[fix] pep/flake8 compatibility

This commit is contained in:
asciimoo 2014-01-20 02:31:20 +01:00
parent 692c0bf5f0
commit b2492c94f4
23 changed files with 197 additions and 109 deletions

View file

@ -1,14 +1,15 @@
from HTMLParser import HTMLParser
#import htmlentitydefs
import csv
import codecs
from codecs import getincrementalencoder
import cStringIO
import re
def gen_useragent():
# TODO
return "Mozilla/5.0 (X11; Linux x86_64; rv:26.0) Gecko/20100101 Firefox/26.0"
ua = "Mozilla/5.0 (X11; Linux x86_64; rv:26.0) Gecko/20100101 Firefox/26.0"
return ua
def highlight_content(content, query):
@ -46,7 +47,10 @@ class HTMLTextExtractor(HTMLParser):
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)
if number[0] in (u'x', u'X'):
codepoint = int(number[1:], 16)
else:
codepoint = int(number)
self.result.append(unichr(codepoint))
def handle_entityref(self, name):
@ -75,10 +79,16 @@ class UnicodeWriter:
self.queue = cStringIO.StringIO()
self.writer = csv.writer(self.queue, dialect=dialect, **kwds)
self.stream = f
self.encoder = codecs.getincrementalencoder(encoding)()
self.encoder = 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])
unicode_row = []
for col in row:
if type(col) == str or type(col) == unicode:
unicode_row.append(col.encode('utf-8').strip())
else:
unicode_row.append(col)
self.writer.writerow(unicode_row)
# Fetch UTF-8 output from the queue ...
data = self.queue.getvalue()
data = data.decode("utf-8")