"""Shared support for scanning document type declarations in HTML and XHTML. This module is used as a foundation for the html.parser module. It has no documented public API and should not be used directly. """ import re _declname_match = re.compile(r'[a-zA-Z][-_.a-zA-Z0-9]*\s*').match _declstringlit_match = re.compile(r'(\'[^\']*\'|"[^"]*")\s*').match _commentclose = re.compile(r'--\s*>') _markedsectionclose = re.compile(r']\s*]\s*>') # An analysis of the MS-Word extensions is available at # http://www.planetpublish.com/xmlarena/xap/Thursday/WordtoXML.pdf _msmarkedsectionclose = re.compile(r']\s*>') del re class ParserBase: """Parser base class which provides some common support methods used by the SGML/HTML and XHTML parsers.""" def __init__(self): if self.__class__ is ParserBase: raise RuntimeError( "_markupbase.ParserBase must be subclassed") def error(self, message): raise NotImplementedError( "subclasses of ParserBase must override error()") def reset(self): self.lineno = 1 self.offset = 0 def getpos(self): """Return current line number and offset.""" return self.lineno, self.offset # Internal -- update line number and offset. This should be # called for each piece of data exactly once, in order -- in other # words the concatenation of all the input strings to this # function should be exactly the entire input. def updatepos(self, i, j): if i >= j: return j rawdata = self.rawdata nlines = rawdata.count("\n", i, j) if nlines: self.lineno = self.lineno + nlines pos = rawdata.rindex("\n", i, j) # Should not fail self.offset = j-(pos+1) else: self.offset = self.offset + j-i return j _decl_otherchars = '' # Internal -- parse declaration (for use by subclasses). def parse_declaration(self, i): # This is some sort of declaration; in "HTML as # deployed," this should only be the document type # declaration ("<!DOCTYPE html...>"). # ISO 8879:1986, however, has more complex # declaration syntax for elements in <!...>, including: # --comment-- # [marked section] # name in the following list: ENTITY, DOCTYPE, ELEMENT, # ATTLIST, NOTATION, SHORTREF, USEMAP, # LINKTYPE, LINK, IDLINK, USELINK, SYSTEM rawdata = self.rawdata j = i + 2 assert rawdata[i:j] == "<!", "unexpected call to parse_declaration" if rawdata[j:j+1] == ">": # the empty comment <!> return j + 1 if rawdata[j:j+1] in ("-", ""): # Start of comment followed by buffer boundary, # or just a buffer boundary. return -1 # A simple, practical version could look like: ((name|stringlit) S*) + '>' n = len(rawdata) if rawdata[j:j+2] == '--': #comment # Locate --.*-- as the body of the comment return self.parse_comment(i) elif rawdata[j] == '[': #marked section # Locate [statusWord [...arbitrary SGML...]] as the body of the marked section # Where statusWord is one of TEMP, CDATA, IGNORE, INCLUDE, RCDATA # Note that this is extended by Microsoft Office "Save as Web" function # to include [if...] and [endif]. return self.parse_marked_section(i) else: #all other declaration elements decltype, j = self._scan_name(j, i) if j < 0: return j if decltype == "doctype": self._decl_otherchars = '' while j < n: c = rawdata[j] if c == ">": # end of declaration syntax data = rawdata[i+2:j] if decltype == "doctype": self.handle_decl(data) else: # According to the HTML5 specs sections "8.2.4.44 Bogus # comment state" and "8.2.4.45 Markup declaration open # state", a comment token should be emitted. # Calling unknown_decl provides more flexibility though. self.unknown_decl(data) return j + 1 if c in "\"'": m = _declstringlit_match(rawdata, j) if not m: return -1 # incomplete j = m.end() elif c in "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ": name, j = self._scan_name(j, i) elif c in self._decl_otherchars: j = j + 1 elif c == "[": # this could be handled in a separate doctype parser if decltype == "doctype": j = self._parse_doctype_subset(j + 1, i) elif decltype in {"attlist", "linktype", "link", "element"}: # must tolerate []'d groups in a content model in an element declaration # also in data attribute specifications of attlist declaration # also link type declaration subsets in linktype declarations # also link attribute specification lists in link declarations self.error("unsupported '[' char in %s declaration" % decltype) else: self.error("unexpected '[' char in declaration") else: self.error( "unexpected %r char in declaration" % rawdata[j]) if j < 0: return j return -1 # incomplete # Internal -- parse a marked section # Override this to handle MS-word extension syntax <![if word]>content<![endif]> def parse_marked_section(self, i, report=1): rawdata= self.rawdata assert rawdata[i:i+3] == '<![', "unexpected call to parse_marked_section()" sectName, j = self._scan_name( i+3, i ) if j < 0: return j if sectName in {"temp", "cdata", "ignore", "include", "rcdata"}: # look for standard ]]> ending match= _markedsectionclose.search(rawdata, i+3) elif sectName in {"if", "else", "endif"}: # look for MS Office ]> ending match= _msmarkedsectionclose.search(rawdata, i+3) else: self.error('unknown status keyword %r in marked section' % rawdata[i+3:j]) if not match: return -1 if report: j = match.start(0) self.unknown_decl(rawdata[i+3: j]) return match.end(0) # Internal -- parse comment, return length or -1 if not terminated def parse_comment(self, i, report=1): rawdata = self.rawdata if rawdata[i:i+4] != '<!--': self.error('unexpected call to parse_comment()') match = _commentclose.search(rawdata, i+4) if not match: return -1 if report: j = match.start(0) self.handle_comment(rawdata[i+4: j]) return match.end(0) # Internal -- scan past the internal subset in a <!DOCTYPE declaration, # returning the index just past any whitespace following the trailing ']'. def _parse_doctype_subset(self, i, declstartpos): rawdata = self.rawdata n = len(rawdata) j = i while j < n: c = rawdata[j] if c == "<": s = rawdata[j:j+2] if s == "<": # end of buffer; incomplete return -1 if s != "<!": self.updatepos(declstartpos, j + 1) self.error("unexpected char in internal subset (in %r)" % s) if (j + 2) == n: # end of buffer; incomplete return -1 if (j + 4) > n: # end of buffer; incomplete return -1 if rawdata[j:j+4] == "<!--": j = self.parse_comment(j, report=0) if j < 0: return j continue name, j = self._scan_name(j + 2, declstartpos) if j == -1: return -1 if name not in {"attlist", "element", "entity", "notation"}: self.updatepos(declstartpos, j + 2) self.error( "unknown declaration %r in internal subset" % name) # handle the individual names meth = getattr(self, "_parse_doctype_" + name) j = meth(j, declstartpos) if j < 0: return j elif c == "%": # parameter entity reference if (j + 1) == n: # end of buffer; incomplete return -1 s, j = self._scan_name(j + 1, declstartpos) if j < 0: return j if rawdata[j] == ";": j = j + 1 elif c == "]": j = j + 1 while j < n and rawdata[j].isspace(): j = j + 1 if j < n: if rawdata[j] == ">": return j self.updatepos(declstartpos, j) self.error("unexpected char after internal subset") else: return -1 elif c.isspace(): j = j + 1 else: self.updatepos(declstartpos, j) self.error("unexpected char %r in internal subset" % c) # end of buffer reached return -1 # Internal -- scan past <!ELEMENT declarations def _parse_doctype_element(self, i, declstartpos): name, j = self._scan_name(i, declstartpos) if j == -1: return -1 # style content model; just skip until '>' rawdata = self.rawdata if '>' in rawdata[j:]: return rawdata.find(">", j) + 1 return -1 # Internal -- scan past <!ATTLIST declarations def _parse_doctype_attlist(self, i, declstartpos): rawdata = self.rawdata name, j = self._scan_name(i, declstartpos) c = rawdata[j:j+1] if c == "": return -1 if c == ">": return j + 1 while 1: # scan a series of attribute descriptions; simplified: # name type [value] [#constraint] name, j = self._scan_name(j, declstartpos) if j < 0: return j c = rawdata[j:j+1] if c == "": return -1 if c == "(": # an enumerated type; look for ')' if ")" in rawdata[j:]: j = rawdata.find(")", j) + 1 else: return -1 while rawdata[j:j+1].isspace(): j = j + 1 if not rawdata[j:]: # end of buffer, incomplete return -1 else: name, j = self._scan_name(j, declstartpos) c = rawdata[j:j+1] if not c: return -1 if c in "'\"": m = _declstringlit_match(rawdata, j) if m: j = m.end() else: return -1 c = rawdata[j:j+1] if not c: return -1 if c == "#": if rawdata[j:] == "#": # end of buffer return -1 name, j = self._scan_name(j + 1, declstartpos) if j < 0: return j c = rawdata[j:j+1] if not c: return -1 if c == '>': # all done return j + 1 # Internal -- scan past <!NOTATION declarations def _parse_doctype_notation(self, i, declstartpos): name, j = self._scan_name(i, declstartpos) if j < 0: return j rawdata = self.rawdata while 1: c = rawdata[j:j+1] if not c: # end of buffer; incomplete return -1 if c == '>': return j + 1 if c in "'\"": m = _declstringlit_match(rawdata, j) if not m: return -1 j = m.end() else: name, j = self._scan_name(j, declstartpos) if j < 0: return j # Internal -- scan past <!ENTITY declarations def _parse_doctype_entity(self, i, declstartpos): rawdata = self.rawdata if rawdata[i:i+1] == "%": j = i + 1 while 1: c = rawdata[j:j+1] if not c: return -1 if c.isspace(): j = j + 1 else: break else: j = i name, j = self._scan_name(j, declstartpos) if j < 0: return j while 1: c = self.rawdata[j:j+1] if not c: return -1 if c in "'\"": m = _declstringlit_match(rawdata, j) if m: j = m.end() else: return -1 # incomplete elif c == ">": return j + 1 else: name, j = self._scan_name(j, declstartpos) if j < 0: return j # Internal -- scan a name token and the new position and the token, or # return -1 if we've reached the end of the buffer. def _scan_name(self, i, declstartpos): rawdata = self.rawdata n = len(rawdata) if i == n: return None, -1 m = _declname_match(rawdata, i) if m: s = m.group() name = s.strip() if (i + len(s)) == n: return None, -1 # end of buffer return name.lower(), m.end() else: self.updatepos(declstartpos, i) self.error("expected name token at %r" % rawdata[declstartpos:declstartpos+20]) # To be overridden -- handlers for unknown objects def unknown_decl(self, data): pass

RE-INVENTING THE TELEVISION NEWS BUSINESS*

A revolution in video storytelling

Creating entirely new & cost-effective production methods

From the world leaders in video production training and the creators of Character Driven Storytelling™

*and every other business that uses video

WHAT WE DO

Over the past 35 years, we have designed, built or restructured some of the most powerful news and journalism companies in the world.

We replace the traditional TV news ‘crew’ with one highly trained journalist, working alone with nothing but an iPhone.

No more TV news ‘crews’, no editors and no field producers.

This is television news done the way newspaper journalism is done – one reporter with their electronic pad and pencil.

In doing this, we can cut the cost of production by as much as 75% while increasing ratings and audience engagement.

In the place of conventional TV news ‘packages’ – ie, reporter stand up, interview, b-roll, man on the street, we marry great journalism with Netflix and Hollywood storytelling.

It’s a combination that works.

We have taken most of our clients to #1 in their respective markets.

And it’s not just for news. Any company, any profit, any NGO and anyone else who is online needs to tell their story in compelling yet cost-effective video. We can teach you to do that. Either in person or virtually.

EXAMPLES OF WHAT WE CAN TEACH YOUR STAFF TO PRODUCE

ITAY HOD

Itay Hod, MMJ with KPIX/CBS in San Francisco, took the 5-Day Intensive Video Storytelling Bootcamp in 2018.

Because he works alone, with only an iPhone, he was able to embed himself with a homeless family.

Here’s the story he produced in a one-day turn.

KIET DO

Kiet Do, an MMJ with KPIX/CBS in San Francisco, took the 5-Day Intensive Video Storytelling Bootcamp in 2021.

Here is a story he produced, all on his own, with only an iPhone and in a one-day turn.

TAYLOR SCHAUB

Taylor Schaub, an MMJ with Spectrum News 1 in LA, took the 5-Day Intensive Video Storytelling Bootcamp in 2023.

Here is a story he turned in only one day, using only an iPhone. It was the first video story he ever did and it was nominated for an Emmy.

THE BOOTCAMP

How do we convert stations and whole networks to working in this way?

Since 1988, we have run intensive 5-Day Video Storytelling Bootcamps

We have done these all over the world.

These are hands-on bootcamps, and participants learn an entirely new way of creating TV news stories.

-We shoot at a 3:1 ratio or lower, so turnaround times are fast.

-We go directly from camera to timelilne and edit – no written scripts. We work in the medium of pictures and sound.

-We are entirely character-driven.

-We are driven by pictures and real events.

-We are focused almost entirely on ’the viewer experience’.

Since 1988, more than 70,000 journalists around the world have taken our bootcamps, either in person on virtualy.

Case Studies

CBS News

We have started to work with CBS News, bringing our ideas of character-driven storytelling to one of the most successful and biggest networks in the United States. Since beginning to work with them ratings have climbed and more importantly, audience engagement is through the ceiling.

Learn More

New York Times Television

We started New York Times Television in 1990 and it was the first paper to be brought into the world of TV. It quickly became one of the most successful non-fiction production companies in the United States. The series and documentaries we produced won many awards including multiple Emmys.

Learn More

The BBC

We have been working with the BBC since the year 2000 helping to convert their national news network to our visual storytelling technique. Most recently we have trained teams from their sports, documentaries, and comedy divisions to make character-driven stories using only smartphones.

Learn More

Spectrum News

For the past five years we have worked with Spectrum News to introduce and train their journalists on visual, character driven storytelling using smartphones helping to create a different kind of local news for their network of 24-Hour News Stations across the United States.

Learn More

The United Nations

In 2006, we were approached by the United Nations. Rather than rely on news outlets, it would be much easier to train the field operatives to produce their own stories. We spent two years working with the UN, training more than 100 of their staff in bootcamps in Geneva and Nairobi.

Learn More

The Newark Star-Ledger

We trained 50 print reporters at the paper to shoot and tell their own stories, in conjunction with their print work. We built a TV newsroom in their existing print newsroom – you could not ask for a better set and they began to live stream their stories in conjunction with their print work.

Learn More

Mcgraw Hill

We spent two years with McGraw Hill, training more than 150 of their staffers, making them completely video literate. McGraw/Hill media properties we transit included Business Week, Aviation Week, (what was the name of the architecture magazine), and JD Power and Associates.

Learn More

Voice of America

In 1990, we were approached by The Voice of America, the official broadcasting agency for the United States Government. When we met with VOA, they were only a short wave radio broadcaster, but working with them, we took them into television, launching VOA-TV.

Learn More

Oyster Yachts

British based Oyster Yachts makes some of the finest yachts in the world. Like every other company, they had to find a way to feed the never-ending video demands of social media – sites like Instagram and TikTok. We trained the Oyster staff to tell their own stories, using only iPhones.

Learn More

Scottish Environmental Protection Agency

We were approached by SEPA, the Scottish Environmental Protection Agency because they had to continually find a way to ‘feed the media beast’. The result was that SEPA was able to tell their own stories, whenever they wanted, and at almost no additional cost.

Learn More

Michael on Media

Michael Rosenblum has been writing about the media since 1988. His work and ideas have appeared in The Guardian, The Huffington Post, Ilkeston Life and many other publications.

He has been blogging regularly for the past 35 years on this subject. Having taught media studies at Columbia University, NYU and now the University of Oxford, he is considered an expert on this subject.

Continue reading this post or look back at previous posts.

Do You Have Questions About Learning Video Skills?

If you would like to know more about our courses contact us and one of our training advisors will be happy to call you.

Your IP : 216.73.216.134

RE-INVENTING THE TELEVISION NEWS BUSINESS*

A revolution in video storytelling

Creating entirely new & cost-effective production methods

From the world leaders in video production training and the creators of Character Driven Storytelling™

*and every other business that uses video

WHAT WE DO

Over the past 35 years, we have designed, built or restructured some of the most powerful news and journalism companies in the world.

We replace the traditional TV news ‘crew’ with one highly trained journalist, working alone with nothing but an iPhone.

No more TV news ‘crews’, no editors and no field producers.

This is television news done the way newspaper journalism is done – one reporter with their electronic pad and pencil.

In doing this, we can cut the cost of production by as much as 75% while increasing ratings and audience engagement.

In the place of conventional TV news ‘packages’ – ie, reporter stand up, interview, b-roll, man on the street, we marry great journalism with Netflix and Hollywood storytelling.

It’s a combination that works.

We have taken most of our clients to #1 in their respective markets.

And it’s not just for news. Any company, any profit, any NGO and anyone else who is online needs to tell their story in compelling yet cost-effective video. We can teach you to do that. Either in person or virtually.

EXAMPLES OF WHAT WE CAN TEACH YOUR STAFF TO PRODUCE

ITAY HOD

Itay Hod, MMJ with KPIX/CBS in San Francisco, took the 5-Day Intensive Video Storytelling Bootcamp in 2018.

Because he works alone, with only an iPhone, he was able to embed himself with a homeless family.

Here’s the story he produced in a one-day turn.

KIET DO

Kiet Do, an MMJ with KPIX/CBS in San Francisco, took the 5-Day Intensive Video Storytelling Bootcamp in 2021.

Here is a story he produced, all on his own, with only an iPhone and in a one-day turn.

TAYLOR SCHAUB

Taylor Schaub, an MMJ with Spectrum News 1 in LA, took the 5-Day Intensive Video Storytelling Bootcamp in 2023.

Here is a story he turned in only one day, using only an iPhone. It was the first video story he ever did and it was nominated for an Emmy.

THE BOOTCAMP

How do we convert stations and whole networks to working in this way?

Since 1988, we have run intensive 5-Day Video Storytelling Bootcamps

We have done these all over the world.

These are hands-on bootcamps, and participants learn an entirely new way of creating TV news stories.

-We shoot at a 3:1 ratio or lower, so turnaround times are fast.

-We go directly from camera to timelilne and edit – no written scripts. We work in the medium of pictures and sound.

-We are entirely character-driven.

-We are driven by pictures and real events.

-We are focused almost entirely on ’the viewer experience’.

Since 1988, more than 70,000 journalists around the world have taken our bootcamps, either in person on virtualy.

Case Studies

CBS News

New York Times Television

The BBC

Spectrum News

The United Nations

The Newark Star-Ledger

Mcgraw Hill

Voice of America

Oyster Yachts

Scottish Environmental Protection Agency

Michael on Media