注：私はPython 3を使用しています。
これは CSS セレクターのサブセットのみを処理しますが、目的には十分かもしれません。
from html.parser import HTMLParser
class AttrQuery():
def __init__(self):
self.repl_text = ""
self.selectors = []
def add_css_sel(self, seltext):
sels = seltext.split(" ")
for selector in sels:
if selector[:1] == "#":
self.add_selector({"id": selector[1:]})
elif selector[:1] == ".":
self.add_selector({"class": selector[1:]})
elif "." in selector:
html_tag, html_class = selector.split(".")
self.add_selector({"html_tag": html_tag, "class": html_class})
else:
self.add_selector({"html_tag": selector})
def add_selector(self, selector_dict):
self.selectors.append(selector_dict)
def match_test(self, tagwithattrs_list):
for selector in self.selectors:
for condition in selector:
condition_value = selector[condition]
if not self._condition_test(tagwithattrs_list, condition, condition_value):
return False
return True
def _condition_test(self, tagwithattrs_list, condition, condition_value):
for tagwithattrs in tagwithattrs_list:
try:
if condition_value == tagwithattrs[condition]:
return True
except KeyError:
pass
return False
class HTMLAttrParser(HTMLParser):
def __init__(self, html, **kwargs):
super().__init__(self, **kwargs)
self.tagwithattrs_list = []
self.queries = []
self.matchrepl_list = []
self.html = html
def handle_starttag(self, tag, attrs):
tagwithattrs = dict(attrs)
tagwithattrs["html_tag"] = tag
self.tagwithattrs_list.append(tagwithattrs)
if debug:
print("push\t", end="")
for attrname in tagwithattrs:
print("{}:{}, ".format(attrname, tagwithattrs[attrname]), end="")
print("")
def handle_endtag(self, tag):
try:
while True:
tagwithattrs = self.tagwithattrs_list.pop()
if debug:
print("pop \t", end="")
for attrname in tagwithattrs:
print("{}:{}, ".format(attrname, tagwithattrs[attrname]), end="")
print("")
if tag == tagwithattrs["html_tag"]: break
except IndexError:
raise IndexError("Found a close-tag for a non-existent element.")
def handle_data(self, data):
if self.tagwithattrs_list:
for query in self.queries:
if query.match_test(self.tagwithattrs_list):
line, position = self.getpos()
length = len(data)
match_replace = (line-1, position, length, query.repl_text)
self.matchrepl_list.append(match_replace)
def addquery(self, query):
self.queries.append(query)
def transform(self):
split_html = self.html.split("\n")
self.matchrepl_list.reverse()
if debug: print ("\nreversed list of matches (line, position, len, repl_text):\n{}\n".format(self.matchrepl_list))
for line, position, length, repl_text in self.matchrepl_list:
oldline = split_html[line]
newline = oldline[:position] + repl_text + oldline[position+length:]
split_html = split_html[:line] + [newline] + split_html[line+1:]
return "\n".join(split_html)
以下の使用例を参照してください。
html_test = """<div class=header><span class=title>Foo</span></div>
<p>1<p>2
<table><tr><td class=hi><div id=there>1</div></td></tr></table>"""
debug = False
parser = HTMLAttrParser(html_test)
query = AttrQuery()
query.repl_text = "Bar"
query.add_selector({"html_tag": "div", "class": "header"})
query.add_selector({"class": "title"})
parser.addquery(query)
query = AttrQuery()
query.repl_text = "InTable"
query.add_css_sel("table tr td.hi #there")
parser.addquery(query)
parser.feed(html_test)
transformed_html = parser.transform()
print("transformed html:\n{}".format(transformed_html))
出力：
transformed html:
<div class=header><span class=title>Bar</span></div>
<p>1<p>2
<table><tr><td class=hi><div id=there>InTable</div></td></tr></table>