| 20 | significant_attrs = ["alt", "href", "src", "title"] |
| 21 | whitespace_re = re.compile(r"\s+") |
| 22 | class MyHTMLParser(HTMLParser): |
| 23 | def __init__(self): |
| 24 | HTMLParser.__init__(self) |
| 25 | self.convert_charrefs = False |
| 26 | self.last = "starttag" |
| 27 | self.in_pre = False |
| 28 | self.output = "" |
| 29 | self.last_tag = "" |
| 30 | def handle_data(self, data): |
| 31 | after_tag = self.last == "endtag" or self.last == "starttag" |
| 32 | after_block_tag = after_tag and self.is_block_tag(self.last_tag) |
| 33 | if after_tag and self.last_tag == "br": |
| 34 | data = data.lstrip('\n') |
| 35 | if not self.in_pre: |
| 36 | data = whitespace_re.sub(' ', data) |
| 37 | if after_block_tag and not self.in_pre: |
| 38 | if self.last == "starttag": |
| 39 | data = data.lstrip() |
| 40 | elif self.last == "endtag": |
| 41 | data = data.strip() |
| 42 | self.output += data |
| 43 | self.last = "data" |
| 44 | def handle_endtag(self, tag): |
| 45 | if tag == "pre": |
| 46 | self.in_pre = False |
| 47 | elif self.is_block_tag(tag): |
| 48 | self.output = self.output.rstrip() |
| 49 | self.output += "</" + tag + ">" |
| 50 | self.last_tag = tag |
| 51 | self.last = "endtag" |
| 52 | def handle_starttag(self, tag, attrs): |
| 53 | if tag == "pre": |
| 54 | self.in_pre = True |
| 55 | if self.is_block_tag(tag): |
| 56 | self.output = self.output.rstrip() |
| 57 | self.output += "<" + tag |
| 58 | # For now we don't strip out 'extra' attributes, because of |
| 59 | # raw HTML test cases. |
| 60 | # attrs = filter(lambda attr: attr[0] in significant_attrs, attrs) |
| 61 | if attrs: |
| 62 | attrs.sort() |
| 63 | for (k,v) in attrs: |
| 64 | self.output += " " + k |
| 65 | if v in ['href','src']: |
| 66 | self.output += ("=" + '"' + |
| 67 | urllib.quote(urllib.unquote(v), safe='/') + '"') |
| 68 | elif v != None: |
| 69 | self.output += ("=" + '"' + html.escape(v,quote=True) + '"') |
| 70 | self.output += ">" |
| 71 | self.last_tag = tag |
| 72 | self.last = "starttag" |
| 73 | def handle_startendtag(self, tag, attrs): |
| 74 | """Ignore closing tag for self-closing """ |
| 75 | self.handle_starttag(tag, attrs) |
| 76 | self.last_tag = tag |
| 77 | self.last = "endtag" |
| 78 | def handle_comment(self, data): |
| 79 | self.output += '<!--' + data + '-->' |