()
datestr = datestr.replace("[]?？()（）", "") # あいまい記号を削除
datestr = datestr.replace(" ", "") # 半角全角スペースを削除
datestr = datestr.translate(str.maketrans("１２３４５６７８９０", '1234567890')) # 全角数字を半角に変換
datestr = datestr.translate(str.maketrans("一二三四五六七八九〇元", '12345678901')) # 漢数字を半角数字に変換
datestr = datestr.upper() # アルファベット半角小文字を半角大文字に変換
datestr = datestr.translate(str.maketrans(".-", '//'))
#print("datestr={0}".format(datestr))
gengou_label = datestr[0:2]
gengou = next((filter(lambda x:x['key'] == gengou_label, DateHelper.GENGOUS)), None)
m = REMatcher()
if gengou:
# 和暦
datestr = datestr.translate(str.maketrans("年月日", '///'))
key = gengou['key']
if m.match("^({0})(\d{{1,2}})\/(\d{{1,2}})\/(\d{{1,2}})".format(key) , datestr):
syyyy = DateHelper.wareki2yyyy(m.group(1), m.group(2))
dfrom = dto = Date(syyyy, int(re.group(3)), int(re.group(4)))
elif m.match("^({0})(\d{{1,2}})\/(\d{{1,2}})".format(key), datestr):
syyyy = DateHelper.wareki2yyyy(m.group(1), int(m.group(2)))
dfrom = SimpleDate(syyyy, m.group(3)).to_date()
dto = SimpleDate(syyyy, m.group(3)).end_of_month()
elif m.match("^({0})(\d{{1,2}})".format(key), datestr):
syyyy = DateHelper.wareki2yyyy(m.group(1), int(m.group(2)))
dfrom = SimpleDate(syyyy).to_date()
dto = SimpleDate(syyyy).end_of_year()
else:
dfrom = Date.strptime(gengou['from'], '%Y%m%d')
dto = Date.strptime(gengou['to'], '%Y%m%d')
# union
if dfrom:
yyyymmdd_from = dfrom.strftime("%Y%m%d")
if dto:
yyyymmdd_to = dto.strftime("%Y%m%d")
elif m.match(r"^\d{4}", datestr):
# 西暦
datestr = datestr.translate(str.maketrans("年月日", '///'))
#print("datestr={0}".format(datestr))
if m.match(r"^(\d{4})\/(\d{1,2})\/(\d{1,2})", datestr):
dfrom = dto = SimpleDate(m.group(1), m.group(2), m.group(3)).to_date()
elif m.match(r"^(\d{4})\/(\d{1,2})", datestr):
dfrom = SimpleDate(m.group(1), m.group(2)).to_date()
dto = SimpleDate(m.group(1), m.group(2)).end_of_month()
elif m.match(r"^(\d{4})", datestr):
dfrom = SimpleDate(m.group(1)).to_date()
dto = SimpleDate(m.group(1)).end_of_year()
else:
print("format error (3) #{datestr}")
# union
if dfrom:
yyyymmdd_from = dfrom.strftime("%Y%m%d")
if dto:
yyyymmdd_to = dto.strftime("%Y%m%d")
else:
print("format error (1) #{datestr}")
return yyyymmdd_from, yyyymmdd_to
def stateFor(re):
if re.group(1):
return teststate[1]
return teststate[0]
def shape_element(element):
node = {}
# process only 2 types of top level tags: "node" and "way"
if element.tag == "node" or element.tag == "way" :
# set "type" key/value with tag name
node["type"]=element.tag
# For each attrib in node
for attrib in element.attrib:
# attributes for latitude and longitude should be added to a "pos" array as float
if attrib == 'lat':
if 'pos' not in node:
node['pos'] = [None,None]
node['pos'][0] = float (element.attrib['lat'])
elif attrib == 'lon':
if 'pos' not in node:
node['pos'] = [None,None]
node['pos'][1] = float (element.attrib['lon'])
# attributes in the CREATED array should be added under a key "created"
elif attrib in CREATED:
if 'created' not in node:
node['created'] = {}
node['created'][attrib]=element.attrib[attrib]
# all attributes of "node" and "way" should be turned into regular key/value pairs
else:
node[attrib]=element.attrib[attrib]
# For address we need to look in "k" for each "tag" nodes
for tag in element.iter("tag"):
# if "k" contains problematic characters, it should be ignored in any case
if problemchars.match(tag.attrib["k"]):
continue
else:
# if "k" starts with "addr:", it should be added to a dictionary "address"
re = lower_colon.match(tag.attrib["k"])
if re:
if re.group(1) == 'addr':
if not "address" in node.keys():
node["address"] = {}
addr_key = re.group(3)
# if there is a second ":" that separates the type/direction of a street, the tag should be ignored
if lower_colon.match(re.group(3)):
continue
else:
node["address"][re.group(3)] = tag.attrib["v"]
# there is a lower_colon.match for something different from "addr"
else:
# discard anything in form key:value where key contains ":" and it is not addr
continue
else:
# other k values
node[tag.attrib["k"]]=tag.attrib["v"]
# For nodes "node" and "way"
# If there is a son tag... we process tag "nd"
#
for tag in element.iter("nd"):
if not "node_refs" in node.keys():
node["node_refs"] = []
node["node_refs"].append(tag.attrib["ref"])
return node
else:
return None
re.split(pattern, string, max=0) # Проводит разбиение строки string на основе разделителя регулярного # выражения раttern и в случае успеха возвращает список полученных # сопоставлений, в котором содержится не более чем max фрагментов # (по умолчанию разбиение проводится по всем вхождениям) re.sub(pattern, repl, string, count=0) # Заменяет все вхождения шаблона регулярного выражения pattern в # строке string подстрокой repl, выполняя подстановку вместо всех # вхождений, если не задан параметр count (см. также функцию subn(), # которая, кроме этого, возвращает количество выполненных подстановок) re.purge() # Очищает кеш неявно скомпилированных шаблонов регулярного выражения re.group(num=0) # Возвращает все сопоставление (или конкретную подгруппу num) re.groups(default=None) # Возвращает все сопоставленные подгруппы в виде кортежа (если # сопоставления отсутствуют, кортеж пуст) re.groupdict(default=None) # Возвращает словарь, содержащий все согласованные именованные # подгруппы, в котором ключами являются имена подгрупп (если # сопоставления отсутствуют, словарь пуст) # ::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::: re.I, re.IGNORECASE
import re
import requests
c=requests.get('http://blackfoxs.org/radar/puzzle/',headers={'user-agent':'9e9'})
re=re.search('id="desc">(.*?)</h2>',c.text)
result=re.group(1)
print(result)
input()
import re
fh = open("techinfo.txt")
for line in fh:
if re.search("python|perl",line):
print(re.group())
fh.close()
import re
p = re.compile(r'\W+')
result = p.split("This is my first split example string")
print(result)
DOB = "25-01-1991#This is Date of Birth"
# Delete Python-style comments
Birth = re.sub(r'#.*$', "", DOB)
print("Date of Birth : ", Birth)
# Remove anything other than digits
Birth1 = re.sub(r'\D', "", Birth)
print("Before substituting DOB : ", Birth1)
# Substituting the '-' with '.(dot)'
New = re.sub(r'\W', ".", Birth)
print("After substituting DOB: ", New)
a = re.compile(r'\W+')
m = re.group("string goes here")
print(m)
self._do_work()
steps_regex = re.compile("Step (\w).*step (\w)")
with open(INPUT) as f:
data = [x.strip() for x in f.readlines()]
# parse datas
graph = defaultdict(list)
prereq = defaultdict(list)
origin = set()
target = set()
for line in data:
re = steps_regex.match(line)
f = re.group(1)
t = re.group(2)
origin.add(f)
target.add(t)
graph[f].append(t)
prereq[t].append(f)
# nodes that are not targets
starter = origin - target
# part 1
available = list(starter)
result = ""
while len(available) > 0:
available.sort()
node = available.pop(0)
#sub:替换,去掉一个字符串的所有数字
strs = '34ibikalksajGDSOPX682j'
strs = re.sub('\d+', '', strs)
print(strs)
print()
#获取所有li节点的歌名,第一种方法
results = re.findall('<li.*?>\s*?(<a.*?>)?(\w+)(</a>)?\s*?</li>', html, re.S)
for result in results:
print(result[1])
print()
#sub方法获取所有li节点的歌名，第二种方法
s = re.sub('<a.*?>|</a>', '', html)
fs = re.findall('<li.*?>(.*?)</li>', s, re.S)
# print(fs)
for k in fs:
print(k.strip()) #去掉字符串两边的空格或换行符
print()
#目标使匹配齐秦 往事随风，发现其唯一的class=active
#re.S:使.匹配包括换行符在内的所有字符,写了之后。不用在正则李写空白符\s了
# .： 匹配任意字符除了 换行
#* ：前面的原子重复0次、1次到多次 {0,}
#.*?：阻止贪婪匹配
re = re.search('li.*?active.*?singer="(.*?)">(.*?)</a>', html, re.S)
print(re)
print(re.group(1))
print(re.group(2))
print()
with xlsxwriter.Workbook(xlsx_file, {'default_date_format': 'yyyy-mm-dd hh:mm:ss'}) as workbook:
worksheet = workbook.add_worksheet()
row_no = 0
for filename in filenames:
print(filename)
with open(filename) as f:
try:
data = json.load(f)
except JSONDecodeError as e:
raise RuntimeError(f"For file {filename}") from e
# Argument to put in the first column, if timestamp convert to date.
first_field_value = filename
try:
if re.search('\\\\(\\d+)[^\\\\]*', first_field_value):
first_field_value = datetime.datetime.fromtimestamp(int(re.group(1)))
except ValueError:
pass
if first:
# Identify a column for every key.
column_for["_"] = len(column_for)
for row in data:
for key in row:
if not key in column_for:
column_width = []
column_for[key] = len(column_for)
column_width = [0] * len(column_for)
#
