def unescapeHTML(s): if '&' in s: p = htmllib.HTMLParser(None) p.save_bgn() p.feed(s) return p.save_end() return s
def format(self, text): writer = SimpleWriter() format = formatter.AbstractFormatter(writer) parser = htmllib.HTMLParser(format) parser.feed(text) parser.close() return writer
def unescape(self, s):
"""解码html转义"""
p = htmllib.HTMLParser(None)
p.save_bgn()
p.feed(s)
return p.save_end()
def unescape(s):
if not s:
return s
p = htmllib.HTMLParser(None)
p.save_bgn()
p.feed(s)
return p.save_end()
def prep_text(intext):
intext = intext.replace("\\r", ' ') #get rid of the line returns
#convert the entities back into characters
p = htmllib.HTMLParser(None)
p.save_bgn()
p.feed(intext)
return p.save_end()
def __get_unescape_u(text_u):
"""get unesace unicode html"""
html_parser = htmllib.HTMLParser(None)
html_parser.save_bgn()
html_parser.feed(text_u)
unescaped_u = html_parser.save_end()
return unescaped_u
def unescape_entities(html_string):
"""Removes HTML or XML character references and entities
from a html string (see http://wiki.python.org/moin/EscapingHtml)"""
parser = htmllib.HTMLParser(None)
parser.save_bgn()
parser.feed(html_string.encode("iso8859-1"))
return parser.save_end()
def create_html_mail(subject,
html,
text=None,
from_addr=None,
to_addr=None,
headers=None,
encoding='UTF-8'):
"""Create a mime-message that will render HTML in popular
MUAs, text in better ones.
"""
# Use DumbWriters word wrapping to ensure that no text line
# is longer than plain_text_maxcols characters.
plain_text_maxcols = 72
html = html.encode(encoding)
if text is None:
# Produce an approximate textual rendering of the HTML string,
# unless you have been given a better version as an argument
textout = StringIO.StringIO()
formtext = formatter.AbstractFormatter(
formatter.DumbWriter(textout, plain_text_maxcols))
parser = htmllib.HTMLParser(formtext)
parser.feed(html)
parser.close()
# append the anchorlist at the bottom of a message
# to keep the message readable.
counter = 0
anchorlist = "\n\n" + ("-" * plain_text_maxcols) + "\n\n"
for item in parser.anchorlist:
counter += 1
anchorlist += "[%d] %s\n" % (counter, item)
text = textout.getvalue() + anchorlist
del textout, formtext, parser, anchorlist
else:
text = text.encode(encoding)
# if we would like to include images in future, there should
# probably be 'related' instead of 'mixed'
msg = MIMEMultipart('mixed')
# maybe later :) msg['From'] = Header("%s <%s>" %
# (send_from_name, send_from), encoding)
msg['Subject'] = Header(subject, encoding)
msg['From'] = from_addr
msg['To'] = to_addr
msg['Date'] = formatdate(localtime=True)
msg["Message-ID"] = email.Utils.make_msgid()
if headers:
for key, value in headers.items():
msg[key] = value
msg.preamble = 'This is a multi-part message in MIME format.'
alternatives = MIMEMultipart('alternative')
msg.attach(alternatives)
alternatives.attach(MIMEText(text, 'plain', _charset=encoding))
alternatives.attach(MIMEText(html, 'html', _charset=encoding))
return msg
def parse(self):
# We're using the parser just to get the HREFs
# We should also use it to e.g. respect <META NOFOLLOW>
w = formatter.DumbWriter(StringIO())
f = formatter.AbstractFormatter(w)
self.parser = htmllib.HTMLParser(f)
self.parser.feed(self.body)
self.parser.close()
def unescapeHTML(s):
if reHTMLEscape.search(s) is not None:
p = htmllib.HTMLParser(None)
p.save_bgn()
p.feed(s)
return p.save_end()
else:
return s
def unescape(s):
"""
remplace les sequences d'echappement par leurs caracteres equivalent
"""
p = htmllib.HTMLParser(None)
p.save_bgn()
p.feed(s)
return p.save_end()
def find_links(html):
"""return list of links in HTML"""
writer = formatter.DumbWriter(StringIO())
f = formatter.AbstractFormatter(writer)
parser = htmllib.HTMLParser(f)
parser.feed(html)
parser.close()
return parser.anchorlist
def extract(self,htmldata, docno,url):
try:
parser = htmllib.HTMLParser(formatter.NullFormatter())
parser.feed(htmldata)
return parser.anchorlist
except Exception,ex:
pass
return []
def getLinkByHTML2(html):
format = formatter.AbstractFormatter(formatter.NullWriter())
ptext = htmllib.HTMLParser(format)
ptext.feed(html)
for link in ptext.anchorlist:
print(link)
return link
return ""
def unescape(s):
p = htmllib.HTMLParser(None)
p.save_bgn()
try:
p.feed(s)
except:
return s
return p.save_end()
def html2txt(htmlblock):
import htmllib, formatter, StringIO
s = StringIO.StringIO('')
w = formatter.DumbWriter(s)
f = formatter.AbstractFormatter(w)
p = htmllib.HTMLParser(f)
p.feed(htmlblock)
return s.getvalue().strip()
def unescape(s):
p = htmllib.HTMLParser(formatter.NullFormatter() )
# we need to preserve line breaks, nofill makes sure we don't
# loose them
p.nofill = True
p.save_bgn()
p.feed(s)
return p.save_end().strip()
def unescape(s):
p = htmllib.HTMLParser(None)
p.save_bgn()
try:
p.feed(s)
except:
raise ValueError(s)
return p.save_end()
def get_data(self):
'''
Download data from Weather Underground website for a given stationid
, a startyar, and an endyear. The html file is parsed and written
as csv to a separate txt file for each day.
[singleprocessing code, deprecated]
'''
logger.info('Download data for stationid: ' + self.stationid +
' [start]')
for td in utils.progressbar(range(0, (self.enddate - self.startdate)
.days + 1), "Downloading: ", 60):
# increase the date by 1 day for the next download
current_date = self.startdate + timedelta(days=td)
# set download url
url = 'http://www.wunderground.com/weatherstation/WXDailyHistory.asp?ID=' + \
self.stationid + '&day=' + str(current_date.day) + '&year=' + \
str(current_date.year) + '&month=' + \
str(current_date.month) + '&format=1'
# define outputfile
outputfile = self.stationid + '_' + str(current_date.year) \
+ str(current_date.month).zfill(2) + \
str(current_date.day).zfill(2) + '.txt'
# check if we want to keep previous downloaded files
if self.keep:
if os.path.exists(os.path.join(self.outputdir, outputfile)):
# check if filesize is not null
if os.path.getsize(os.path.join(self.outputdir,
outputfile)) > 0:
# file exists and is not null, continue next iteration
continue
else:
# file exists but is null, so remove and redownload
os.remove(os.path.join(self.outputdir, outputfile))
elif os.path.exists(os.path.join(self.outputdir, outputfile)):
os.remove(os.path.join(self.outputdir, outputfile))
# open outputfile
with open(os.path.join(self.outputdir, outputfile),
'wb') as outfile:
# open and read the url
handler = urllib2.urlopen(url)
content = handler.read()
# convert spaces to non-breaking spaces
content = content.replace(' ', ' ')
# Removing all the HTML tags from the file
outstream = cStringIO.StringIO()
parser = htmllib.HTMLParser(
formatter.AbstractFormatter(
formatter.DumbWriter(outstream)))
parser.feed(content)
# convert spaces back to regular whitespace (' ')
content = outstream.getvalue().replace('\xa0', ' ')
# write output
outfile.write(content)
# close handler and outstream
outstream.close()
handler.close()
logger.info('Download data for stationid: ' + self.stationid +
' [completed]')
def getLinks():
website = urllib2.urlopen("http://www.profmcmmillan.com")
data = website.read()
website.close()
Format = formatter.AbstractFormatter(formatter.NullWriter())
ptext = htmllib.HTMLParser(Format)
ptext.feed(data)
for link in ptext.anchorlist:
print link
def textFromHtml(self, html):
textout = cStringIO.StringIO()
formtext = formatter.AbstractFormatter(formatter.DumbWriter(textout))
parser = htmllib.HTMLParser(formtext)
parser.feed(html)
parser.close()
text = textout.getvalue()
del textout, formtext, parser
return text
def find_links(html):
"""Return a list of links in html."""
# We're using the parser just to get the HREFs
writer = formatter.DumbWriter(StringIO())
f = formatter.AbstractFormatter(writer)
parser = htmllib.HTMLParser(f)
parser.feed(html)
parser.close()
return parser.anchorlist
def unescape(self, s):
"""Quick and dirty unescaping."""
s = s.replace(" ","")
p = htmllib.HTMLParser(None)
p.save_bgn()
p.feed(s)
return p.save_end()
def decodeHTMLCharacterEntities(self, code):
#print code
outputstring = StringIO.StringIO()
w = formatter.DumbWriter(outputstring, maxcol=9999999) # plain text
f = formatter.AbstractFormatter(w)
p = htmllib.HTMLParser(f)
p.feed(code)
p.close()
#print outputstring.getvalue()
return (outputstring.getvalue())
def unescape(s):
"""http://wiki.python.org/moin/EscapingHtml
Example:
>>> unescape("Norwegian<>Polish Dictionar TR'App")
>>> Norwegian<>Polish Dictionar TR'App
"""
_htmlParser = htmllib.HTMLParser(None)
_htmlParser.save_bgn()
_htmlParser.feed(s)
return _htmlParser.save_end()
def parse_links(self):
'Parse out the links found in downloaded HTML file'
f = open(self.file, 'r')
data = f.read()
f.close()
parser = htmllib.HTMLParser(
formatter.AbstractFormatter(formatter.DumbWriter(io.StringIO())))
parser.feed(data)
parser.close()
return parser.anchorlist
def parse_links(self): #解析刚下载下来的页面链接
f = open(self.file, 'r') #读取下载的页面
data = f.read()
f.close()
parser = htmllib.HTMLParser(
formatter.AbstractFormatter( #AbstractFormatter用来解析数据
formatter.DumbWriter(cStringIO.StringIO()))
) #DumbWriter用来输出内容，cStringIO保障不输出到标准输出（最好输出到文件）
parser.feed(data)
parser.close()
return parser.anchorlist #返回解析后的列表
def get_extra_information(self):
text = ""
if self.diff:
self.diff = self.escape(self.diff)
outstream = cStringIO.StringIO()
p = htmllib.HTMLParser(
formatter.AbstractFormatter(formatter.DumbWriter(outstream)))
p.feed(self.diff)
self.diff = outstream.getvalue()
outstream.close()
text = self.diff.replace("&", "&")
return text
def unescape(self, s):
p = htmllib.HTMLParser(None)
p.save_bgn()
p.feed(str(s))
s = p.save_end()
#~ s = s.replace('<','<')
#~ s = s.replace('>','>')
s = s.replace(' rel="nofollow"', '')
#~ s = s.replace('"e;','"')
s = s.replace('&', '%26')
s = s.replace('[1]', '')
return s
def pretty_print(self):
"""Print a pretty (formatted) version of the HTML content.
If the content is not text/html then it is just printed.
"""
if not self.headers['content-type'].lower().startswith('text/html'):
print self.contents
else:
parser = htmllib.HTMLParser(
formatter.AbstractFormatter(formatter.DumbWriter()))
parser.feed(self.contents)
parser.close()
