Skip to content

Commit aec6a33

Browse files
committed
flake8 cleanups dehtml.py
Note you need to disable long lines as there is a test example that requires really long lines of htmlized output.
1 parent 5b006ef commit aec6a33

File tree

1 file changed

+20
-18
lines changed

1 file changed

+20
-18
lines changed

roundup/dehtml.py

Lines changed: 20 additions & 18 deletions
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,8 @@
11

22
from __future__ import print_function
33
from roundup.anypy.strings import u2s, uchr
4+
5+
46
class dehtml:
57
def __init__(self, converter):
68
if converter == "none":
@@ -11,6 +13,7 @@ def __init__(self, converter):
1113
if converter == "beautifulsoup":
1214
# Not as well tested as dehtml.
1315
from bs4 import BeautifulSoup
16+
1417
def html2text(html):
1518
soup = BeautifulSoup(html)
1619

@@ -22,62 +25,62 @@ def html2text(html):
2225

2326
self.html2text = html2text
2427
else:
25-
raise ImportError # use
28+
raise ImportError
2629
except ImportError:
2730
# use the fallback below if beautiful soup is not installed.
2831
try:
2932
# Python 3+.
3033
from html.parser import HTMLParser
3134
from html.entities import name2codepoint
32-
pyver=3
35+
pyver = 3
3336
except ImportError:
3437
# Python 2.
3538
from HTMLParser import HTMLParser
3639
from htmlentitydefs import name2codepoint
37-
pyver=2
40+
pyver = 2
3841

3942
class DumbHTMLParser(HTMLParser):
4043
# class attribute
41-
text=""
44+
text = ""
4245

4346
# internal state variable
4447
_skip_data = False
4548
_last_empty = False
4649

4750
def handle_data(self, data):
48-
if self._skip_data: # skip data if in script or style block
51+
if self._skip_data: # skip data in script or style block
4952
return
5053

51-
if ( data.strip() == ""):
54+
if (data.strip() == ""):
5255
# reduce multiple blank lines to 1
53-
if ( self._last_empty ):
56+
if (self._last_empty):
5457
return
5558
else:
5659
self._last_empty = True
5760
else:
5861
self._last_empty = False
5962

60-
self.text=self.text + data
63+
self.text = self.text + data
6164

6265
def handle_starttag(self, tag, attrs):
63-
if (tag == "p" ):
64-
self.text= self.text + "\n"
65-
if (tag in ("style", "script")):
66+
if (tag == "p"):
67+
self.text = self.text + "\n"
68+
if (tag in ("style", "script")):
6669
self._skip_data = True
6770

6871
def handle_endtag(self, tag):
69-
if (tag in ("style", "script")):
72+
if (tag in ("style", "script")):
7073
self._skip_data = False
7174

7275
def handle_entityref(self, name):
7376
if self._skip_data:
7477
return
7578
c = uchr(name2codepoint[name])
7679
try:
77-
self.text= self.text + c
80+
self.text = self.text + c
7881
except UnicodeEncodeError:
7982
# print a space as a placeholder
80-
self.text= self.text + ' '
83+
self.text = self.text + ' '
8184

8285
def html2text(html):
8386
if pyver == 3:
@@ -90,8 +93,9 @@ def html2text(html):
9093

9194
self.html2text = html2text
9295

96+
9397
if "__main__" == __name__:
94-
html='''
98+
html = '''
9599
<body>
96100
<script>
97101
this must not be in output
@@ -152,12 +156,10 @@ def html2text(html):
152156
if html2text:
153157
print(html2text(html))
154158
except NameError as e:
155-
print("captured error %s"%e)
159+
print("captured error %s" % e)
156160

157161
html2text = dehtml("none").html2text
158162
if html2text:
159163
print("FAIL: Error, dehtml(none) is returning a function")
160164
else:
161165
print("PASS: dehtml(none) is returning None")
162-
163-

0 commit comments

Comments
 (0)