python - Regex not matching pattern between quotes? -

i have simple regex parse source code files , each line extract content enclosed in double quotes, use in gettext.po file

here regex:

gettext_subject = re.compile(r"""[subject: |summary: ]\"(.*?)\"""").findall 

here sample input file:

exports.onappointment = (appt, user, lang, isnew) ->   if not user return promise.reject "appointment has no user."   moment.locale(lang)   start = moment(appt.when)   cal = new ical()   console.log appt.when   cal.addevent     start: start.todate()     end: moment(start).add(2,"hours").todate()     summary: "continental showroom visit"   mail =     to: user.emailid     subject: if isnew "new appointment" else "appointment updated"     alternatives: [         contenttype: "text/calendar",         contents: new buffer(cal.tostring()),         contentencoding: "7bit"       ]   template =     name: "booking"     lang: lang     locals:       name: "#{user.firstname} #{user.lastname}"       datetime: moment(appt.when).format("dddd mmmm [at] hh:mm a")       cancelurl: config.server.baseurl + "/appointment/cancel/#{appt._id}"   emailclient.send2 mail, template 

this code runs correct:

gettext_subject = re.compile(r"""subject: \"(.*?)\"""").findall 

and testing command line returns, right answer

$ python python 2.7.6 (default, mar 22 2014, 22:59:56)  [gcc 4.8.2] on linux2 type "help", "copyright", "credits" or "license" more information. >>> import re >>> gettext = re.compile(r"""[subject: |summary: ]\"(.*?)\"""").findall >>> pattern = """subject: \"blah blah blah\"\nsummary: \"summary text\"\nsubject: \"second subject line\"\nsummary: if isnew \"new appointment\" else \"appointment updated\"\n""" >>> print gettext(pattern) ['blah blah blah', 'summary text', 'second subject line', 'new appointment', 'appointment updated'] >>>  

but when run through code not work, here code:

import os import sys import re operator import itemgetter  walk_dir = ["app", "email", "views"] #t=(" ") gettext_messages = re.compile(r"""\"(.*)\"""", re.multiline).findall gettext_re = re.compile(r"""[=|#|{]t\(\"(.*?)\"""").findall gettext_subject = re.compile(r"""[subject: |summary: ]\"(.*?)\"""").findall  gettext = [] x in walk_dir:     curr_dir = "../node-blade-boiler-template/" + x     root, dirs, files in os.walk(curr_dir, topdown=false):         if ".git" in dirs:             dirs.remove(".git")         if "node-modules" in dirs:             dirs.remove("node-modules")         if "models" in dirs:             dirs.remove("models")          filename in files:             file_path = os.path.join(root, filename)             #print('\n- file %s (full path: %s)' % (filename, file_path))             open(file_path, 'rb') f:                 f_content = f.read()                 if 'messages.coffee' == filename:                     #pass                     msgids = gettext_messages(f_content)                 elif 'map.coffee' == filename:                     pass                 elif 'emailtrigger.coffee' == filename:                     #print f_content                     if 'subject: ' in f_content:                         print gettext_subject(f_content)                         msgids = gettext_subject(f_content)                  else:                     msgids = gettext_re(f_content)                 msgid in msgids:                     msgid = '"' + msgid + '"'                     #print msgid                     dic = {                     'path' : file_path,                     'msgid' : "%s" % msgid                     }                     gettext.append(dic) 

any advice appreciated.

(?:subject:|summary:)[^"]*"(.*?)" 

you can try this.see demo.[] not think.its character class.[subject] match subject,tcejubs charcters in order.

see demo.

https://regex101.com/r/mt0ie7/33#python