def _start(self, result, position=0):
     i_start = 0
     for i in range(self.margin)[::-1]:
         start = result[position:i + position]
         start = extract_utils.escape_regex_meta(start)
         p = re.compile(start, re.IGNORECASE)
         match = p.search(self.html_text)
         if match:
             s = match.group()
             i_start = self.html_text.index(s)
             break
     return i_start
Esempio n. 2
0
 def _end(self, result):
     i_end = 0
     for i in range(1, self.margin)[::-1]:
         end = result[-i:]
         end = extract_utils.escape_regex_meta(end)
         p = re.compile(end, re.IGNORECASE)
         match = p.search(self.html_text)
         if match:
             s = match.group()
             i_end = self.html_text.index(s) + len(s)
             break
     return i_end
 def _end(self, result):
     i_end = 0
     for i in range(1, self.margin)[::-1]:
         end = result[-i:]
         end = extract_utils.escape_regex_meta(end)
         p = re.compile(end, re.IGNORECASE)
         match = p.search(self.html_text)
         if match:
             s = match.group()
             i_end = self.html_text.index(s) + len(s)
             break
     return i_end
Esempio n. 4
0
 def _start(self, result, position=0):
     i_start = 0
     for i in range(self.margin)[::-1]:
         start = result[position:i + position]
         start = extract_utils.escape_regex_meta(start)
         p = re.compile(start, re.IGNORECASE)
         match = p.search(self.html_text)
         if match:
             s = match.group()
             i_start = self.html_text.index(s)
             break
     return i_start