def content(path, contentpage, output):
parser = TocHlpHtmlParser(AbstractFormatter(AlmostNullWriter()),
path, output)
f = open(path + '/' + contentpage)
parser.feed(f.read())
parser.close()
f.close()
def rewrite_htmlinclude(match, include_dir, quietly):
file_path = os.path.join(include_dir, match.group(1))
trailing_char = match.group(2)
if not valid_file(file_path):
if not quietly:
print("Warning: unable to expand @htmlinclude '" + match.group(1) + "'")
return ''
# First, try to see if there's a .txt version. If so, use that.
txt_file = re.sub(r'html', 'txt', file_path, re.IGNORECASE)
if valid_file(txt_file):
contents = read_file_contents(txt_file)
return rewrite_included_contents(contents) + trailing_char
else: # No txt file; proceed with .html file.
file = open(file_path, 'r')
writer = RewritePydocStringWriter()
parser = RewritePydocHTMLParser(AbstractFormatter(writer))
parser.feed(file.read())
parser.close()
file.close()
return rewrite_included_contents(writer.get_text()) + trailing_char
def __init__(self, writer, settings, context):
if not self._inited:
for k, v in self.fontdingbats.items():
self.dingbats[(k, 'grey')] = v
self.dingbats[(k, 'color')] = v
import Greek
for k, v in Greek.entitydefs.items():
tup = (v, 'Symbol')
self.dingbats[(k, 'grey')] = tup
self.dingbats[(k, 'color')] = tup
PrintingHTMLParser._inited = 1
HTMLParser.__init__(self, AbstractFormatter(writer))
if settings.strict_parsing:
self.sgml_parser.restrict(0)
self._baseurl = context.get_baseurl()
self.context = context
self.settings = settings
if settings.imageflag:
self._image_loader = utils.image_loader
self._image_cache = {}
self._anchors = {None: None}
self._anchor_sequence = []
self._anchor_xforms = []
if not settings.footnoteflag:
self.add_anchor_transform(disallow_anchor_footnotes)
else:
self.add_anchor_transform(
disallow_self_reference(context.get_url()))
self.__fontsize = [3]
def parseAndGetLinks(self):
# 创建一个基本的HTML解释器，可能需要单独一篇文章来说这句
self.parser = HTMLParser(AbstractFormatter(DumbWriter(StringIO())))
# 解析html文件，获取所有的连接（带有href的）
self.parser.feed(open(self.file).read())
self.parser.close()
return self.parser.anchorlist
def parseAndGetLinks(self): # pars HTML, save links
self.parser = HTMLParser(AbstractFormatter( \
DumbWriter(StringIO())))
self.parser.feed(open(self.file).read())
self.parser.close()
print self.parser
return self.parser.anchorlist
def index(path, indexpage, output):
parser = IdxHlpHtmlParser(AbstractFormatter(AlmostNullWriter()),
path, output)
f = open(path + '/' + indexpage)
parser.feed(f.read())
parser.close()
f.close()
def parseAndGetLinks(self):
"""StringIO是从内存中读取数据 DumbWriter将事件流转换为存文本文档 AbstractFormatter 类进行格式化
"""
self.parser = HTMLParser(AbstractFormatter(DumbWriter(StringIO())))
self.parser.feed(open(self.file).read())
self.parser.close()
return self.parser.anchorlist
def insert_read_only_node(c, p, name):
if name == "":
name = g.app.gui.runOpenFileDialog(
c,
title="Open",
filetypes=[("All files", "*")],
)
c.setHeadString(p, "@read-only %s" % name)
c.redraw()
parse = urlparse.urlparse(name)
try:
if parse[0] == 'ftp':
file = FTPurl(name) # FTP URL
elif parse[0] == 'http':
file = urllib.urlopen(name) # HTTP URL
else:
file = open(name, "r") # local file
g.es("..." + name)
new = file.read()
file.close()
except IOError: # as msg:
# g.es("error reading %s: %s" % (name, msg))
# g.es("...not found: " + name)
c.setBodyString(p, "") # Clear the body text.
return True # Mark the node as changed.
else:
ext = os.path.splitext(parse[2])[1]
if ext.lower() in ['.htm', '.html']:
#@+<< convert HTML to text >>
#@+node:edream.110203113231.895: *3* << convert HTML to text >>
fh = StringIO()
fmt = AbstractFormatter(DumbWriter(fh))
# the parser stores parsed data into fh (file-like handle)
parser = HTMLParser(fmt)
# send the HTML text to the parser
parser.feed(new)
parser.close()
# now replace the old string with the parsed text
new = fh.getvalue()
fh.close()
# finally, get the list of hyperlinks and append to the end of the text
hyperlinks = parser.anchorlist
numlinks = len(hyperlinks)
if numlinks > 0:
hyperlist = ['\n\n--Hyperlink list follows--']
for i in range(numlinks):
hyperlist.append("\n[%d]: %s" %
(i + 1, hyperlinks[i])) # 3/26/03: was i.
new = new + ''.join(hyperlist)
#@-<< convert HTML to text >>
previous = p.b
c.setBodyString(p, new)
changed = (g.toUnicode(new) != g.toUnicode(previous))
if changed and previous != "":
g.es("changed: %s" % name) # A real change.
return changed
def parseAndGetLinks(self):
self.parser = HTMLParser(AbstractFormatter(DumbWriter(StringIO())))
try:
self.parser.feed(open(self.file).read())
self.parser.close()
except IOError:
pass
return self.parser.anchorlist
def parse_links(self):
'Parse out the links found in downloaded HTML file'
f = open(self.file, 'r')
data = f.read()
f.close()
parser = HTMLParser(AbstractFormatter(DumbWriter(io.StringIO())))
parser.feed(data)
parser.close()
return parser.anchorlist
def html2text(html):
f = StringIO()
parser = HTMLParser(AbstractFormatter(DumbWriter(f)))
try:
parser.feed(html)
except HTMLParseError:
return ''
else:
parser.close()
return f.getvalue()
def get_text_from_html( html_input ):
"Strip tags and non-ascii characters from HTML input."
my_stringio = StringIO.StringIO() # make an instance of this file-like string thing
p = HTMLParser(AbstractFormatter(DumbWriter(my_stringio)))
try: p.feed(html_input); p.close() #calling close is not usually needed, but let's play it safe
except HTMLParseError: print '***HTML malformed***' #the html is badly malformed (or you found a bug)
#return my_stringio.getvalue().replace('\xa0','')
s = re.sub( r'[^\x00-\x7f]', r' ', my_stringio.getvalue() )
s = s.replace('\r\n',' ').replace('\n',' ')
s = re.sub( ' +', ' ', s )
return s
def parseAndGetLinks(self):
'''解析html页面，获取页面中的链接，并保存链接'''
self.parser = HTMLParser(AbstractFormatter(DumbWriter(StringIO())))
#使用HTMLParser的方法进行处理 , StringIO是从内存中读取数据，DumbWriter将事件流转换为存文本文档。
self.parser.feed(open(self.file).read())
#将self.file文件打开，并一次性读入上面定的文件中
self.parser.close()
print 'self.parser.anchorlist --> ', self.parser.anchorlist
return self.parser.anchorlist #anchorlist 记录href 地址
def email_strip_html(html_content):
"""Strip html tags from html_content, trying to respect formatting."""
html_content = RE_SPACES.sub(' ', html_content)
html_content = RE_NEWLINES.sub('\n', html_content)
html_content = RE_HTML_TAGS.sub('', html_content)
html_content = html_content.split('\n')
out = StringIO()
out_format = AbstractFormatter(DumbWriter(out))
for row in html_content:
out_format.add_flowing_data(row)
out_format.end_paragraph(1)
return out.getvalue()
def test():
import sys
file = 'test.html'
if sys.argv[1:]: file = sys.argv[1]
fp = open(file, 'r')
data = fp.read()
fp.close()
from formatter import NullWriter, AbstractFormatter
w = NullWriter()
f = AbstractFormatter(w)
p = HTMLParser(f)
p.feed(data)
p.close()
def parse_html(self, html):
from StringIO import StringIO
from formatter import (AbstractFormatter, DumbWriter)
from htmllib import HTMLParser
_html = re.sub(self.notrans_tag, r" \1 ", html)
buf = StringIO()
p = HTMLParser(AbstractFormatter(DumbWriter(buf)))
p.feed(_html)
_sub = re.sub(self.whitespaces, " ", buf.getvalue())
# FIXME: how can zerowidth be removed more simply?
_sub = re.sub(self.zerowidth, "", _sub)
_sub = re.sub(self.colon, r"\1", _sub)
return _sub
def parseAndGetLinks(self, html_string):
try:
self.parser = HTMLParser(AbstractFormatter(DumbWriter(StringIO())))
self.parser.feed(html_string)
self.parser.close()
links = []
for eachLink in self.parser.anchorlist:
if eachLink[:4] != "http" and find(eachLink, "://") == -1:
eachLink = urljoin(self.base_url, eachLink)
links.append(eachLink)
return links
except IOError:
return []
def get_plain_from_html(html):
"""extract plain text from html
>>> test_html = "<div><h1>Hey<h1><p>This is some text</p></div>"
>>> get_plain_from_html(test_html)
'\\nHey\\n\\nThis is some text'
"""
from htmllib import HTMLParser # import here to avoid high startup cost
textout = StringIO()
formtext = AbstractFormatter(DumbWriter(textout))
parser = HTMLParser(formtext)
parser.feed(html)
parser.close()
return textout.getvalue()
def extract_from_html(self,
html,
lower_threshold=None,
upper_threshold=None):
# Create an instance of ParsingTracker and pass TextWriter() to collect approrpiate output
self.writer = TextWriter()
formatter = AbstractFormatter(self.writer)
self.parser = ParsingTracker(self.writer, formatter)
if lower_threshold:
self.writer.lower_threshold = lower_threshold
if upper_threshold:
self.writer.upper_threshold = upper_threshold
self.parser.feed(html)
self.parser.close()
return self.writer.output()
def collectURLSFromPage(page):
"""
This returns a list of URLS that come from a certain page.
Useful for spiders. It takes just a string as an argument.
"""
resultList = []
if page == "":
#nothing to parse, so nothing to return
return resultList
#print "Doing form parser"
if page.count("<form") > 0:
otherlist = daveFormParse(page)
for key in otherlist:
resultList.append(key)
pass
#DEBUG
#return resultList
#print "Doing RAW Parser"
spamList = rawParse(page)
for key in spamList:
resultList.append(key)
pass
#This needs to be documented somehow, but I have no idea what it does
try:
parser = HTMLParser(AbstractFormatter(DumbWriter(StringIO())))
parser.feed(page)
parser.close()
except:
#print "DEBUG: Caught an exception trying to parse that html file."
#print "(Not sure why this happens - you'll have to crawl this page manually)"
return resultList
#print "Adding HTML Parser data"
for key in parser.anchorlist:
resultList.append(key)
pass
return resultList
def parseAndGetLinks(self): # parse HTML, save links
self.parser = HTMLParser(AbstractFormatter(DumbWriter(StringIO())))
r = self.download()
if r:
print '________'
try:
try:
s = r.read(50000)
except socket.error as e:
print "***************************socket error***************************", e
return []
self.parser.feed(s)
print '------------------'
r.close()
print '***************************'
except HTMLParseError:
print 'get links error\n'
return []
self.parser.close()
return self.parser.anchorlist
def collectURLSFromPage(page):
resultList = []
#print "Doing form parser"
if page.count("<form") > 0:
otherlist = daveFormParse(page)
for key in otherlist:
resultList.append(key)
pass
#DEBUG
#return resultList
#print "Doing RAW Parser"
spamList = rawParse(page)
for key in spamList:
resultList.append(key)
pass
#the whole "AbstractFormater()" line is a bunch of crap I copied
#That needs to be documented somehow, but I have no idea what it does
try:
parser = HTMLParser(AbstractFormatter(DumbWriter(StringIO())))
parser.feed(page)
parser.close()
except:
#print "DEBUG: Caught an exception trying to parse that html file."
#print "(Not sure why this happens - you'll have to crawl this page manually)"
return resultList
#print "Adding HTML Parser data"
for key in parser.anchorlist:
resultList.append(key)
pass
return resultList
def __init__(self):
HTMLParser.__init__(self, AbstractFormatter(NullWriter()))
self.result = []
self.requires_no_close = ['img', 'br']
def extract(html): mywriter = writer() formatter = AbstractFormatter(mywriter) parser = Parser(mywriter, formatter) parser.feedme(html) parser.close()
def parseAndGetLinks(self): #¿?¿?HTML¿?¿?¿?¿?¿?
self.parser = HTMLParser(AbstractFormatter(DumbWriter(StringIO())))
self.parser.feed(open(self.file).read())
self.parser.close()
return self.parser.anchorlist
def parseAndGetLinks(self): # 解析HTML文档，保存链接 parse html,save links
self.parser = HTMLParser(AbstractFormatter(DumbWriter(StringIO())))
self.parser.feed(open(self.file).read())
self.parser.close()
return self.parser.anchorlist
def html2text(html):
output = StringIO()
writer = DumbWriter(output)
p = HTMLParser(AbstractFormatter(writer))
p.feed(toText(html))
return toText(output.getvalue())
def new_formatter(self):
formatter = AbstractFormatter(self._viewer)
# set parskip to prevent blank line at top of cell if the content
# starts with a <P> or header element.
formatter.parskip = 1
return formatter
def __init__(self, gc):
Coloring.__init__(self, gc, 'help')
self.heading = self.printer('heading', attr='bold')
self.wrap = AbstractFormatter(DumbWriter())
def parseAndGetLinks(self): self.parser = HTMLParser(AbstractFormatter(DumbWriter(StringIO()))) self.parser.feed(urlopen(self.url).read()) self.parser.close() return self.parser.anchorlist
