Python pdfstring_to_text Examples

Example #1

File: retrieval.py Project: AndrewJHart/everyblock_code

 def parse_list(self, page):
     precinct, raw_pdf = page
     pdf_text = pdfstring_to_text(raw_pdf, keep_layout=False)
     m = pdf_re.search(pdf_text)
     if not m:
         raise ScraperBroken("Didn't find data in PDF for precinct %s" % precinct)
     else:
         yield dict(m.groupdict(), precinct=precinct)

Example #2

File: retrieval.py Project: frankk00/openblock

 def parse_list(self, page):
     precinct, raw_pdf = page
     pdf_text = pdfstring_to_text(raw_pdf, keep_layout=False)
     m = pdf_re.search(pdf_text)
     if not m:
         raise ScraperBroken("Didn't find data in PDF for precinct %s" % precinct)
     else:
         yield dict(m.groupdict(), precinct=precinct)

Example #3

 def parse_detail(self, page, list_record):
     text = pdfstring_to_text(page)
     m = self.parse_detail_re.search(text)
     if m:
         self.logger.debug('Got a match for parse_detail_re')
         return m.groupdict()
     else:
         self.logger.warning("Regex failed on %s", self.__current_url)
         raise SkipRecord

Example #4

File: retrieval.py Project: AndrewJHart/everyblock_code

 def parse_detail(self, page, list_record):
     text = pdfstring_to_text(page)
     m = self.parse_detail_re.search(text)
     if m:
         self.logger.debug('Got a match for parse_detail_re')
         return m.groupdict()
     else:
         self.logger.warning("Regex failed on %s", self.__current_url)
         raise SkipRecord