60 lines
1.7 KiB
Python
60 lines
1.7 KiB
Python
from HTMLParser import HTMLParser
|
|
import htmlentitydefs
|
|
import csv
|
|
import codecs
|
|
import cStringIO
|
|
|
|
class HTMLTextExtractor(HTMLParser):
|
|
def __init__(self):
|
|
HTMLParser.__init__(self)
|
|
self.result = [ ]
|
|
|
|
def handle_data(self, d):
|
|
self.result.append(d)
|
|
|
|
def handle_charref(self, number):
|
|
codepoint = int(number[1:], 16) if number[0] in (u'x', u'X') else int(number)
|
|
self.result.append(unichr(codepoint))
|
|
|
|
def handle_entityref(self, name):
|
|
codepoint = htmlentitydefs.name2codepoint[name]
|
|
self.result.append(unichr(codepoint))
|
|
|
|
def get_text(self):
|
|
return u''.join(self.result)
|
|
|
|
def html_to_text(html):
|
|
s = HTMLTextExtractor()
|
|
s.feed(html)
|
|
return s.get_text()
|
|
|
|
|
|
class UnicodeWriter:
|
|
"""
|
|
A CSV writer which will write rows to CSV file "f",
|
|
which is encoded in the given encoding.
|
|
"""
|
|
|
|
def __init__(self, f, dialect=csv.excel, encoding="utf-8", **kwds):
|
|
# Redirect output to a queue
|
|
self.queue = cStringIO.StringIO()
|
|
self.writer = csv.writer(self.queue, dialect=dialect, **kwds)
|
|
self.stream = f
|
|
self.encoder = codecs.getincrementalencoder(encoding)()
|
|
|
|
def writerow(self, row):
|
|
self.writer.writerow([(s.encode("utf-8").strip() if type(s) == str or type(s) == unicode else str(s)) for s in row])
|
|
# Fetch UTF-8 output from the queue ...
|
|
data = self.queue.getvalue()
|
|
data = data.decode("utf-8")
|
|
# ... and reencode it into the target encoding
|
|
data = self.encoder.encode(data)
|
|
# write to the target stream
|
|
self.stream.write(data)
|
|
# empty queue
|
|
self.queue.truncate(0)
|
|
|
|
def writerows(self, rows):
|
|
for row in rows:
|
|
self.writerow(row)
|