from __future__ import print_function import sys from roundup.anypy.strings import u2s, uchr _pyver = sys.version_info[0] class dehtml: def __init__(self, converter): if converter == "none": self.html2text = None return try: if converter == "beautifulsoup": # Not as well tested as dehtml. from bs4 import BeautifulSoup def html2text(html): soup = BeautifulSoup(html, "html.parser") # kill all script and style elements for script in soup(["script", "style"]): script.extract() return u2s(soup.get_text("\n", strip=True)) self.html2text = html2text else: raise ImportError except ImportError: # use the fallback below if beautiful soup is not installed. try: # Python 3+. from html.entities import name2codepoint from html.parser import HTMLParser except ImportError: # Python 2. from htmlentitydefs import name2codepoint from HTMLParser import HTMLParser class DumbHTMLParser(HTMLParser): # class attribute text = "" # internal state variable _skip_data = False _last_empty = False def handle_data(self, data): if self._skip_data: # skip data in script or style block return if (data.strip() == ""): # reduce multiple blank lines to 1 if (self._last_empty): return else: self._last_empty = True else: self._last_empty = False self.text = self.text + data def handle_starttag(self, tag, attrs): # noqa: ARG002 if (tag == "p"): self.text = self.text + "\n" if (tag in ("style", "script")): self._skip_data = True def handle_endtag(self, tag): if (tag in ("style", "script")): self._skip_data = False def handle_entityref(self, name): if self._skip_data: return c = uchr(name2codepoint[name]) try: self.text = self.text + c except UnicodeEncodeError: # print a space as a placeholder self.text = self.text + " " def html2text(html): parser = DumbHTMLParser( convert_charrefs=True) if _pyver == 3 else DumbHTMLParser() parser.feed(html) parser.close() return parser.text self.html2text = html2text if __name__ == "__main__": html = """

Roundup