Created
February 4, 2015 00:59
-
-
Save samba/b0879ffcefdec729d298 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
## Adjusts HTML structure and applies style attributes (etc) to static HTML. | |
## Conceptually inspired by jQuery, of course. | |
import sys | |
from xml.etree import ElementTree as tree | |
class QueryResult(object): | |
def __init__(self, matches): | |
self.matches = matches | |
def find(self, expression): | |
result = [] | |
for i in self.matches: | |
result += i.findall(expression) | |
return QueryResult(Set(result)) | |
def attr(self, **attribs): | |
for i in self.matches: | |
for name, value in attribs.iteritems(): | |
i.set(name, value) | |
return self | |
def rename(self, new_name): | |
for i in self.matches: | |
i.tag = new_name | |
return self | |
class Document(object): | |
def __init__(self, filename): | |
self.doc = tree.parse(filename) | |
self.root = self.doc.getroot() | |
def query(self, expression): | |
return QueryResult(self.doc.findall(expression)) | |
def write(self, output, method = 'html'): | |
self.doc.write(output, method = method) | |
def main(filename): | |
doc = Document(filename) | |
doc.query('table').attr(id = 'block-detailed', style = "border-collapse: inherit") | |
doc.query('table//tr[1]/td').rename('th') | |
doc.query('table//tr/td[2]').attr(style = 'font-weight: bold') | |
doc.query("table//td[@colspan='3'][1]/../td").attr(style = 'font-weight: bold; border-top: 1px solid #939393; padding-bottom: 2em;') | |
doc.write(sys.stdout, method = "html") | |
if __name__ == '__main__': | |
main(sys.argv[1]) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment