pax_global_header00006660000000000000000000000064126135177650014527gustar00rootroot0000000000000052 comment=d2b621f0317cf7ecc4dbdebe9786889294a18221 urlscan-0.8.2/000077500000000000000000000000001261351776500132055ustar00rootroot00000000000000urlscan-0.8.2/.gitignore000066400000000000000000000001021261351776500151660ustar00rootroot00000000000000*.pyc *.egg *.egg-info *.gz *.xz build dist test_emails/ MANIFEST urlscan-0.8.2/COPYING000066400000000000000000000431031261351776500142410ustar00rootroot00000000000000 GNU GENERAL PUBLIC LICENSE Version 2, June 1991 Copyright (C) 1989, 1991 Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA Everyone is permitted to copy and distribute verbatim copies of this license document, but changing it is not allowed. Preamble The licenses for most software are designed to take away your freedom to share and change it. By contrast, the GNU General Public License is intended to guarantee your freedom to share and change free software--to make sure the software is free for all its users. This General Public License applies to most of the Free Software Foundation's software and to any other program whose authors commit to using it. (Some other Free Software Foundation software is covered by the GNU Lesser General Public License instead.) You can apply it to your programs, too. When we speak of free software, we are referring to freedom, not price. Our General Public Licenses are designed to make sure that you have the freedom to distribute copies of free software (and charge for this service if you wish), that you receive source code or can get it if you want it, that you can change the software or use pieces of it in new free programs; and that you know you can do these things. To protect your rights, we need to make restrictions that forbid anyone to deny you these rights or to ask you to surrender the rights. These restrictions translate to certain responsibilities for you if you distribute copies of the software, or if you modify it. For example, if you distribute copies of such a program, whether gratis or for a fee, you must give the recipients all the rights that you have. You must make sure that they, too, receive or can get the source code. And you must show them these terms so they know their rights. We protect your rights with two steps: (1) copyright the software, and (2) offer you this license which gives you legal permission to copy, distribute and/or modify the software. Also, for each author's protection and ours, we want to make certain that everyone understands that there is no warranty for this free software. If the software is modified by someone else and passed on, we want its recipients to know that what they have is not the original, so that any problems introduced by others will not reflect on the original authors' reputations. Finally, any free program is threatened constantly by software patents. We wish to avoid the danger that redistributors of a free program will individually obtain patent licenses, in effect making the program proprietary. To prevent this, we have made it clear that any patent must be licensed for everyone's free use or not licensed at all. The precise terms and conditions for copying, distribution and modification follow. GNU GENERAL PUBLIC LICENSE TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION 0. This License applies to any program or other work which contains a notice placed by the copyright holder saying it may be distributed under the terms of this General Public License. The "Program", below, refers to any such program or work, and a "work based on the Program" means either the Program or any derivative work under copyright law: that is to say, a work containing the Program or a portion of it, either verbatim or with modifications and/or translated into another language. (Hereinafter, translation is included without limitation in the term "modification".) Each licensee is addressed as "you". Activities other than copying, distribution and modification are not covered by this License; they are outside its scope. The act of running the Program is not restricted, and the output from the Program is covered only if its contents constitute a work based on the Program (independent of having been made by running the Program). Whether that is true depends on what the Program does. 1. You may copy and distribute verbatim copies of the Program's source code as you receive it, in any medium, provided that you conspicuously and appropriately publish on each copy an appropriate copyright notice and disclaimer of warranty; keep intact all the notices that refer to this License and to the absence of any warranty; and give any other recipients of the Program a copy of this License along with the Program. You may charge a fee for the physical act of transferring a copy, and you may at your option offer warranty protection in exchange for a fee. 2. You may modify your copy or copies of the Program or any portion of it, thus forming a work based on the Program, and copy and distribute such modifications or work under the terms of Section 1 above, provided that you also meet all of these conditions: a) You must cause the modified files to carry prominent notices stating that you changed the files and the date of any change. b) You must cause any work that you distribute or publish, that in whole or in part contains or is derived from the Program or any part thereof, to be licensed as a whole at no charge to all third parties under the terms of this License. c) If the modified program normally reads commands interactively when run, you must cause it, when started running for such interactive use in the most ordinary way, to print or display an announcement including an appropriate copyright notice and a notice that there is no warranty (or else, saying that you provide a warranty) and that users may redistribute the program under these conditions, and telling the user how to view a copy of this License. (Exception: if the Program itself is interactive but does not normally print such an announcement, your work based on the Program is not required to print an announcement.) These requirements apply to the modified work as a whole. If identifiable sections of that work are not derived from the Program, and can be reasonably considered independent and separate works in themselves, then this License, and its terms, do not apply to those sections when you distribute them as separate works. But when you distribute the same sections as part of a whole which is a work based on the Program, the distribution of the whole must be on the terms of this License, whose permissions for other licensees extend to the entire whole, and thus to each and every part regardless of who wrote it. Thus, it is not the intent of this section to claim rights or contest your rights to work written entirely by you; rather, the intent is to exercise the right to control the distribution of derivative or collective works based on the Program. In addition, mere aggregation of another work not based on the Program with the Program (or with a work based on the Program) on a volume of a storage or distribution medium does not bring the other work under the scope of this License. 3. You may copy and distribute the Program (or a work based on it, under Section 2) in object code or executable form under the terms of Sections 1 and 2 above provided that you also do one of the following: a) Accompany it with the complete corresponding machine-readable source code, which must be distributed under the terms of Sections 1 and 2 above on a medium customarily used for software interchange; or, b) Accompany it with a written offer, valid for at least three years, to give any third party, for a charge no more than your cost of physically performing source distribution, a complete machine-readable copy of the corresponding source code, to be distributed under the terms of Sections 1 and 2 above on a medium customarily used for software interchange; or, c) Accompany it with the information you received as to the offer to distribute corresponding source code. (This alternative is allowed only for noncommercial distribution and only if you received the program in object code or executable form with such an offer, in accord with Subsection b above.) The source code for a work means the preferred form of the work for making modifications to it. For an executable work, complete source code means all the source code for all modules it contains, plus any associated interface definition files, plus the scripts used to control compilation and installation of the executable. However, as a special exception, the source code distributed need not include anything that is normally distributed (in either source or binary form) with the major components (compiler, kernel, and so on) of the operating system on which the executable runs, unless that component itself accompanies the executable. If distribution of executable or object code is made by offering access to copy from a designated place, then offering equivalent access to copy the source code from the same place counts as distribution of the source code, even though third parties are not compelled to copy the source along with the object code. 4. You may not copy, modify, sublicense, or distribute the Program except as expressly provided under this License. Any attempt otherwise to copy, modify, sublicense or distribute the Program is void, and will automatically terminate your rights under this License. However, parties who have received copies, or rights, from you under this License will not have their licenses terminated so long as such parties remain in full compliance. 5. You are not required to accept this License, since you have not signed it. However, nothing else grants you permission to modify or distribute the Program or its derivative works. These actions are prohibited by law if you do not accept this License. Therefore, by modifying or distributing the Program (or any work based on the Program), you indicate your acceptance of this License to do so, and all its terms and conditions for copying, distributing or modifying the Program or works based on it. 6. Each time you redistribute the Program (or any work based on the Program), the recipient automatically receives a license from the original licensor to copy, distribute or modify the Program subject to these terms and conditions. You may not impose any further restrictions on the recipients' exercise of the rights granted herein. You are not responsible for enforcing compliance by third parties to this License. 7. If, as a consequence of a court judgment or allegation of patent infringement or for any other reason (not limited to patent issues), conditions are imposed on you (whether by court order, agreement or otherwise) that contradict the conditions of this License, they do not excuse you from the conditions of this License. If you cannot distribute so as to satisfy simultaneously your obligations under this License and any other pertinent obligations, then as a consequence you may not distribute the Program at all. For example, if a patent license would not permit royalty-free redistribution of the Program by all those who receive copies directly or indirectly through you, then the only way you could satisfy both it and this License would be to refrain entirely from distribution of the Program. If any portion of this section is held invalid or unenforceable under any particular circumstance, the balance of the section is intended to apply and the section as a whole is intended to apply in other circumstances. It is not the purpose of this section to induce you to infringe any patents or other property right claims or to contest validity of any such claims; this section has the sole purpose of protecting the integrity of the free software distribution system, which is implemented by public license practices. Many people have made generous contributions to the wide range of software distributed through that system in reliance on consistent application of that system; it is up to the author/donor to decide if he or she is willing to distribute software through any other system and a licensee cannot impose that choice. This section is intended to make thoroughly clear what is believed to be a consequence of the rest of this License. 8. If the distribution and/or use of the Program is restricted in certain countries either by patents or by copyrighted interfaces, the original copyright holder who places the Program under this License may add an explicit geographical distribution limitation excluding those countries, so that distribution is permitted only in or among countries not thus excluded. In such case, this License incorporates the limitation as if written in the body of this License. 9. The Free Software Foundation may publish revised and/or new versions of the General Public License from time to time. Such new versions will be similar in spirit to the present version, but may differ in detail to address new problems or concerns. Each version is given a distinguishing version number. If the Program specifies a version number of this License which applies to it and "any later version", you have the option of following the terms and conditions either of that version or of any later version published by the Free Software Foundation. If the Program does not specify a version number of this License, you may choose any version ever published by the Free Software Foundation. 10. If you wish to incorporate parts of the Program into other free programs whose distribution conditions are different, write to the author to ask for permission. For software which is copyrighted by the Free Software Foundation, write to the Free Software Foundation; we sometimes make exceptions for this. Our decision will be guided by the two goals of preserving the free status of all derivatives of our free software and of promoting the sharing and reuse of software generally. NO WARRANTY 11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION. 12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES. END OF TERMS AND CONDITIONS How to Apply These Terms to Your New Programs If you develop a new program, and you want it to be of the greatest possible use to the public, the best way to achieve this is to make it free software which everyone can redistribute and change under these terms. To do so, attach the following notices to the program. It is safest to attach them to the start of each source file to most effectively convey the exclusion of warranty; and each file should have at least the "copyright" line and a pointer to where the full notice is found. Copyright (C) This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation; either version 2 of the License, or (at your option) any later version. This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You should have received a copy of the GNU General Public License along with this program; if not, write to the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. Also add information on how to contact you by electronic and paper mail. If the program is interactive, make it output a short notice like this when it starts in an interactive mode: Gnomovision version 69, Copyright (C) year name of author Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'. This is free software, and you are welcome to redistribute it under certain conditions; type `show c' for details. The hypothetical commands `show w' and `show c' should show the appropriate parts of the General Public License. Of course, the commands you use may be called something other than `show w' and `show c'; they could even be mouse-clicks or menu items--whatever suits your program. You should also get your employer (if you work as a programmer) or your school, if any, to sign a "copyright disclaimer" for the program, if necessary. Here is a sample; alter the names: Yoyodyne, Inc., hereby disclaims all copyright interest in the program `Gnomovision' (which makes passes at compilers) written by James Hacker. , 1 April 1989 Ty Coon, President of Vice This General Public License does not permit incorporating your program into proprietary programs. If your program is a subroutine library, you may consider it more useful to permit linking proprietary applications with the library. If this is what you want to do, use the GNU Lesser General Public License instead of this License. urlscan-0.8.2/MANIFEST.in000066400000000000000000000000421261351776500147370ustar00rootroot00000000000000include COPYING include urlscan.1 urlscan-0.8.2/README.rst000066400000000000000000000060511261351776500146760ustar00rootroot00000000000000Urlscan ======= Contributors ------------ Daniel Burrows (Original Author) Scott Hansen (Maintainer) Maxime Chatelle (Debian Maintainer) Purpose and Requirements ------------------------ Urlscan is a small program that is designed to integrate with the "mutt" mailreader to allow you to easily launch a Web browser for URLs contained in email messages. It is a replacement for the "urlview" program. Requires: Python 2.6+ (including Python 3.x) and the python-urwid library Features -------- Urlscan parses an email message or file and scans it for URLs and email addresses. It then displays the URLs and their context within the message, and allows you to choose one or more URLs to send to your Web browser. Alternatively, it send a list of all URLs to stdout. Relative to urlview, urlscan has the following additional features: - Support for emails in quoted-printable and base64 encodings. No more stripping out =40D from URLs by hand! - The context of each URL is provided along with the URL. For HTML mails, a crude parser is used to render the HTML into text. Installation and setup ---------------------- To install urlscan, install from your distribution repositories, from Pypi, install the `Archlinux Package`_ , or install from source using setup.py. .. NOTE:: To work with Python 3.x the minimum required version of urwid is 1.2.1. Python 2.x works fine with urwid >= 1.0.1 Once urlscan is installed, add the following lines to your .muttrc: macro index,pager \cb " urlscan" "call urlscan to extract URLs out of a message" macro attach,compose \cb " urlscan" "call urlscan to extract URLs out of a message" Once this is done, Control-b while reading mail in mutt will automatically invoke urlscan on the message. To choose a particular browser, set the environment variable BROWSER: export BROWSER=/usr/bin/epiphany Command Line usage ------------------ :: urlscan [-n] Urlscan can extract URLs and email addresses from emails, or any text file. Calling without the '-n' flag will start the curses browser. Calling with '-n' will just output a list of URLs/email addressess to stdout. Files can also be piped to urlscan using normal shell pipe mechanisms: `cat | urlscan` or `urlscan < ` Known bugs and limitations -------------------------- - Running urlscan sometimes "messes up" the terminal background. This seems to be an urwid bug, but I haven't tracked down just what's going on. - Extraction of context from HTML messages leaves something to be desired. Probably the ideal solution would be to extract context on a word basis rather than on a paragraph basis. - The HTML message handling is a bit kludgy in general. - multipart/alternative sections are handled by descending into all the sub-parts, rather than just picking one, which may lead to URLs and context appearing twice. - Configurability is more than a little bit lacking. .. _Archlinux Package: https://aur.archlinux.org/packages/urlscan-git/ urlscan-0.8.2/bin/000077500000000000000000000000001261351776500137555ustar00rootroot00000000000000urlscan-0.8.2/bin/urlscan000077500000000000000000000105401261351776500153520ustar00rootroot00000000000000#!/usr/bin/env python # # A simple urlview replacement that handles things like quoted-printable # properly. aka "urlview minus teh suck" # # Copyright (C) 2006-2007 Daniel Burrows # Copyright (C) 2015 Scott Hansen # # This program is free software; you can redistribute it and/or # modify it under the terms of the GNU General Public License as # published by the Free Software Foundation; either version 2 of the # License, or (at your option) any later version. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU # General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program; see the file COPYING. If not, write to # the Free Software Foundation, Inc., 59 Temple Place - Suite 330, # Boston, MA 02111-1307, USA. from __future__ import unicode_literals import argparse import io import locale import os import sys from urlscan import urlchoose, urlscan try: from email.Parser import Parser as parser except ImportError: from email.parser import Parser as parser def parse_arguments(): """Parse command line options. Returns: args """ arg_parse = argparse.ArgumentParser(description="Parse and display URLs") arg_parse.add_argument('--compact', '-c', action='store_true', default=False, help="Don't display the context of each URL.") arg_parse.add_argument('--no-browser', '-n', dest="nobrowser", action='store_true', default=False, help="Pipe URLs to stdout") arg_parse.add_argument('message', nargs='?', default=sys.stdin, help="Filename of the message to parse") args = arg_parse.parse_args() return args def close_stdin(): """This section closes out sys.stdin if necessary so as not to block curses keyboard inputs """ if not os.isatty(0): fd = os.open('/dev/tty', os.O_RDONLY) if fd < 0: sys.stderr.write('Unable to open an input tty.\n') sys.exit(-1) else: os.dup2(fd, 0) os.close(fd) def process_input(fn): """Return the parsed text of stdin or the message. Accounts for possible file encoding differences. Args: fn - filename or sys.stdin Returns: msg - parsed (email parser) text of the message with the correct encoding set """ enc_list = ['UTF-8', 'LATIN-1', 'iso8859-1', 'iso8859-2', 'UTF-16', 'CP720', 'CP437'] locale.setlocale(locale.LC_ALL, '') code = locale.getpreferredencoding() if code not in enc_list: enc_list.insert(0, code) if fn is sys.stdin: try: stdin_file = fn.buffer.read() except AttributeError: stdin_file = fn.read() else: stdin_file = None for c in enc_list: try: if stdin_file is not None: f = io.StringIO(stdin_file.decode(c)) else: f = io.open(fn, mode='r', encoding=(c)) msg = parser().parse(f) except (UnicodeDecodeError, UnicodeError): continue else: break finally: try: fi.close() except NameError: pass print("Encoding not detected. Please pass encoding value manually") raise close_stdin() # Handle multiple nested message parts _msg_set_charset(msg, c) return msg def _msg_set_charset(msg, encoding): """Recursive function to set the charset of nested message parts. """ encoding = msg.get_content_charset() or encoding try: msg.set_charset(encoding) except (AttributeError, TypeError): for part in msg.get_payload(): _msg_set_charset(part, encoding) if __name__ == "__main__": args = parse_arguments() msg = process_input(args.message) if args.nobrowser is False: ui = urlchoose.URLChooser(urlscan.msgurls(msg), compact_mode=args.compact) ui.main() else: out = urlchoose.process_urls(urlscan.msgurls(msg), nobrowser=True) print("\n".join(out)) urlscan-0.8.2/requirements.txt000066400000000000000000000000151261351776500164650ustar00rootroot00000000000000urwid>=1.2.1 urlscan-0.8.2/setup.py000077500000000000000000000012251261351776500147220ustar00rootroot00000000000000#!/usr/bin/env python from setuptools import setup setup(name="urlscan", version="0.8.2", description="View/select the URLs in an email message or file", author="Scott Hansen", author_email="firecat4153@gmail.com", url="https://github.com/firecat53/urlscan", download_url="https://github.com/firecat53/urlscan/archive/0.8.2.zip", packages=['urlscan'], scripts=['bin/urlscan'], package_data={'urlscan': ['README.rst']}, data_files=[('share/doc/urlscan', ['README.rst', 'COPYING']), ('share/man/man1', ['urlscan.1'])], license="GPLv2", install_requires=["urwid"] ) urlscan-0.8.2/urlscan.1000066400000000000000000000035761261351776500147510ustar00rootroot00000000000000.\" Hey, EMACS: -*- nroff -*- .TH URLSCAN 1 "October 26, 2015" .SH NAME urlscan \- browse the URLs in an email message from a terminal .SH SYNOPSIS \fBurlscan\fR [options] < .I message \fBurlscan\fR [options] .I message .SH DESCRIPTION \fBurlscan\fR accepts a single email message on standard input, then displays a terminal-based list of the URLs in the given message. Selecting a URL uses the Python webbrowser module to determine which browser to open. The \fBBROWSER\fR environment variable will be used if it is set. \fBurlscan\fR is primarily intended to be used with the .B mutt (1) mailreader, but it should work well with any terminal-based mail program. \fBurlscan\fR is similar to \fBurlview\fR(1), but has the following additional features: \fB1.\fR Support for more message encodings, such as quoted-printable and base64. \fB2.\fR Extraction and display of the context surrounding each URL. .SH OPTIONS .TP .B \-c, \-\-compact Display a simple list of the extracted URLs, instead of showing the context of each URL. .TP .B \-n, \-\-no-browser Disables the selection interface and print the links to standard output. Useful for scripting (implies \fB\-\-compact\fR). .SH MUTT INTEGRATION To integrate urlscan with mutt, include the following two commands in \fB~/.muttrc\fR: .ad l macro index,pager \\cb " urlscan" "call urlscan to extract URLs out of a message" macro attach,compose \\cb " urlscan" "call urlscan to extract URLs out of a message" .ad b Once these lines are in your mutt configuration file, pressing Control-b will allow you to browse and open the URLs in the currently selected message. .SH SEE ALSO \fI/usr/share/doc/urlscan/README\fR, \fBurlview\fR(1), \fBmutt\fR(1) .SH AUTHOR This manual page was written by Daniel Burrows and Scott Hansen urlscan-0.8.2/urlscan/000077500000000000000000000000001261351776500146545ustar00rootroot00000000000000urlscan-0.8.2/urlscan/__init__.py000066400000000000000000000000561261351776500167660ustar00rootroot00000000000000__all__ = ['browser', 'urlchoose', 'urlscan'] urlscan-0.8.2/urlscan/urlchoose.py000066400000000000000000000175031261351776500172370ustar00rootroot00000000000000# Copyright (C) 2006-2007 Daniel Burrows # Copyright (C) 2015 Scott Hansen # # This program is free software; you can redistribute it and/or # modify it under the terms of the GNU General Public License as # published by the Free Software Foundation; either version 2 of the # License, or (at your option) any later version. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU # General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program; see the file COPYING. If not, write to # the Free Software Foundation, Inc., 59 Temple Place - Suite 330, # Boston, MA 02111-1307, USA. """An urwid listview-based widget that lets you choose a URL from a list of URLs.""" import urwid import urwid.curses_display import webbrowser from threading import Thread from time import sleep def mkbrowseto(url): """Create the urwid callback function to open the web browser. """ def browse(*args): webbrowser.open(url) return browse def process_urls(extractedurls, compact_mode=False, nobrowser=False): """Process the 'extractedurls' and ready them for either the curses browser or non-interactive output Args: extractedurls compact_mode - True/False (Default False) nobrowser - True/False (Default False) Returns: items urls firstbutton - Number of first URL button if nobrowser, then _only_ return urls """ items = [] urls = [] first = True firstbutton = 0 if nobrowser is True: compact_mode = True for group, usedfirst, usedlast in extractedurls: if first: first = False elif not compact_mode: items.append(urwid.Divider(div_char='-', top=1, bottom=1)) groupurls = [] markup = [] if compact_mode: lasturl = None for chunks in group: for chunk in chunks: if chunk.url and chunk.url != lasturl: groupurls.append(chunk.url) urls.append(chunk.url) lasturl = chunk.url else: if not usedfirst: markup.append(('msgtext:ellipses', '...\n')) for chunks in group: i = 0 while i < len(chunks): chunk = chunks[i] i += 1 if chunk.url is None: markup.append(chunk.markup) else: urls.append(chunk.url) groupurls.append(chunk.url) # Collect all immediately adjacent # chunks with the same URL. tmpmarkup = [] if chunk.markup: tmpmarkup.append(chunk.markup) while i < len(chunks) and \ chunks[i].url == chunk.url: if chunks[i].markup: tmpmarkup.append(chunks[i].markup) i += 1 markup += [tmpmarkup or '', ('urlref:number:braces', ' ['), ('urlref:number', repr(len(urls))), ('urlref:number:braces', ']')] markup += '\n' if not usedlast: markup += [('msgtext:ellipses', '...\n\n')] items.append(urwid.Text(markup)) i = len(urls) - len(groupurls) for url in groupurls: if firstbutton == 0 and not compact_mode: firstbutton = len(items) i += 1 markup = [('urlref:number:braces', '['), ('urlref:number', repr(i)), ('urlref:number:braces', ']'), ' ', ('urlref:url', url)] items.append(urwid.Button(markup, mkbrowseto(url), user_data=url)) if not items: items.append(urwid.Text("No URLs found")) firstbutton = 1 if nobrowser is True: return urls else: return items, urls, firstbutton # Based on urwid examples. class URLChooser: def __init__(self, extractedurls, compact_mode=False): items, urls, firstbutton = process_urls(extractedurls, compact_mode) self.listbox = urwid.ListBox(items) self.listbox.set_focus(firstbutton) if len(urls) == 1: header = 'Found 1 url.' else: header = 'Found %d urls.' % len(urls) headerwid = urwid.AttrWrap(urwid.Text(header), 'header') self.top = urwid.Frame(self.listbox, headerwid) def main(self): self.ui = urwid.curses_display.Screen() self.ui.register_palette([ ('header', 'white', 'dark blue', 'standout'), ('footer', 'white', 'dark red', 'standout'), ('msgtext', 'light gray', 'black'), ('msgtext:bullet', 'white', 'black', 'standout'), ('msgtext:bold', 'white', 'black', 'standout'), ('msgtext:italic', 'dark cyan', 'black', 'standout'), ('msgtext:bolditalic', 'light cyan', 'black', 'standout'), ('anchor', 'yellow', 'black', 'standout'), ('anchor:bold', 'yellow', 'black', 'standout'), ('anchor:italic', 'yellow', 'black', 'standout'), ('anchor:bolditalic', 'yellow', 'black', 'standout'), ('msgtext:ellipses', 'light gray', 'black'), ('urlref:number:braces', 'light gray', 'black'), ('urlref:number', 'yellow', 'black', 'standout'), ('urlref:url', 'white', 'black', 'standout') ]) return self.ui.run_wrapper(self.run) def run(self): size = self.ui.get_cols_rows() try: while True: self.ui.s.erase() self.draw_screen(size) keys = self.ui.get_input() for k in keys: if k == 'window resize': size = self.ui.get_cols_rows() elif k == 'q': return None elif k == 'ctrl l': self.ui.s.clear() elif k == 'j': self.top.keypress(size, "down") elif k == 'k': self.top.keypress(size, "up") elif k == 'enter' or k == ' ': footer = "loading URL" footerwid = urwid.AttrWrap(urwid.Text(footer), 'footer') self.top.set_footer(footerwid) self.top.keypress(size, k) load_thread = Thread(target=self._loading_thread) load_thread.daemon = True load_thread.start() self.ui.s.clear() else: self.top.keypress(size, k) except KeyboardInterrupt: return None def _loading_thread(self): """Simple thread to wait 5 seconds after launching a URL, clearing the screen and clearing the footer loading message. """ sleep(5) footerwid = urwid.AttrWrap(urwid.Text(""), "default") self.top.set_footer(footerwid) size = self.ui.get_cols_rows() self.draw_screen(size) def draw_screen(self, size): canvas = self.top.render(size, focus=True) self.ui.draw_screen(size, canvas) urlscan-0.8.2/urlscan/urlscan.py000066400000000000000000000350401261351776500166770ustar00rootroot00000000000000# -*- coding: utf-8 -*- # Copyright (C) 2006-2007 Daniel Burrows # Copyright (C) 2015 Scott Hansen # # This program is free software; you can redistribute it and/or # modify it under the terms of the GNU General Public License as # published by the Free Software Foundation; either version 2 of the # License, or (at your option) any later version. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU # General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program; see the file COPYING. If not, write to # the Free Software Foundation, Inc., 59 Temple Place - Suite 330, # Boston, MA 02111-1307, USA. """Contains the backend logic that scans messages for URLs and context.""" from __future__ import unicode_literals import re try: from HTMLParser import HTMLParser except ImportError: from html.parser import HTMLParser def get_charset(message, default="utf-8"): """Get the message charset""" if message.get_content_charset(): return message.get_content_charset() if message.get_charset(): return message.get_charset() return default class Chunk: '''Represents a chunk of (marked-up) text that may or may not be linked to a URL. Attributes: markup - how this chunk will be rendered via urwid. This may be None if url is set, indicating that a URL footnote should be autogenerated. url - the URL to which this text is linked, or None if no URL link is present.''' def __init__(self, markup, url): self.markup = markup self.url = url def __str__(self): return 'Chunk(markup = %s, url= %s)' % (repr(self.markup), repr(self.url)) def __repr__(self): return self.__str__() def isheadertag(t): return len(t) == 2 and t[0] == 'h' and t[1].isdigit() class HTMLChunker(HTMLParser): """An HTMLParser that generates a sequence of lists of chunks. Each list represents a single paragraph.""" def __init__(self): HTMLParser.__init__(self) # This attribute is the current output list. self.rval = [] # If this attribute is True, the next chunk added will start a # new list. self.at_para_start = True self.trailing_space = False self.style_stack = [set()] self.anchor_stack = [None] self.list_stack = [] # either 'ul' or 'ol' entries. # Styled text uses the named attribute # msgtext:style1style2... where the styles # are always sorted in alphabetic order. # (if the text is in an anchor, substitute # "msgtext:anchor" for "msgtext") tag_styles = {'b': 'bold', 'i': 'italic'} ul_tags = ['*', '+', '-'] def cur_url(self): return self.anchor_stack[-1] def add_chunk(self, chunk): if self.at_para_start: self.rval.append([]) elif self.trailing_space: self.rval[-1].append(Chunk(' ', self.cur_url())) self.rval[-1].append(chunk) self.at_para_start = False self.trailing_space = False def end_para(self): if self.at_para_start: self.rval.append([]) else: self.at_para_start = True self.trailing_space = False if len(self.list_stack) > 0: self.add_chunk(Chunk(' ' * 3 * len(self.list_stack), self.cur_url())) def end_list_para(self): if self.at_para_start: self.rval.append([]) if len(self.list_stack) > 0: tp = self.list_stack[-1][0] if tp == 'ul': depth = len([t for t in self.list_stack if t[0] == tp]) ul_tags = HTMLChunker.ul_tags chunk = Chunk('%s ' % (ul_tags[depth % len(ul_tags)]), self.cur_url()) else: counter = self.list_stack[-1][1] self.list_stack[-1] = (tp, counter + 1) chunk = Chunk("%2d." % counter, self.cur_url()) self.add_chunk(chunk) else: self.end_para() def findattr(self, attrs, searchattr): for attr, val in attrs: if attr == searchattr: return val return None # TODO: should have better formatting. def handle_starttag(self, tag, attrs): if tag == 'a': self.anchor_stack.append(self.findattr(attrs, 'href')) elif tag == 'ul' or tag == 'ol': self.list_stack.append((tag, 1)) self.end_para() elif tag in HTMLChunker.tag_styles: self.style_stack.append(self.style_stack[-1] | set([HTMLChunker.tag_styles[tag]])) elif isheadertag(tag): self.style_stack.append(self.style_stack[-1] | set(['bold'])) elif tag == 'p' or tag == 'br': self.end_para() elif tag == 'img': # Since we expect HTML *email*, image links # should be external (naja?) alt = self.findattr(attrs, 'alt') if alt is None: alt = '[IMG]' src = self.findattr(attrs, 'src') if src is not None and src[:7] != 'http://': src = None if src is not None: self.anchor_stack.append(src) self.handle_data(alt) del self.anchor_stack[-1] else: self.handle_data(alt) elif tag == 'li': self.end_list_para() def handle_startendtag(self, tag, attrs): if tag in set(['p', 'br', 'li', 'img']): self.handle_starttag(tag, attrs) def handle_endtag(self, tag): if tag == 'a': del self.anchor_stack[-1] elif tag in HTMLChunker.tag_styles: del self.style_stack[-1] elif tag == 'ul' or tag == 'ol': del self.list_stack[-1] self.end_para() elif isheadertag(tag): del self.style_stack[-1] self.end_para() def handle_data(self, data): future_trailing_space = False if len(data) > 0: if data[0].isspace(): self.trailing_space = True if data[-1].isspace(): future_trailing_space = True data = ' '.join(data.split()) if self.anchor_stack[-1] is None: style = 'msgtext' else: style = 'anchor' if len(self.style_stack[-1]) > 0: stylelist = list(self.style_stack[-1]) stylelist.sort() style = style + ':' + ''.join(stylelist) self.add_chunk(Chunk((style, data), self.cur_url())) self.trailing_space = future_trailing_space extrachars = {8212: "--", 8217: "'", 8220: "``", 8221: "''", 8230: "..."} def handle_charref(self, name): if name[0] == 'x': n = int(name[1:], 16) else: n = int(name) if n < 128: name = chr(n) elif n in HTMLChunker.extrachars: name = HTMLChunker.extrachars[n] else: name = '&#%s;' % name self.handle_data(name) entities = {'nbsp': ' ', 'lt': '<', 'gt': '>', 'amp': '&', 'ldquo': '``', 'rdquo': "''", 'apos': "'"} def handle_entityref(self, name): if name in HTMLChunker.entities: self.handle_data(HTMLChunker.entities[name]) else: # If you see a reference, it needs to be # added above. self.handle_data('&%s;' % name) urlinternalpattern = r'[{}()@\w/\-%?&.=:;+,#~]' urltrailingpattern = r'[{}()@\w/\-%&=+#]' httpurlpattern = (r'(?:(https?|file|ftps?)://' + urlinternalpattern + r'*' + urltrailingpattern + r')') # Used to guess that blah.blah.blah.TLD is a URL. tlds = ['biz', 'com', 'edu', 'info', 'org', 'de'] guessedurlpattern = (r'(?:[\w\-%]+(?:\.[\w\-%]+)*\.(?:' + '|'.join(tlds) + '))') urlre = re.compile(r'(?:<(?:URL:)?)?(' + httpurlpattern + '|' + guessedurlpattern + '|(?P(mailto:)?[\w\-.]*@[\w\-.]*[\w\-]))>?', flags=re.U) # Poor man's test cases. assert(urlre.match('')) assert(urlre.match('http://linuxtoday.com')) assert(re.compile(guessedurlpattern).match('example.biz')) assert(urlre.match('example.biz')) assert(urlre.match('linuxtoday.com')) assert(urlre.match('master.wizard.edu')) assert(urlre.match('blah.bar.info')) assert(urlre.match('goodpr.org')) assert(urlre.match('http://github.com/firecat53/ürlscan')) assert(urlre.match('https://Schöne_Grüße.es/test')) assert(urlre.match('http://www.pantherhouse.com/newshelton/my-wife-thinks-i’m-a-swan/')) assert(not urlre.match('blah..org')) def parse_text_urls(s): """Parse a block of text, splitting it into its url and non-url components.""" rval = [] loc = 0 for match in urlre.finditer(s): if loc < match.start(): rval.append(Chunk(s[loc:match.start()], None)) # Turn email addresses into mailto: links email = match.group("email") if email and "mailto" not in email: m = "mailto:{}".format(email) else: m = match.group(1) rval.append(Chunk(None, m)) loc = match.end() if loc < len(s): rval.append(Chunk(s[loc:], None)) return rval def extract_with_context(lst, pred, before_context, after_context): rval = [] start = 0 length = 0 while start < len(lst): usedfirst = False usedlast = False # Extend to the next match. while start + length < len(lst) and length < before_context + 1 \ and not pred(lst[start + length]): length += 1 # Slide to the next match. while start + length < len(lst) and not pred(lst[start + length]): start += 1 # If there was no next match, abort here (it's easier # to do this than to try to detect this case later). if start + length == len(lst): break # Now extend repeatedly until we can't find anything. while start + length < len(lst) and pred(lst[start + length]): extendlength = 1 # Read in the 'after' context and see if it holds a URL. while extendlength < after_context + 1 and start + length + \ extendlength < len(lst) and \ not pred(lst[start + length + extendlength]): extendlength += 1 length += extendlength if start + length < len(lst) and not pred(lst[start + length]): # Didn't find a matching line, so we either # hit the end or extended to after_context + 1.. # # Now read in possible 'before' context # from the next URL; if we don't find one, # we discard the readahead. extendlength = 1 while extendlength < before_context and start + length + \ extendlength < len(lst) and \ not pred(lst[start + length + extendlength]): extendlength += 1 if start + length + extendlength < len(lst) and \ pred(lst[start + length + extendlength]): length += extendlength if length > 0 and start + length <= len(lst): if start == 0: usedfirst = True if start + length == len(lst): usedlast = True rval.append((lst[start:start + length], usedfirst, usedlast)) start += length length = 0 return rval nlre = re.compile('\r\n|\n|\r') def extracturls(s): """Given a text message, extract all the URLs found in the message, along with their surrounding context. The output is a list of sequences of Chunk objects, corresponding to the contextual regions extracted from the string. """ lines = nlre.split(s) # The number of lines of context above to provide. # above_context = 1 # The number of lines of context below to provide. # below_context = 1 # Plan here is to first transform lines into the form # [line_fragments] where each fragment is a chunk as # seen by parse_text_urls. Note that this means that # lines with more than one entry or one entry that's # a URL are the only lines containing URLs. linechunks = [parse_text_urls(l) for l in lines] return extract_with_context(linechunks, lambda chunk: len(chunk) > 1 or (len(chunk) == 1 and chunk[0].url is not None), 1, 1) def extracthtmlurls(s): c = HTMLChunker() c.feed(s) c.close() # above_context = 1 # below_context = 1 def somechunkisurl(chunks): for chunk in chunks: if chunk.url is not None: return True return False return extract_with_context(c.rval, somechunkisurl, 1, 1) def msgurls(msg, urlidx=1): # Written as a generator so I can easily choose only # one subpart in the future (e.g., for # multipart/alternative). Actually, I might even add # a browser for the message structure? enc = get_charset(msg) if msg.is_multipart(): for part in msg.get_payload(): for chunk in msgurls(part, urlidx): urlidx += 1 yield chunk elif msg.get_content_type() == 'text/plain': msg = decode_bytes(msg.get_payload(decode=True), enc) for chunk in extracturls(msg): urlidx += 1 yield chunk elif msg.get_content_type() == 'text/html': msg = decode_bytes(msg.get_payload(decode=True), enc) for chunk in extracthtmlurls(msg): urlidx += 1 yield chunk def decode_bytes(b, enc='utf-8'): """Given a string or bytes input, return a string. Args: b - bytes or string enc - encoding to use for decoding the byte string. """ try: s = b.decode(enc) except UnicodeDecodeError as e: s = "Unable to decode message:\n{}\n{}".format(str(b), e) except (AttributeError, UnicodeEncodeError): # If b is already a string, just return it return b return s