Skip to content

regex updated #2

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
eneq123 wants to merge 4 commits into from
Closed

regex updated #2

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
4ee49b6
regex updated
Dec 8, 2013
ade9651
Revert to 4ee49b6f6e7176348fb92599980a13b6edc21593
Dec 9, 2013
29ed666
Merge branch 'master' of https://github.com/eneq123/python-stdnum
Dec 9, 2013
a058e66
regex fixed, some optimization
Dec 12, 2013
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
59 changes: 43 additions & 16 deletions getimsi.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -81,14 +81,23 @@


remove_ref_re = re.compile(r'<ref>.*?</ref>')

remove_comment_re = re.compile(r'{{.*?}}')
remove_href_re = re.compile(ur'(?i)\b((?:https?://|www\d{0,3}[.]|[a-z0-9.\-]+' +
ur'[.][a-z]{2,4}/)(?:[^\s()<>]+|\(([^\s()<>]+|' +
ur'(\([^\s()<>]+\)))*\))+(?:\(([^\s()<>]+|' +
ur'(\([^\s()<>]+\)))*\)|[^\s`!()\[\]{};:\'".,<>' +
ur'?\xab\xbb\u201c\u201d\u2018\u2019]))')

def cleanup_value(val):
"""Remove unneeded markup from the value."""
# remove uninteresting things from value
val = val.replace('[', '').replace(']', '').strip()
val = remove_comment_re.sub('', val)
val = remove_ref_re.sub('', val)
val = remove_href_re.sub('', val)
val = val.replace('[', '').replace(']', '').replace('\'\'', '').strip()
val = val.split('|')[-1]
# replace value
val = val.replace('Unknown', '')
val = val.replace('United Kingdom|UK', 'United Kingdom')
val = val.replace('United States|US', 'United States')
val = val.replace('New Zealand|NZ', 'New Zealand').strip()
Expand All @@ -105,14 +114,14 @@ def get_mncs_from_wikipedia(data):
"""Update the collection of Mobile Country Codes from Wikipedia.
This parses a Wikipedia page to extract the MCC and MNC, the first
part of any IMSI, and stores the results."""
mnc_country_re = re.compile(r'^====\s+(?P<country>.*?)(\s+-\s+(?P<cc>[^\s]{2}))?\s+====$')
mnc_line_re = re.compile(r'^\|\s+(?P<mcc>[0-9]+)' +
r'\s+\|\|\s+(?P<mnc>[0-9]+)' +
r'(\s+\|\|\s+(?P<brand>[^|]*)' +
r'(\s+\|\|\s+(?P<operator>[^|]*)' +
r'(\s+\|\|\s+(?P<status>[^|]*)' +
r'(\s+\|\|\s+(?P<bands>[^|]*)' +
r'(\s+\|\|\s+(?P<notes>[^|]*)' +
mnc_country_re = re.compile(r'^[=]{2,4}\s+(?P<country>.*?)(\s+-\s+(?P<cc>[^\s]{2}))?\s+[=]{2,4}$')
mnc_line_re = re.compile(r'^\|\s*(?P<mcc>[0-9]+)' +
r'\s*\\\\\s*(?P<mnc>[0-9]+)' +
r'(\s*\\\\\s*(?P<brand>[^\\]*)' +
r'(\s*\\\\\s*(?P<operator>[^\\]*)' +
r'(\s*\\\\\s*(?P<status>[^\\]*)' +
r'(\s*\\\\\s*(?P<bands>[^\\]*)' +
r'(\s*\\\\\s*(?P<notes>[^\\]*)' +
r')?)?)?)?)?')
f = urllib.urlopen(mcc_list_url)
country = cc = ''
Expand All @@ -122,14 +131,32 @@ def get_mncs_from_wikipedia(data):
if match:
country = match.group('country')
cc = (match.group('cc') or '').lower()
if "||" not in line:
continue
line = line.replace('||', '\\\\')
match = mnc_line_re.match(line)
if match:
update_mncs(data, match.group('mcc'), match.group('mnc'),
country=country, cc=cc, brand=match.group('brand'),
operator=match.group('operator'),
status=match.group('status'),
bands=match.group('bands'))

mnc_list = str2range(match.group('mnc'))
for mnc in mnc_list:
update_mncs(data, match.group('mcc'), mnc,
country=country, cc=cc, brand=match.group('brand'),
operator=match.group('operator'),
status=match.group('status'),
bands=match.group('bands'))

def str2range(x):
result = []
for part in x.split(','):
if '-' in part:
a, b = part.split('-')
f = "%0" + str(len(b)) + "d"
a, b = int(a), int(b)
for i in range(a, b + 1):
result.append(f % (i))
else:
a = part
result.append(part)
return result

if __name__ == '__main__':
# download/parse the information
Expand Down
Loading