diff options
| author | Nathan Kinkade <nath@nkinka.de> | 2013-11-07 22:47:47 +0000 |
|---|---|---|
| committer | Nathan Kinkade <nath@nkinka.de> | 2013-11-07 22:47:47 +0000 |
| commit | ef765867532a0a6767bf36cb6dd9db14fe8f79fc (patch) | |
| tree | e63144397effa07894d2b918db495cfa84656153 | |
| parent | 4a1b3b1f50dde44d500361d5ccb7bc5e17a2d35b (diff) | |
Fixed a bug where numbers less than 10 needed to be padded with a zero, but not ones over, of course.
| -rwxr-xr-x | miami-dade_clerk_courts.py | 17 |
1 files changed, 11 insertions, 6 deletions
diff --git a/miami-dade_clerk_courts.py b/miami-dade_clerk_courts.py index d9b3ef5..4cfc201 100755 --- a/miami-dade_clerk_courts.py +++ b/miami-dade_clerk_courts.py @@ -281,12 +281,17 @@ def parse_akas(akas_soup, case_id): akas_count_text = akas_soup.find(id='ctl00_cphPage_lblDefendants').text akas_count = re.match('^\d+', akas_count_text).group(0) for num in range(0, int(akas_count)): + + # We have to pad numbers less than 10 + if num < 10: + num = '0%s' % num + # For readability, get field ids into variables - last_name_id = 'ctl00_cphPage_rptDefendants_ctl0%s_lnkDefendantLastName' % num - first_name_id = 'ctl00_cphPage_rptDefendants_ctl0%s_lnkDefendantFirstName' % num - middle_name_id = 'ctl00_cphPage_rptDefendants_ctl0%s_lnkDefendantMiddleName' % num - race_id = 'ctl00_cphPage_rptDefendants_ctl0%s_lnkDefendantRace' % num - sex_id = 'ctl00_cphPage_rptDefendants_ctl0%s_lnkDefendantSex' % num + last_name_id = 'ctl00_cphPage_rptDefendants_ctl%s_lnkDefendantLastName' % num + first_name_id = 'ctl00_cphPage_rptDefendants_ctl%s_lnkDefendantFirstName' % num + middle_name_id = 'ctl00_cphPage_rptDefendants_ctl%s_lnkDefendantMiddleName' % num + race_id = 'ctl00_cphPage_rptDefendants_ctl%s_lnkDefendantRace' % num + sex_id = 'ctl00_cphPage_rptDefendants_ctl%s_lnkDefendantSex' % num # Now get the actual variables from the soup last_name = akas_soup.find(id=last_name_id).text @@ -327,7 +332,7 @@ def main(): # Keep track of how many NOT FOUND errors we get. case_not_found_count = 0 - for seq in range(37,39): + for seq in range(23000,25000): if case_not_found_count > max_case_not_found_count: # If our not_found_count exceeds the maximum set, # then assume that we have reached the end of all |