├── LICENSE
├── README.md
├── assets
├── Hakuna Metadata -1.pdf
├── certs.pem
├── css
│ ├── bootstrap-responsive.min.css
│ ├── bootstrap.min.css
│ ├── demo.css
│ └── introjs.css
├── img
│ ├── edri_logo_WEB.png
│ └── lobbyletter_banner.png
├── js
│ └── intro.js
├── pages
│ ├── README.md
│ ├── facebook.html
│ ├── images.html
│ ├── stats.py
│ └── twitter.html
└── stanford-ner-2016-10-31
│ ├── LICENSE.txt
│ ├── NERDemo.java
│ ├── README.txt
│ ├── build.xml
│ ├── classifiers
│ ├── english.all.3class.distsim.crf.ser.gz
│ ├── english.all.3class.distsim.prop
│ ├── english.conll.4class.distsim.crf.ser.gz
│ ├── english.conll.4class.distsim.prop
│ ├── english.muc.7class.distsim.crf.ser.gz
│ ├── english.muc.7class.distsim.prop
│ ├── example.serialized.ncc.ncc.ser.gz
│ └── example.serialized.ncc.prop
│ ├── lib
│ ├── joda-time.jar
│ ├── jollyday-0.4.9.jar
│ └── stanford-ner-resources.jar
│ ├── ner-gui.bat
│ ├── ner-gui.command
│ ├── ner-gui.sh
│ ├── ner.bat
│ ├── ner.sh
│ ├── sample-conll-file.txt
│ ├── sample-w-time.txt
│ ├── sample.ner.txt
│ ├── sample.txt
│ ├── stanford-ner-3.7.0-javadoc.jar
│ ├── stanford-ner-3.7.0-sources.jar
│ ├── stanford-ner-3.7.0.jar
│ └── stanford-ner.jar
├── index.html
├── requirements
├── requirements-iOS
├── tool-iOS.py
└── tool.py
/LICENSE:
--------------------------------------------------------------------------------
1 | GNU GENERAL PUBLIC LICENSE
2 | Version 3, 29 June 2007
3 |
4 | Copyright (C) 2007 Free Software Foundation, Inc.
5 | Everyone is permitted to copy and distribute verbatim copies
6 | of this license document, but changing it is not allowed.
7 |
8 | Preamble
9 |
10 | The GNU General Public License is a free, copyleft license for
11 | software and other kinds of works.
12 |
13 | The licenses for most software and other practical works are designed
14 | to take away your freedom to share and change the works. By contrast,
15 | the GNU General Public License is intended to guarantee your freedom to
16 | share and change all versions of a program--to make sure it remains free
17 | software for all its users. We, the Free Software Foundation, use the
18 | GNU General Public License for most of our software; it applies also to
19 | any other work released this way by its authors. You can apply it to
20 | your programs, too.
21 |
22 | When we speak of free software, we are referring to freedom, not
23 | price. Our General Public Licenses are designed to make sure that you
24 | have the freedom to distribute copies of free software (and charge for
25 | them if you wish), that you receive source code or can get it if you
26 | want it, that you can change the software or use pieces of it in new
27 | free programs, and that you know you can do these things.
28 |
29 | To protect your rights, we need to prevent others from denying you
30 | these rights or asking you to surrender the rights. Therefore, you have
31 | certain responsibilities if you distribute copies of the software, or if
32 | you modify it: responsibilities to respect the freedom of others.
33 |
34 | For example, if you distribute copies of such a program, whether
35 | gratis or for a fee, you must pass on to the recipients the same
36 | freedoms that you received. You must make sure that they, too, receive
37 | or can get the source code. And you must show them these terms so they
38 | know their rights.
39 |
40 | Developers that use the GNU GPL protect your rights with two steps:
41 | (1) assert copyright on the software, and (2) offer you this License
42 | giving you legal permission to copy, distribute and/or modify it.
43 |
44 | For the developers' and authors' protection, the GPL clearly explains
45 | that there is no warranty for this free software. For both users' and
46 | authors' sake, the GPL requires that modified versions be marked as
47 | changed, so that their problems will not be attributed erroneously to
48 | authors of previous versions.
49 |
50 | Some devices are designed to deny users access to install or run
51 | modified versions of the software inside them, although the manufacturer
52 | can do so. This is fundamentally incompatible with the aim of
53 | protecting users' freedom to change the software. The systematic
54 | pattern of such abuse occurs in the area of products for individuals to
55 | use, which is precisely where it is most unacceptable. Therefore, we
56 | have designed this version of the GPL to prohibit the practice for those
57 | products. If such problems arise substantially in other domains, we
58 | stand ready to extend this provision to those domains in future versions
59 | of the GPL, as needed to protect the freedom of users.
60 |
61 | Finally, every program is threatened constantly by software patents.
62 | States should not allow patents to restrict development and use of
63 | software on general-purpose computers, but in those that do, we wish to
64 | avoid the special danger that patents applied to a free program could
65 | make it effectively proprietary. To prevent this, the GPL assures that
66 | patents cannot be used to render the program non-free.
67 |
68 | The precise terms and conditions for copying, distribution and
69 | modification follow.
70 |
71 | TERMS AND CONDITIONS
72 |
73 | 0. Definitions.
74 |
75 | "This License" refers to version 3 of the GNU General Public License.
76 |
77 | "Copyright" also means copyright-like laws that apply to other kinds of
78 | works, such as semiconductor masks.
79 |
80 | "The Program" refers to any copyrightable work licensed under this
81 | License. Each licensee is addressed as "you". "Licensees" and
82 | "recipients" may be individuals or organizations.
83 |
84 | To "modify" a work means to copy from or adapt all or part of the work
85 | in a fashion requiring copyright permission, other than the making of an
86 | exact copy. The resulting work is called a "modified version" of the
87 | earlier work or a work "based on" the earlier work.
88 |
89 | A "covered work" means either the unmodified Program or a work based
90 | on the Program.
91 |
92 | To "propagate" a work means to do anything with it that, without
93 | permission, would make you directly or secondarily liable for
94 | infringement under applicable copyright law, except executing it on a
95 | computer or modifying a private copy. Propagation includes copying,
96 | distribution (with or without modification), making available to the
97 | public, and in some countries other activities as well.
98 |
99 | To "convey" a work means any kind of propagation that enables other
100 | parties to make or receive copies. Mere interaction with a user through
101 | a computer network, with no transfer of a copy, is not conveying.
102 |
103 | An interactive user interface displays "Appropriate Legal Notices"
104 | to the extent that it includes a convenient and prominently visible
105 | feature that (1) displays an appropriate copyright notice, and (2)
106 | tells the user that there is no warranty for the work (except to the
107 | extent that warranties are provided), that licensees may convey the
108 | work under this License, and how to view a copy of this License. If
109 | the interface presents a list of user commands or options, such as a
110 | menu, a prominent item in the list meets this criterion.
111 |
112 | 1. Source Code.
113 |
114 | The "source code" for a work means the preferred form of the work
115 | for making modifications to it. "Object code" means any non-source
116 | form of a work.
117 |
118 | A "Standard Interface" means an interface that either is an official
119 | standard defined by a recognized standards body, or, in the case of
120 | interfaces specified for a particular programming language, one that
121 | is widely used among developers working in that language.
122 |
123 | The "System Libraries" of an executable work include anything, other
124 | than the work as a whole, that (a) is included in the normal form of
125 | packaging a Major Component, but which is not part of that Major
126 | Component, and (b) serves only to enable use of the work with that
127 | Major Component, or to implement a Standard Interface for which an
128 | implementation is available to the public in source code form. A
129 | "Major Component", in this context, means a major essential component
130 | (kernel, window system, and so on) of the specific operating system
131 | (if any) on which the executable work runs, or a compiler used to
132 | produce the work, or an object code interpreter used to run it.
133 |
134 | The "Corresponding Source" for a work in object code form means all
135 | the source code needed to generate, install, and (for an executable
136 | work) run the object code and to modify the work, including scripts to
137 | control those activities. However, it does not include the work's
138 | System Libraries, or general-purpose tools or generally available free
139 | programs which are used unmodified in performing those activities but
140 | which are not part of the work. For example, Corresponding Source
141 | includes interface definition files associated with source files for
142 | the work, and the source code for shared libraries and dynamically
143 | linked subprograms that the work is specifically designed to require,
144 | such as by intimate data communication or control flow between those
145 | subprograms and other parts of the work.
146 |
147 | The Corresponding Source need not include anything that users
148 | can regenerate automatically from other parts of the Corresponding
149 | Source.
150 |
151 | The Corresponding Source for a work in source code form is that
152 | same work.
153 |
154 | 2. Basic Permissions.
155 |
156 | All rights granted under this License are granted for the term of
157 | copyright on the Program, and are irrevocable provided the stated
158 | conditions are met. This License explicitly affirms your unlimited
159 | permission to run the unmodified Program. The output from running a
160 | covered work is covered by this License only if the output, given its
161 | content, constitutes a covered work. This License acknowledges your
162 | rights of fair use or other equivalent, as provided by copyright law.
163 |
164 | You may make, run and propagate covered works that you do not
165 | convey, without conditions so long as your license otherwise remains
166 | in force. You may convey covered works to others for the sole purpose
167 | of having them make modifications exclusively for you, or provide you
168 | with facilities for running those works, provided that you comply with
169 | the terms of this License in conveying all material for which you do
170 | not control copyright. Those thus making or running the covered works
171 | for you must do so exclusively on your behalf, under your direction
172 | and control, on terms that prohibit them from making any copies of
173 | your copyrighted material outside their relationship with you.
174 |
175 | Conveying under any other circumstances is permitted solely under
176 | the conditions stated below. Sublicensing is not allowed; section 10
177 | makes it unnecessary.
178 |
179 | 3. Protecting Users' Legal Rights From Anti-Circumvention Law.
180 |
181 | No covered work shall be deemed part of an effective technological
182 | measure under any applicable law fulfilling obligations under article
183 | 11 of the WIPO copyright treaty adopted on 20 December 1996, or
184 | similar laws prohibiting or restricting circumvention of such
185 | measures.
186 |
187 | When you convey a covered work, you waive any legal power to forbid
188 | circumvention of technological measures to the extent such circumvention
189 | is effected by exercising rights under this License with respect to
190 | the covered work, and you disclaim any intention to limit operation or
191 | modification of the work as a means of enforcing, against the work's
192 | users, your or third parties' legal rights to forbid circumvention of
193 | technological measures.
194 |
195 | 4. Conveying Verbatim Copies.
196 |
197 | You may convey verbatim copies of the Program's source code as you
198 | receive it, in any medium, provided that you conspicuously and
199 | appropriately publish on each copy an appropriate copyright notice;
200 | keep intact all notices stating that this License and any
201 | non-permissive terms added in accord with section 7 apply to the code;
202 | keep intact all notices of the absence of any warranty; and give all
203 | recipients a copy of this License along with the Program.
204 |
205 | You may charge any price or no price for each copy that you convey,
206 | and you may offer support or warranty protection for a fee.
207 |
208 | 5. Conveying Modified Source Versions.
209 |
210 | You may convey a work based on the Program, or the modifications to
211 | produce it from the Program, in the form of source code under the
212 | terms of section 4, provided that you also meet all of these conditions:
213 |
214 | a) The work must carry prominent notices stating that you modified
215 | it, and giving a relevant date.
216 |
217 | b) The work must carry prominent notices stating that it is
218 | released under this License and any conditions added under section
219 | 7. This requirement modifies the requirement in section 4 to
220 | "keep intact all notices".
221 |
222 | c) You must license the entire work, as a whole, under this
223 | License to anyone who comes into possession of a copy. This
224 | License will therefore apply, along with any applicable section 7
225 | additional terms, to the whole of the work, and all its parts,
226 | regardless of how they are packaged. This License gives no
227 | permission to license the work in any other way, but it does not
228 | invalidate such permission if you have separately received it.
229 |
230 | d) If the work has interactive user interfaces, each must display
231 | Appropriate Legal Notices; however, if the Program has interactive
232 | interfaces that do not display Appropriate Legal Notices, your
233 | work need not make them do so.
234 |
235 | A compilation of a covered work with other separate and independent
236 | works, which are not by their nature extensions of the covered work,
237 | and which are not combined with it such as to form a larger program,
238 | in or on a volume of a storage or distribution medium, is called an
239 | "aggregate" if the compilation and its resulting copyright are not
240 | used to limit the access or legal rights of the compilation's users
241 | beyond what the individual works permit. Inclusion of a covered work
242 | in an aggregate does not cause this License to apply to the other
243 | parts of the aggregate.
244 |
245 | 6. Conveying Non-Source Forms.
246 |
247 | You may convey a covered work in object code form under the terms
248 | of sections 4 and 5, provided that you also convey the
249 | machine-readable Corresponding Source under the terms of this License,
250 | in one of these ways:
251 |
252 | a) Convey the object code in, or embodied in, a physical product
253 | (including a physical distribution medium), accompanied by the
254 | Corresponding Source fixed on a durable physical medium
255 | customarily used for software interchange.
256 |
257 | b) Convey the object code in, or embodied in, a physical product
258 | (including a physical distribution medium), accompanied by a
259 | written offer, valid for at least three years and valid for as
260 | long as you offer spare parts or customer support for that product
261 | model, to give anyone who possesses the object code either (1) a
262 | copy of the Corresponding Source for all the software in the
263 | product that is covered by this License, on a durable physical
264 | medium customarily used for software interchange, for a price no
265 | more than your reasonable cost of physically performing this
266 | conveying of source, or (2) access to copy the
267 | Corresponding Source from a network server at no charge.
268 |
269 | c) Convey individual copies of the object code with a copy of the
270 | written offer to provide the Corresponding Source. This
271 | alternative is allowed only occasionally and noncommercially, and
272 | only if you received the object code with such an offer, in accord
273 | with subsection 6b.
274 |
275 | d) Convey the object code by offering access from a designated
276 | place (gratis or for a charge), and offer equivalent access to the
277 | Corresponding Source in the same way through the same place at no
278 | further charge. You need not require recipients to copy the
279 | Corresponding Source along with the object code. If the place to
280 | copy the object code is a network server, the Corresponding Source
281 | may be on a different server (operated by you or a third party)
282 | that supports equivalent copying facilities, provided you maintain
283 | clear directions next to the object code saying where to find the
284 | Corresponding Source. Regardless of what server hosts the
285 | Corresponding Source, you remain obligated to ensure that it is
286 | available for as long as needed to satisfy these requirements.
287 |
288 | e) Convey the object code using peer-to-peer transmission, provided
289 | you inform other peers where the object code and Corresponding
290 | Source of the work are being offered to the general public at no
291 | charge under subsection 6d.
292 |
293 | A separable portion of the object code, whose source code is excluded
294 | from the Corresponding Source as a System Library, need not be
295 | included in conveying the object code work.
296 |
297 | A "User Product" is either (1) a "consumer product", which means any
298 | tangible personal property which is normally used for personal, family,
299 | or household purposes, or (2) anything designed or sold for incorporation
300 | into a dwelling. In determining whether a product is a consumer product,
301 | doubtful cases shall be resolved in favor of coverage. For a particular
302 | product received by a particular user, "normally used" refers to a
303 | typical or common use of that class of product, regardless of the status
304 | of the particular user or of the way in which the particular user
305 | actually uses, or expects or is expected to use, the product. A product
306 | is a consumer product regardless of whether the product has substantial
307 | commercial, industrial or non-consumer uses, unless such uses represent
308 | the only significant mode of use of the product.
309 |
310 | "Installation Information" for a User Product means any methods,
311 | procedures, authorization keys, or other information required to install
312 | and execute modified versions of a covered work in that User Product from
313 | a modified version of its Corresponding Source. The information must
314 | suffice to ensure that the continued functioning of the modified object
315 | code is in no case prevented or interfered with solely because
316 | modification has been made.
317 |
318 | If you convey an object code work under this section in, or with, or
319 | specifically for use in, a User Product, and the conveying occurs as
320 | part of a transaction in which the right of possession and use of the
321 | User Product is transferred to the recipient in perpetuity or for a
322 | fixed term (regardless of how the transaction is characterized), the
323 | Corresponding Source conveyed under this section must be accompanied
324 | by the Installation Information. But this requirement does not apply
325 | if neither you nor any third party retains the ability to install
326 | modified object code on the User Product (for example, the work has
327 | been installed in ROM).
328 |
329 | The requirement to provide Installation Information does not include a
330 | requirement to continue to provide support service, warranty, or updates
331 | for a work that has been modified or installed by the recipient, or for
332 | the User Product in which it has been modified or installed. Access to a
333 | network may be denied when the modification itself materially and
334 | adversely affects the operation of the network or violates the rules and
335 | protocols for communication across the network.
336 |
337 | Corresponding Source conveyed, and Installation Information provided,
338 | in accord with this section must be in a format that is publicly
339 | documented (and with an implementation available to the public in
340 | source code form), and must require no special password or key for
341 | unpacking, reading or copying.
342 |
343 | 7. Additional Terms.
344 |
345 | "Additional permissions" are terms that supplement the terms of this
346 | License by making exceptions from one or more of its conditions.
347 | Additional permissions that are applicable to the entire Program shall
348 | be treated as though they were included in this License, to the extent
349 | that they are valid under applicable law. If additional permissions
350 | apply only to part of the Program, that part may be used separately
351 | under those permissions, but the entire Program remains governed by
352 | this License without regard to the additional permissions.
353 |
354 | When you convey a copy of a covered work, you may at your option
355 | remove any additional permissions from that copy, or from any part of
356 | it. (Additional permissions may be written to require their own
357 | removal in certain cases when you modify the work.) You may place
358 | additional permissions on material, added by you to a covered work,
359 | for which you have or can give appropriate copyright permission.
360 |
361 | Notwithstanding any other provision of this License, for material you
362 | add to a covered work, you may (if authorized by the copyright holders of
363 | that material) supplement the terms of this License with terms:
364 |
365 | a) Disclaiming warranty or limiting liability differently from the
366 | terms of sections 15 and 16 of this License; or
367 |
368 | b) Requiring preservation of specified reasonable legal notices or
369 | author attributions in that material or in the Appropriate Legal
370 | Notices displayed by works containing it; or
371 |
372 | c) Prohibiting misrepresentation of the origin of that material, or
373 | requiring that modified versions of such material be marked in
374 | reasonable ways as different from the original version; or
375 |
376 | d) Limiting the use for publicity purposes of names of licensors or
377 | authors of the material; or
378 |
379 | e) Declining to grant rights under trademark law for use of some
380 | trade names, trademarks, or service marks; or
381 |
382 | f) Requiring indemnification of licensors and authors of that
383 | material by anyone who conveys the material (or modified versions of
384 | it) with contractual assumptions of liability to the recipient, for
385 | any liability that these contractual assumptions directly impose on
386 | those licensors and authors.
387 |
388 | All other non-permissive additional terms are considered "further
389 | restrictions" within the meaning of section 10. If the Program as you
390 | received it, or any part of it, contains a notice stating that it is
391 | governed by this License along with a term that is a further
392 | restriction, you may remove that term. If a license document contains
393 | a further restriction but permits relicensing or conveying under this
394 | License, you may add to a covered work material governed by the terms
395 | of that license document, provided that the further restriction does
396 | not survive such relicensing or conveying.
397 |
398 | If you add terms to a covered work in accord with this section, you
399 | must place, in the relevant source files, a statement of the
400 | additional terms that apply to those files, or a notice indicating
401 | where to find the applicable terms.
402 |
403 | Additional terms, permissive or non-permissive, may be stated in the
404 | form of a separately written license, or stated as exceptions;
405 | the above requirements apply either way.
406 |
407 | 8. Termination.
408 |
409 | You may not propagate or modify a covered work except as expressly
410 | provided under this License. Any attempt otherwise to propagate or
411 | modify it is void, and will automatically terminate your rights under
412 | this License (including any patent licenses granted under the third
413 | paragraph of section 11).
414 |
415 | However, if you cease all violation of this License, then your
416 | license from a particular copyright holder is reinstated (a)
417 | provisionally, unless and until the copyright holder explicitly and
418 | finally terminates your license, and (b) permanently, if the copyright
419 | holder fails to notify you of the violation by some reasonable means
420 | prior to 60 days after the cessation.
421 |
422 | Moreover, your license from a particular copyright holder is
423 | reinstated permanently if the copyright holder notifies you of the
424 | violation by some reasonable means, this is the first time you have
425 | received notice of violation of this License (for any work) from that
426 | copyright holder, and you cure the violation prior to 30 days after
427 | your receipt of the notice.
428 |
429 | Termination of your rights under this section does not terminate the
430 | licenses of parties who have received copies or rights from you under
431 | this License. If your rights have been terminated and not permanently
432 | reinstated, you do not qualify to receive new licenses for the same
433 | material under section 10.
434 |
435 | 9. Acceptance Not Required for Having Copies.
436 |
437 | You are not required to accept this License in order to receive or
438 | run a copy of the Program. Ancillary propagation of a covered work
439 | occurring solely as a consequence of using peer-to-peer transmission
440 | to receive a copy likewise does not require acceptance. However,
441 | nothing other than this License grants you permission to propagate or
442 | modify any covered work. These actions infringe copyright if you do
443 | not accept this License. Therefore, by modifying or propagating a
444 | covered work, you indicate your acceptance of this License to do so.
445 |
446 | 10. Automatic Licensing of Downstream Recipients.
447 |
448 | Each time you convey a covered work, the recipient automatically
449 | receives a license from the original licensors, to run, modify and
450 | propagate that work, subject to this License. You are not responsible
451 | for enforcing compliance by third parties with this License.
452 |
453 | An "entity transaction" is a transaction transferring control of an
454 | organization, or substantially all assets of one, or subdividing an
455 | organization, or merging organizations. If propagation of a covered
456 | work results from an entity transaction, each party to that
457 | transaction who receives a copy of the work also receives whatever
458 | licenses to the work the party's predecessor in interest had or could
459 | give under the previous paragraph, plus a right to possession of the
460 | Corresponding Source of the work from the predecessor in interest, if
461 | the predecessor has it or can get it with reasonable efforts.
462 |
463 | You may not impose any further restrictions on the exercise of the
464 | rights granted or affirmed under this License. For example, you may
465 | not impose a license fee, royalty, or other charge for exercise of
466 | rights granted under this License, and you may not initiate litigation
467 | (including a cross-claim or counterclaim in a lawsuit) alleging that
468 | any patent claim is infringed by making, using, selling, offering for
469 | sale, or importing the Program or any portion of it.
470 |
471 | 11. Patents.
472 |
473 | A "contributor" is a copyright holder who authorizes use under this
474 | License of the Program or a work on which the Program is based. The
475 | work thus licensed is called the contributor's "contributor version".
476 |
477 | A contributor's "essential patent claims" are all patent claims
478 | owned or controlled by the contributor, whether already acquired or
479 | hereafter acquired, that would be infringed by some manner, permitted
480 | by this License, of making, using, or selling its contributor version,
481 | but do not include claims that would be infringed only as a
482 | consequence of further modification of the contributor version. For
483 | purposes of this definition, "control" includes the right to grant
484 | patent sublicenses in a manner consistent with the requirements of
485 | this License.
486 |
487 | Each contributor grants you a non-exclusive, worldwide, royalty-free
488 | patent license under the contributor's essential patent claims, to
489 | make, use, sell, offer for sale, import and otherwise run, modify and
490 | propagate the contents of its contributor version.
491 |
492 | In the following three paragraphs, a "patent license" is any express
493 | agreement or commitment, however denominated, not to enforce a patent
494 | (such as an express permission to practice a patent or covenant not to
495 | sue for patent infringement). To "grant" such a patent license to a
496 | party means to make such an agreement or commitment not to enforce a
497 | patent against the party.
498 |
499 | If you convey a covered work, knowingly relying on a patent license,
500 | and the Corresponding Source of the work is not available for anyone
501 | to copy, free of charge and under the terms of this License, through a
502 | publicly available network server or other readily accessible means,
503 | then you must either (1) cause the Corresponding Source to be so
504 | available, or (2) arrange to deprive yourself of the benefit of the
505 | patent license for this particular work, or (3) arrange, in a manner
506 | consistent with the requirements of this License, to extend the patent
507 | license to downstream recipients. "Knowingly relying" means you have
508 | actual knowledge that, but for the patent license, your conveying the
509 | covered work in a country, or your recipient's use of the covered work
510 | in a country, would infringe one or more identifiable patents in that
511 | country that you have reason to believe are valid.
512 |
513 | If, pursuant to or in connection with a single transaction or
514 | arrangement, you convey, or propagate by procuring conveyance of, a
515 | covered work, and grant a patent license to some of the parties
516 | receiving the covered work authorizing them to use, propagate, modify
517 | or convey a specific copy of the covered work, then the patent license
518 | you grant is automatically extended to all recipients of the covered
519 | work and works based on it.
520 |
521 | A patent license is "discriminatory" if it does not include within
522 | the scope of its coverage, prohibits the exercise of, or is
523 | conditioned on the non-exercise of one or more of the rights that are
524 | specifically granted under this License. You may not convey a covered
525 | work if you are a party to an arrangement with a third party that is
526 | in the business of distributing software, under which you make payment
527 | to the third party based on the extent of your activity of conveying
528 | the work, and under which the third party grants, to any of the
529 | parties who would receive the covered work from you, a discriminatory
530 | patent license (a) in connection with copies of the covered work
531 | conveyed by you (or copies made from those copies), or (b) primarily
532 | for and in connection with specific products or compilations that
533 | contain the covered work, unless you entered into that arrangement,
534 | or that patent license was granted, prior to 28 March 2007.
535 |
536 | Nothing in this License shall be construed as excluding or limiting
537 | any implied license or other defenses to infringement that may
538 | otherwise be available to you under applicable patent law.
539 |
540 | 12. No Surrender of Others' Freedom.
541 |
542 | If conditions are imposed on you (whether by court order, agreement or
543 | otherwise) that contradict the conditions of this License, they do not
544 | excuse you from the conditions of this License. If you cannot convey a
545 | covered work so as to satisfy simultaneously your obligations under this
546 | License and any other pertinent obligations, then as a consequence you may
547 | not convey it at all. For example, if you agree to terms that obligate you
548 | to collect a royalty for further conveying from those to whom you convey
549 | the Program, the only way you could satisfy both those terms and this
550 | License would be to refrain entirely from conveying the Program.
551 |
552 | 13. Use with the GNU Affero General Public License.
553 |
554 | Notwithstanding any other provision of this License, you have
555 | permission to link or combine any covered work with a work licensed
556 | under version 3 of the GNU Affero General Public License into a single
557 | combined work, and to convey the resulting work. The terms of this
558 | License will continue to apply to the part which is the covered work,
559 | but the special requirements of the GNU Affero General Public License,
560 | section 13, concerning interaction through a network will apply to the
561 | combination as such.
562 |
563 | 14. Revised Versions of this License.
564 |
565 | The Free Software Foundation may publish revised and/or new versions of
566 | the GNU General Public License from time to time. Such new versions will
567 | be similar in spirit to the present version, but may differ in detail to
568 | address new problems or concerns.
569 |
570 | Each version is given a distinguishing version number. If the
571 | Program specifies that a certain numbered version of the GNU General
572 | Public License "or any later version" applies to it, you have the
573 | option of following the terms and conditions either of that numbered
574 | version or of any later version published by the Free Software
575 | Foundation. If the Program does not specify a version number of the
576 | GNU General Public License, you may choose any version ever published
577 | by the Free Software Foundation.
578 |
579 | If the Program specifies that a proxy can decide which future
580 | versions of the GNU General Public License can be used, that proxy's
581 | public statement of acceptance of a version permanently authorizes you
582 | to choose that version for the Program.
583 |
584 | Later license versions may give you additional or different
585 | permissions. However, no additional obligations are imposed on any
586 | author or copyright holder as a result of your choosing to follow a
587 | later version.
588 |
589 | 15. Disclaimer of Warranty.
590 |
591 | THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
592 | APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
593 | HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
594 | OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
595 | THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
596 | PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
597 | IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
598 | ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
599 |
600 | 16. Limitation of Liability.
601 |
602 | IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
603 | WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
604 | THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
605 | GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
606 | USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
607 | DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
608 | PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
609 | EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
610 | SUCH DAMAGES.
611 |
612 | 17. Interpretation of Sections 15 and 16.
613 |
614 | If the disclaimer of warranty and limitation of liability provided
615 | above cannot be given local legal effect according to their terms,
616 | reviewing courts shall apply local law that most closely approximates
617 | an absolute waiver of all civil liability in connection with the
618 | Program, unless a warranty or assumption of liability accompanies a
619 | copy of the Program in return for a fee.
620 |
621 | END OF TERMS AND CONDITIONS
622 |
623 | How to Apply These Terms to Your New Programs
624 |
625 | If you develop a new program, and you want it to be of the greatest
626 | possible use to the public, the best way to achieve this is to make it
627 | free software which everyone can redistribute and change under these terms.
628 |
629 | To do so, attach the following notices to the program. It is safest
630 | to attach them to the start of each source file to most effectively
631 | state the exclusion of warranty; and each file should have at least
632 | the "copyright" line and a pointer to where the full notice is found.
633 |
634 | {one line to give the program's name and a brief idea of what it does.}
635 | Copyright (C) {year} {name of author}
636 |
637 | This program is free software: you can redistribute it and/or modify
638 | it under the terms of the GNU General Public License as published by
639 | the Free Software Foundation, either version 3 of the License, or
640 | (at your option) any later version.
641 |
642 | This program is distributed in the hope that it will be useful,
643 | but WITHOUT ANY WARRANTY; without even the implied warranty of
644 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
645 | GNU General Public License for more details.
646 |
647 | You should have received a copy of the GNU General Public License
648 | along with this program. If not, see .
649 |
650 | Also add information on how to contact you by electronic and paper mail.
651 |
652 | If the program does terminal interaction, make it output a short
653 | notice like this when it starts in an interactive mode:
654 |
655 | {project} Copyright (C) {year} {fullname}
656 | This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
657 | This is free software, and you are welcome to redistribute it
658 | under certain conditions; type `show c' for details.
659 |
660 | The hypothetical commands `show w' and `show c' should show the appropriate
661 | parts of the General Public License. Of course, your program's commands
662 | might be different; for a GUI interface, you would use an "about box".
663 |
664 | You should also get your employer (if you work as a programmer) or school,
665 | if any, to sign a "copyright disclaimer" for the program, if necessary.
666 | For more information on this, and how to apply and follow the GNU GPL, see
667 | .
668 |
669 | The GNU General Public License does not permit incorporating your program
670 | into proprietary programs. If your program is a subroutine library, you
671 | may consider it more useful to permit linking proprietary applications with
672 | the library. If this is what you want to do, use the GNU Lesser General
673 | Public License instead of this License. But first, please read
674 | .
675 |
--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
1 | # Hakuna Metadata - 1
2 |
3 | Browsing history visualization for (Linux or Apple) + Firefox combo.
4 |
5 | P.S: Read the [blog post](https://www.privacypies.org/projects/2017/02/28/hakuna-metadata.html) before trying this tool.
6 |
7 |
8 | ## Install instructions
9 |
10 | ### For Linux
11 | - Download and unzip this repository.
12 | - In the unzipped folder on your computer, right click on an empty space and select "Open in terminal" option.
13 | - In the terminal, type **sh requirements** and press Enter.
14 | - The above command will install all the dependencies.
15 | - In the terminal, type **python tool.py** and press Enter.
16 | - Be patient, it might take a while. Once the program execution is done, it automatically opens up a web browser tab and displays the visualization.
17 |
18 | ### For Apple macOS
19 | - Download and unzip this repository.
20 | - If you don't have Java installed, install it from [here](http://download.oracle.com/otn-pub/java/jdk/8u131-b11/d54c1d3a095b4ff2b6607d096fa80163/jdk-8u131-macosx-x64.dmg)
21 | - In the unzipped folder on your computer, right click on an empty space and select "Open in terminal" option.
22 | - In the terminal, type **sh requirements-iOS** and press Enter.
23 | - The above command will install all the dependencies.
24 | - In the terminal, type **python tool-iOS.py** and press Enter.
25 | - Be patient, it might take a while. Once the program execution is done, it automatically opens up a web browser tab and displays the visualization.
26 |
27 |
28 |
29 | # Screenshots of working example
30 |
31 | 
32 |
51 |
52 |
53 |
54 |
55 |
--------------------------------------------------------------------------------
/assets/pages/stats.py:
--------------------------------------------------------------------------------
1 | """Script that generates the browsing history Visual."""
2 |
3 | import pandas as pd
4 | import tldextract
5 | import sqlite3
6 | from os.path import expanduser
7 | import shutil
8 | import webbrowser
9 | import glob
10 | import json
11 |
12 | # option = 0
13 | # while not int(option) in range(1, 3):
14 | # option = int(input("Select your broswer:\n1.Chrome\n2.Firefox\n"))
15 |
16 | # Chrome
17 | # On Mac: ~/Library/Application\ Support/Google/Chrome/Default/History
18 | # On Windows: C:\Users\YOUR USER NAME\AppData\Local\Google\Chrome\User Data\Default\History
19 | # On Linux: ~/.config/google-chrome/Default/History
20 | home = expanduser("~")
21 | # path = {1: home + "/.config/google-chrome/Default/History",
22 | # 2: glob.glob(home + '/.mozilla/firefox/*/places.sqlite')[0]}
23 | path = glob.glob(home + '/.mozilla/firefox/*/places.sqlite')[0]
24 | shutil.copy2(path, "assets/pages/history.sqlite3")
25 |
26 | # query = {
27 | # 1:
28 | # "select datetime(last_visit_time/1000000-11644473600,'unixepoch') as 'date',url from urls order by last_visit_time desc",
29 | # 2:
30 | # "select datetime(last_visit_date/1000000-11644473600,'unixepoch') as 'date',url from moz_places order by last_visit_date desc"
31 | # }
32 |
33 | query = "select datetime(last_visit_date/1000000-11644473600,'unixepoch') as 'date',url from moz_places order by last_visit_date desc"
34 |
35 | # Read sqlite query results into a pandas DataFrame
36 | con = sqlite3.connect("assets/pages/history.sqlite3", timeout=5)
37 | df = pd.read_sql_query(query, con)
38 | con.close()
39 |
40 | ########################################################################################################
41 | #Below snippet is taken from https://github.com/Dineshkarthik/browsing_history_viz
42 |
43 | ########################################################################################################
44 | def _tld(dns):
45 | ext = tldextract.extract(dns)
46 | return ext.domain
47 |
48 |
49 | def _suffix(dns):
50 | ext = tldextract.extract(dns)
51 | return ext.suffix
52 |
53 |
54 | df["domain"] = df["url"].apply(_tld)
55 | df["suffix"] = df["url"].apply(_suffix)
56 |
57 | s = df.domain.value_counts()
58 | s = s.nlargest(15)
59 | r = df["suffix"].value_counts()
60 | r = r.nlargest(15)
61 |
62 | _dict = {}
63 | _dict["domain"] = s.to_dict()
64 | _dict["suffix"] = r.to_dict()
65 |
66 | json_ = json.dumps(_dict)
67 | with open('assets/pages/data.json', 'w') as savetxt:
68 | savetxt.write(json_)
69 | f = open('assets/pages/stats.html', 'w')
70 | message = """
71 |
72 |
73 |
74 |
75 |
76 | Browsing History
77 |
80 |
81 |
82 |
83 |
84 |
85 |
86 |
87 |
Top 15 most visited domains
88 |
89 |
90 |
Top 15 most visited suffixes
91 |
92 |
93 |
94 |
95 |
97 |
99 |
102 |
103 | """
104 | f.write(message)
105 | f.close()
106 |
107 | ###################################################################################################################
108 |
--------------------------------------------------------------------------------
/assets/pages/twitter.html:
--------------------------------------------------------------------------------
1 |
2 | Twitter social circles
3 |
4 |
46 |
47 |
48 |
123 |
--------------------------------------------------------------------------------
/assets/stanford-ner-2016-10-31/LICENSE.txt:
--------------------------------------------------------------------------------
1 | GNU GENERAL PUBLIC LICENSE
2 | Version 2, June 1991
3 |
4 | Copyright (C) 1989, 1991 Free Software Foundation, Inc.,
5 | 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
6 | Everyone is permitted to copy and distribute verbatim copies
7 | of this license document, but changing it is not allowed.
8 |
9 | Preamble
10 |
11 | The licenses for most software are designed to take away your
12 | freedom to share and change it. By contrast, the GNU General Public
13 | License is intended to guarantee your freedom to share and change free
14 | software--to make sure the software is free for all its users. This
15 | General Public License applies to most of the Free Software
16 | Foundation's software and to any other program whose authors commit to
17 | using it. (Some other Free Software Foundation software is covered by
18 | the GNU Lesser General Public License instead.) You can apply it to
19 | your programs, too.
20 |
21 | When we speak of free software, we are referring to freedom, not
22 | price. Our General Public Licenses are designed to make sure that you
23 | have the freedom to distribute copies of free software (and charge for
24 | this service if you wish), that you receive source code or can get it
25 | if you want it, that you can change the software or use pieces of it
26 | in new free programs; and that you know you can do these things.
27 |
28 | To protect your rights, we need to make restrictions that forbid
29 | anyone to deny you these rights or to ask you to surrender the rights.
30 | These restrictions translate to certain responsibilities for you if you
31 | distribute copies of the software, or if you modify it.
32 |
33 | For example, if you distribute copies of such a program, whether
34 | gratis or for a fee, you must give the recipients all the rights that
35 | you have. You must make sure that they, too, receive or can get the
36 | source code. And you must show them these terms so they know their
37 | rights.
38 |
39 | We protect your rights with two steps: (1) copyright the software, and
40 | (2) offer you this license which gives you legal permission to copy,
41 | distribute and/or modify the software.
42 |
43 | Also, for each author's protection and ours, we want to make certain
44 | that everyone understands that there is no warranty for this free
45 | software. If the software is modified by someone else and passed on, we
46 | want its recipients to know that what they have is not the original, so
47 | that any problems introduced by others will not reflect on the original
48 | authors' reputations.
49 |
50 | Finally, any free program is threatened constantly by software
51 | patents. We wish to avoid the danger that redistributors of a free
52 | program will individually obtain patent licenses, in effect making the
53 | program proprietary. To prevent this, we have made it clear that any
54 | patent must be licensed for everyone's free use or not licensed at all.
55 |
56 | The precise terms and conditions for copying, distribution and
57 | modification follow.
58 |
59 | GNU GENERAL PUBLIC LICENSE
60 | TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
61 |
62 | 0. This License applies to any program or other work which contains
63 | a notice placed by the copyright holder saying it may be distributed
64 | under the terms of this General Public License. The "Program", below,
65 | refers to any such program or work, and a "work based on the Program"
66 | means either the Program or any derivative work under copyright law:
67 | that is to say, a work containing the Program or a portion of it,
68 | either verbatim or with modifications and/or translated into another
69 | language. (Hereinafter, translation is included without limitation in
70 | the term "modification".) Each licensee is addressed as "you".
71 |
72 | Activities other than copying, distribution and modification are not
73 | covered by this License; they are outside its scope. The act of
74 | running the Program is not restricted, and the output from the Program
75 | is covered only if its contents constitute a work based on the
76 | Program (independent of having been made by running the Program).
77 | Whether that is true depends on what the Program does.
78 |
79 | 1. You may copy and distribute verbatim copies of the Program's
80 | source code as you receive it, in any medium, provided that you
81 | conspicuously and appropriately publish on each copy an appropriate
82 | copyright notice and disclaimer of warranty; keep intact all the
83 | notices that refer to this License and to the absence of any warranty;
84 | and give any other recipients of the Program a copy of this License
85 | along with the Program.
86 |
87 | You may charge a fee for the physical act of transferring a copy, and
88 | you may at your option offer warranty protection in exchange for a fee.
89 |
90 | 2. You may modify your copy or copies of the Program or any portion
91 | of it, thus forming a work based on the Program, and copy and
92 | distribute such modifications or work under the terms of Section 1
93 | above, provided that you also meet all of these conditions:
94 |
95 | a) You must cause the modified files to carry prominent notices
96 | stating that you changed the files and the date of any change.
97 |
98 | b) You must cause any work that you distribute or publish, that in
99 | whole or in part contains or is derived from the Program or any
100 | part thereof, to be licensed as a whole at no charge to all third
101 | parties under the terms of this License.
102 |
103 | c) If the modified program normally reads commands interactively
104 | when run, you must cause it, when started running for such
105 | interactive use in the most ordinary way, to print or display an
106 | announcement including an appropriate copyright notice and a
107 | notice that there is no warranty (or else, saying that you provide
108 | a warranty) and that users may redistribute the program under
109 | these conditions, and telling the user how to view a copy of this
110 | License. (Exception: if the Program itself is interactive but
111 | does not normally print such an announcement, your work based on
112 | the Program is not required to print an announcement.)
113 |
114 | These requirements apply to the modified work as a whole. If
115 | identifiable sections of that work are not derived from the Program,
116 | and can be reasonably considered independent and separate works in
117 | themselves, then this License, and its terms, do not apply to those
118 | sections when you distribute them as separate works. But when you
119 | distribute the same sections as part of a whole which is a work based
120 | on the Program, the distribution of the whole must be on the terms of
121 | this License, whose permissions for other licensees extend to the
122 | entire whole, and thus to each and every part regardless of who wrote it.
123 |
124 | Thus, it is not the intent of this section to claim rights or contest
125 | your rights to work written entirely by you; rather, the intent is to
126 | exercise the right to control the distribution of derivative or
127 | collective works based on the Program.
128 |
129 | In addition, mere aggregation of another work not based on the Program
130 | with the Program (or with a work based on the Program) on a volume of
131 | a storage or distribution medium does not bring the other work under
132 | the scope of this License.
133 |
134 | 3. You may copy and distribute the Program (or a work based on it,
135 | under Section 2) in object code or executable form under the terms of
136 | Sections 1 and 2 above provided that you also do one of the following:
137 |
138 | a) Accompany it with the complete corresponding machine-readable
139 | source code, which must be distributed under the terms of Sections
140 | 1 and 2 above on a medium customarily used for software interchange; or,
141 |
142 | b) Accompany it with a written offer, valid for at least three
143 | years, to give any third party, for a charge no more than your
144 | cost of physically performing source distribution, a complete
145 | machine-readable copy of the corresponding source code, to be
146 | distributed under the terms of Sections 1 and 2 above on a medium
147 | customarily used for software interchange; or,
148 |
149 | c) Accompany it with the information you received as to the offer
150 | to distribute corresponding source code. (This alternative is
151 | allowed only for noncommercial distribution and only if you
152 | received the program in object code or executable form with such
153 | an offer, in accord with Subsection b above.)
154 |
155 | The source code for a work means the preferred form of the work for
156 | making modifications to it. For an executable work, complete source
157 | code means all the source code for all modules it contains, plus any
158 | associated interface definition files, plus the scripts used to
159 | control compilation and installation of the executable. However, as a
160 | special exception, the source code distributed need not include
161 | anything that is normally distributed (in either source or binary
162 | form) with the major components (compiler, kernel, and so on) of the
163 | operating system on which the executable runs, unless that component
164 | itself accompanies the executable.
165 |
166 | If distribution of executable or object code is made by offering
167 | access to copy from a designated place, then offering equivalent
168 | access to copy the source code from the same place counts as
169 | distribution of the source code, even though third parties are not
170 | compelled to copy the source along with the object code.
171 |
172 | 4. You may not copy, modify, sublicense, or distribute the Program
173 | except as expressly provided under this License. Any attempt
174 | otherwise to copy, modify, sublicense or distribute the Program is
175 | void, and will automatically terminate your rights under this License.
176 | However, parties who have received copies, or rights, from you under
177 | this License will not have their licenses terminated so long as such
178 | parties remain in full compliance.
179 |
180 | 5. You are not required to accept this License, since you have not
181 | signed it. However, nothing else grants you permission to modify or
182 | distribute the Program or its derivative works. These actions are
183 | prohibited by law if you do not accept this License. Therefore, by
184 | modifying or distributing the Program (or any work based on the
185 | Program), you indicate your acceptance of this License to do so, and
186 | all its terms and conditions for copying, distributing or modifying
187 | the Program or works based on it.
188 |
189 | 6. Each time you redistribute the Program (or any work based on the
190 | Program), the recipient automatically receives a license from the
191 | original licensor to copy, distribute or modify the Program subject to
192 | these terms and conditions. You may not impose any further
193 | restrictions on the recipients' exercise of the rights granted herein.
194 | You are not responsible for enforcing compliance by third parties to
195 | this License.
196 |
197 | 7. If, as a consequence of a court judgment or allegation of patent
198 | infringement or for any other reason (not limited to patent issues),
199 | conditions are imposed on you (whether by court order, agreement or
200 | otherwise) that contradict the conditions of this License, they do not
201 | excuse you from the conditions of this License. If you cannot
202 | distribute so as to satisfy simultaneously your obligations under this
203 | License and any other pertinent obligations, then as a consequence you
204 | may not distribute the Program at all. For example, if a patent
205 | license would not permit royalty-free redistribution of the Program by
206 | all those who receive copies directly or indirectly through you, then
207 | the only way you could satisfy both it and this License would be to
208 | refrain entirely from distribution of the Program.
209 |
210 | If any portion of this section is held invalid or unenforceable under
211 | any particular circumstance, the balance of the section is intended to
212 | apply and the section as a whole is intended to apply in other
213 | circumstances.
214 |
215 | It is not the purpose of this section to induce you to infringe any
216 | patents or other property right claims or to contest validity of any
217 | such claims; this section has the sole purpose of protecting the
218 | integrity of the free software distribution system, which is
219 | implemented by public license practices. Many people have made
220 | generous contributions to the wide range of software distributed
221 | through that system in reliance on consistent application of that
222 | system; it is up to the author/donor to decide if he or she is willing
223 | to distribute software through any other system and a licensee cannot
224 | impose that choice.
225 |
226 | This section is intended to make thoroughly clear what is believed to
227 | be a consequence of the rest of this License.
228 |
229 | 8. If the distribution and/or use of the Program is restricted in
230 | certain countries either by patents or by copyrighted interfaces, the
231 | original copyright holder who places the Program under this License
232 | may add an explicit geographical distribution limitation excluding
233 | those countries, so that distribution is permitted only in or among
234 | countries not thus excluded. In such case, this License incorporates
235 | the limitation as if written in the body of this License.
236 |
237 | 9. The Free Software Foundation may publish revised and/or new versions
238 | of the General Public License from time to time. Such new versions will
239 | be similar in spirit to the present version, but may differ in detail to
240 | address new problems or concerns.
241 |
242 | Each version is given a distinguishing version number. If the Program
243 | specifies a version number of this License which applies to it and "any
244 | later version", you have the option of following the terms and conditions
245 | either of that version or of any later version published by the Free
246 | Software Foundation. If the Program does not specify a version number of
247 | this License, you may choose any version ever published by the Free Software
248 | Foundation.
249 |
250 | 10. If you wish to incorporate parts of the Program into other free
251 | programs whose distribution conditions are different, write to the author
252 | to ask for permission. For software which is copyrighted by the Free
253 | Software Foundation, write to the Free Software Foundation; we sometimes
254 | make exceptions for this. Our decision will be guided by the two goals
255 | of preserving the free status of all derivatives of our free software and
256 | of promoting the sharing and reuse of software generally.
257 |
258 | NO WARRANTY
259 |
260 | 11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
261 | FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN
262 | OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES
263 | PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED
264 | OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
265 | MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS
266 | TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE
267 | PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING,
268 | REPAIR OR CORRECTION.
269 |
270 | 12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
271 | WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
272 | REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES,
273 | INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING
274 | OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED
275 | TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY
276 | YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER
277 | PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE
278 | POSSIBILITY OF SUCH DAMAGES.
279 |
280 | END OF TERMS AND CONDITIONS
281 |
282 | How to Apply These Terms to Your New Programs
283 |
284 | If you develop a new program, and you want it to be of the greatest
285 | possible use to the public, the best way to achieve this is to make it
286 | free software which everyone can redistribute and change under these terms.
287 |
288 | To do so, attach the following notices to the program. It is safest
289 | to attach them to the start of each source file to most effectively
290 | convey the exclusion of warranty; and each file should have at least
291 | the "copyright" line and a pointer to where the full notice is found.
292 |
293 |
294 | Copyright (C)
295 |
296 | This program is free software; you can redistribute it and/or modify
297 | it under the terms of the GNU General Public License as published by
298 | the Free Software Foundation; either version 2 of the License, or
299 | (at your option) any later version.
300 |
301 | This program is distributed in the hope that it will be useful,
302 | but WITHOUT ANY WARRANTY; without even the implied warranty of
303 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
304 | GNU General Public License for more details.
305 |
306 | You should have received a copy of the GNU General Public License along
307 | with this program; if not, write to the Free Software Foundation, Inc.,
308 | 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
309 |
310 | Also add information on how to contact you by electronic and paper mail.
311 |
312 | If the program is interactive, make it output a short notice like this
313 | when it starts in an interactive mode:
314 |
315 | Gnomovision version 69, Copyright (C) year name of author
316 | Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
317 | This is free software, and you are welcome to redistribute it
318 | under certain conditions; type `show c' for details.
319 |
320 | The hypothetical commands `show w' and `show c' should show the appropriate
321 | parts of the General Public License. Of course, the commands you use may
322 | be called something other than `show w' and `show c'; they could even be
323 | mouse-clicks or menu items--whatever suits your program.
324 |
325 | You should also get your employer (if you work as a programmer) or your
326 | school, if any, to sign a "copyright disclaimer" for the program, if
327 | necessary. Here is a sample; alter the names:
328 |
329 | Yoyodyne, Inc., hereby disclaims all copyright interest in the program
330 | `Gnomovision' (which makes passes at compilers) written by James Hacker.
331 |
332 | , 1 April 1989
333 | Ty Coon, President of Vice
334 |
335 | This General Public License does not permit incorporating your program into
336 | proprietary programs. If your program is a subroutine library, you may
337 | consider it more useful to permit linking proprietary applications with the
338 | library. If this is what you want to do, use the GNU Lesser General
339 | Public License instead of this License.
340 |
--------------------------------------------------------------------------------
/assets/stanford-ner-2016-10-31/NERDemo.java:
--------------------------------------------------------------------------------
1 | import edu.stanford.nlp.ie.AbstractSequenceClassifier;
2 | import edu.stanford.nlp.ie.crf.*;
3 | import edu.stanford.nlp.io.IOUtils;
4 | import edu.stanford.nlp.ling.CoreLabel;
5 | import edu.stanford.nlp.ling.CoreAnnotations;
6 | import edu.stanford.nlp.sequences.DocumentReaderAndWriter;
7 | import edu.stanford.nlp.util.Triple;
8 |
9 | import java.util.List;
10 |
11 |
12 | /** This is a demo of calling CRFClassifier programmatically.
13 | *
16 | * If arguments aren't specified, they default to
17 | * classifiers/english.all.3class.distsim.crf.ser.gz and some hardcoded sample text.
18 | * If run with arguments, it shows some of the ways to get k-best labelings and
19 | * probabilities out with CRFClassifier. If run without arguments, it shows some of
20 | * the alternative output formats that you can get.
21 | *
22 | * To use CRFClassifier from the command line:
23 | *
26 | * Or if the file is already tokenized and one word per line, perhaps in
27 | * a tab-separated value format with extra columns for part-of-speech tag,
28 | * etc., use the version below (note the 's' instead of the 'x'):
29 | *
32 | *
33 | * @author Jenny Finkel
34 | * @author Christopher Manning
35 | */
36 |
37 | public class NERDemo {
38 |
39 | public static void main(String[] args) throws Exception {
40 |
41 | String serializedClassifier = "classifiers/english.all.3class.distsim.crf.ser.gz";
42 |
43 | if (args.length > 0) {
44 | serializedClassifier = args[0];
45 | }
46 |
47 | AbstractSequenceClassifier classifier = CRFClassifier.getClassifier(serializedClassifier);
48 |
49 | /* For either a file to annotate or for the hardcoded text example, this
50 | demo file shows several ways to process the input, for teaching purposes.
51 | */
52 |
53 | if (args.length > 1) {
54 |
55 | /* For the file, it shows (1) how to run NER on a String, (2) how
56 | to get the entities in the String with character offsets, and
57 | (3) how to run NER on a whole file (without loading it into a String).
58 | */
59 |
60 | String fileContents = IOUtils.slurpFile(args[1]);
61 | List> out = classifier.classify(fileContents);
62 | for (List sentence : out) {
63 | for (CoreLabel word : sentence) {
64 | System.out.print(word.word() + '/' + word.get(CoreAnnotations.AnswerAnnotation.class) + ' ');
65 | }
66 | System.out.println();
67 | }
68 |
69 | System.out.println("---");
70 | out = classifier.classifyFile(args[1]);
71 | for (List sentence : out) {
72 | for (CoreLabel word : sentence) {
73 | System.out.print(word.word() + '/' + word.get(CoreAnnotations.AnswerAnnotation.class) + ' ');
74 | }
75 | System.out.println();
76 | }
77 |
78 | System.out.println("---");
79 | List> list = classifier.classifyToCharacterOffsets(fileContents);
80 | for (Triple item : list) {
81 | System.out.println(item.first() + ": " + fileContents.substring(item.second(), item.third()));
82 | }
83 | System.out.println("---");
84 | System.out.println("Ten best entity labelings");
85 | DocumentReaderAndWriter readerAndWriter = classifier.makePlainTextReaderAndWriter();
86 | classifier.classifyAndWriteAnswersKBest(args[1], 10, readerAndWriter);
87 |
88 | System.out.println("---");
89 | System.out.println("Per-token marginalized probabilities");
90 | classifier.printProbs(args[1], readerAndWriter);
91 |
92 | // -- This code prints out the first order (token pair) clique probabilities.
93 | // -- But that output is a bit overwhelming, so we leave it commented out by default.
94 | // System.out.println("---");
95 | // System.out.println("First Order Clique Probabilities");
96 | // ((CRFClassifier) classifier).printFirstOrderProbs(args[1], readerAndWriter);
97 |
98 | } else {
99 |
100 | /* For the hard-coded String, it shows how to run it on a single
101 | sentence, and how to do this and produce several formats, including
102 | slash tags and an inline XML output format. It also shows the full
103 | contents of the {@code CoreLabel}s that are constructed by the
104 | classifier. And it shows getting out the probabilities of different
105 | assignments and an n-best list of classifications with probabilities.
106 | */
107 |
108 | String[] example = {"Good afternoon Rajat Raina, how are you today?",
109 | "I go to school at Stanford University, which is located in California." };
110 | for (String str : example) {
111 | System.out.println(classifier.classifyToString(str));
112 | }
113 | System.out.println("---");
114 |
115 | for (String str : example) {
116 | // This one puts in spaces and newlines between tokens, so just print not println.
117 | System.out.print(classifier.classifyToString(str, "slashTags", false));
118 | }
119 | System.out.println("---");
120 |
121 | for (String str : example) {
122 | // This one is best for dealing with the output as a TSV (tab-separated column) file.
123 | // The first column gives entities, the second their classes, and the third the remaining text in a document
124 | System.out.print(classifier.classifyToString(str, "tabbedEntities", false));
125 | }
126 | System.out.println("---");
127 |
128 | for (String str : example) {
129 | System.out.println(classifier.classifyWithInlineXML(str));
130 | }
131 | System.out.println("---");
132 |
133 | for (String str : example) {
134 | System.out.println(classifier.classifyToString(str, "xml", true));
135 | }
136 | System.out.println("---");
137 |
138 | for (String str : example) {
139 | System.out.print(classifier.classifyToString(str, "tsv", false));
140 | }
141 | System.out.println("---");
142 |
143 | // This gets out entities with character offsets
144 | int j = 0;
145 | for (String str : example) {
146 | j++;
147 | List> triples = classifier.classifyToCharacterOffsets(str);
148 | for (Triple trip : triples) {
149 | System.out.printf("%s over character offsets [%d, %d) in sentence %d.%n",
150 | trip.first(), trip.second(), trip.third, j);
151 | }
152 | }
153 | System.out.println("---");
154 |
155 | // This prints out all the details of what is stored for each token
156 | int i=0;
157 | for (String str : example) {
158 | for (List lcl : classifier.classify(str)) {
159 | for (CoreLabel cl : lcl) {
160 | System.out.print(i++ + ": ");
161 | System.out.println(cl.toShorterString());
162 | }
163 | }
164 | }
165 |
166 | System.out.println("---");
167 |
168 | }
169 | }
170 |
171 | }
172 |
--------------------------------------------------------------------------------
/assets/stanford-ner-2016-10-31/README.txt:
--------------------------------------------------------------------------------
1 | Stanford NER - v3.7.0 - 2016-10-31
2 | ----------------------------------------------
3 |
4 | This package provides a high-performance machine learning based named
5 | entity recognition system, including facilities to train models from
6 | supervised training data and pre-trained models for English.
7 |
8 | (c) 2002-2015. The Board of Trustees of The Leland
9 | Stanford Junior University. All Rights Reserved.
10 |
11 | Original CRF code by Jenny Finkel.
12 | Additional modules, features, internationalization, compaction, and
13 | support code by Christopher Manning, Dan Klein, Christopher Cox, Huy Nguyen
14 | Shipra Dingare, Anna Rafferty, and John Bauer.
15 | This release prepared by Jason Bolton.
16 |
17 | LICENSE
18 |
19 | The software is licensed under the full GPL v2+. Please see the file LICENCE.txt
20 |
21 | For more information, bug reports, and fixes, contact:
22 | Christopher Manning
23 | Dept of Computer Science, Gates 2A
24 | Stanford CA 94305-9020
25 | USA
26 | java-nlp-support@lists.stanford.edu
27 | http://www-nlp.stanford.edu/software/CRF-NER.shtml
28 |
29 | CONTACT
30 |
31 | For questions about this distribution, please contact Stanford's JavaNLP group
32 | at java-nlp-user@lists.stanford.edu. We provide assistance on a best-effort
33 | basis.
34 |
35 | TUTORIAL
36 |
37 | Quickstart guidelines, primarily for end users who wish to use the included NER
38 | models, are below. For further instructions on training your own NER model,
39 | go to http://www-nlp.stanford.edu/software/crf-faq.shtml.
40 |
41 | INCLUDED SERIALIZED MODELS / TRAINING DATA
42 |
43 | The basic included serialized model is a 3 class NER tagger that can
44 | label: PERSON, ORGANIZATION, and LOCATION entities. It is included as
45 | english.all.3class.distsim.crf.ser.gz. It is trained on data from
46 | CoNLL, MUC6, MUC7, ACE, OntoNotes, and Wikipedia.
47 | Because this model is trained on both US
48 | and UK newswire, it is fairly robust across the two domains.
49 |
50 | We have also included a 4 class NER tagger trained on the CoNLL 2003
51 | Shared Task training data that labels for PERSON, ORGANIZATION,
52 | LOCATION, and MISC. It is named
53 | english.conll.4class.distsim.crf.ser.gz .
54 |
55 | A third model is trained only on data from MUC and
56 | distinguishes between 7 different classes:
57 | english.muc.7class.distsim.crf.ser.gz.
58 |
59 | All of the serialized classifiers come in two versions, one trained to
60 | basically expected standard written English capitalization, and the other
61 | to ignore capitalization information. The case-insensitive versions
62 | of the three models available on the Stanford NER webpage.
63 | These models use a distributional similarity lexicon to improve performance
64 | (by between 1.5%-3% F-measure). The distributional similarity features
65 | make the models perform substantially better, but they require rather
66 | more memory. The distsim models are included in the release package.
67 | The nodistsim versions of the same models may be available on the
68 | Stanford NER webpage.
69 |
70 | Finally, we have models for other languages, including two German models,
71 | a Chinese model, and a Spanish model. The files for these models can be
72 | found at:
73 |
74 | http://nlp.stanford.edu/software/CRF-NER.shtml
75 |
76 |
77 | QUICKSTART INSTRUCTIONS
78 |
79 | This NER system requires Java 1.8 or later.
80 |
81 | Providing java is on your PATH, you should be able to run an NER GUI
82 | demonstration by just clicking. It might work to double-click on the
83 | stanford-ner.jar archive but this may well fail as the operating system
84 | does not give Java enough memory for our NER system, so it is safer to
85 | instead double click on the ner-gui.bat icon (Windows) or ner-gui.sh
86 | (Linux/Unix/MacOSX). Then, using the top option from the Classifier
87 | menu, load a CRF classifier from the classifiers directory of the
88 | distribution. You can then `either load a text file or web page from
89 | the File menu, or decide to use the default text in the window. Finally,
90 | you can now named entity tag the text by pressing the Run NER button.
91 |
92 | From a command line, you need to have java on your PATH and the
93 | stanford-ner.jar file and the lib directory in your CLASSPATH. (The way of doing this depends on
94 | your OS/shell.) The supplied ner.bat and ner.sh should work to allow
95 | you to tag a single file. For example, for Windows:
96 |
97 | ner file
98 |
99 | Or on Unix/Linux you should be able to parse the test file in the distribution
100 | directory with the command:
101 |
102 | java -mx600m -cp stanford-ner.jar:lib/* edu.stanford.nlp.ie.crf.CRFClassifier -loadClassifier classifiers/english.all.3class.distsim.crf.ser.gz -textFile sample.txt
103 |
104 | Here's an output option that will print out entities and their class to
105 | the first two columns of a tab-separated columns output file:
106 |
107 | java -mx600m -cp stanford-ner.jar:lib/* edu.stanford.nlp.ie.crf.CRFClassifier -loadClassifier classifiers/english.all.3class.distsim.crf.ser.gz -outputFormat tabbedEntities -textFile sample.txt > sample.tsv
108 |
109 | When run from a jar file, you also have the option of using a serialized
110 | classifier contained in the jar file.
111 |
112 | USING FULL STANFORD CORENLP NER FUNCTIONALITY
113 |
114 | This standalone distribution also allows access to the full NER
115 | capabilities of the Stanford CoreNLP pipeline. These capabilities
116 | can be accessed via the NERClassifierCombiner class.
117 | NERClassifierCombiner allows for multiple CRFs to be used together,
118 | and has options for recognizing numeric sequence patterns and time
119 | patterns with the rule-based NER of SUTime.
120 |
121 | Suppose one combines three CRF's CRF-1,CRF-2, and CRF-3 with the
122 | NERClassifierCombiner. When the NERClassiferCombiner runs, it will
123 | first apply the NER tags of CRF-1 to the text, then it will apply
124 | CRF-2's NER tags to any tokens not tagged by CRF-1 and so on. If
125 | the option ner.combinationMode is set to NORMAL (default), any label
126 | applied by CRF-1 cannot be applied by subsequent CRF's. For instance
127 | if CRF-1 applies the LOCATION tag, no other CRF's LOCATION tag will be
128 | used. If ner.combinationMode is set to HIGH_RECALL, this limitation
129 | will be deactivated.
130 |
131 | To use NERClassifierCombiner at the command-line, the jars in lib
132 | and stanford-ner.jar must be in the CLASSPATH. Here is an example command:
133 |
134 | java -mx2g edu.stanford.nlp.ie.NERClassifierCombiner -ner.model \
135 | classifiers/english.conll.4class.distsim.crf.ser.gz,classifiers/english.muc.7class.distsim.crf.ser.gz \
136 | -ner.useSUTime false -textFile sample-w-time.txt
137 |
138 | Let's break this down a bit. The flag "-ner.model" should be followed by a
139 | list of CRF's to be combined by the NERClassifierCombiner. Some serialized
140 | CRF's are provided in the classifiers directory. In this example the CRF's
141 | trained on the CONLL 4 class data and the MUC 7 class data are being combined.
142 |
143 | When the flag "-ner.useSUTime" is followed by "false", SUTime is shut off. You should
144 | note that when the "false" is omitted, the text "4 days ago" suddenly is
145 | tagged with DATE. These are the kinds of phrases SUTime can identify.
146 |
147 | NERClassifierCombiner can be run on different types of input as well. Here is
148 | an example which is run on CONLL style input:
149 |
150 | java -mx2g edu.stanford.nlp.ie.NERClassifierCombiner -ner.model \
151 | classifiers/english.conll.4class.distsim.crf.ser.gz,classifiers/english.muc.7class.distsim.crf.ser.gz \
152 | -map word=0,answer=1 -testFile sample-conll-file.txt
153 |
154 | It is crucial to include the "-map word=0,answer=1" , which is specifying that
155 | the input test file has the words in the first column and the answer labels
156 | in the second column.
157 |
158 | It is also possible to serialize and load an NERClassifierCombiner.
159 |
160 | This command loads the three sample crfs with combinationMode=HIGH_RECALL
161 | and SUTime=false, and dumps them to a file named
162 | test_serialized_ncc.ncc.ser.gz
163 |
164 | java -mx2g edu.stanford.nlp.ie.NERClassifierCombiner -ner.model \
165 | classifiers/english.conll.4class.distsim.crf.ser.gz,classifiers/english.muc.7class.distsim.crf.ser.gz,\
166 | classifiers/english.all.3class.distsim.crf.ser.gz -ner.useSUTime false \
167 | -ner.combinationMode HIGH_RECALL -serializeTo test.serialized.ncc.ncc.ser.gz
168 |
169 | An example serialized NERClassifierCombiner with these settings is supplied in
170 | the classifiers directory. Here is an example of loading that classifier and
171 | running it on the sample CONLL data:
172 |
173 | java -mx2g edu.stanford.nlp.ie.NERClassifierCombiner -loadClassifier \
174 | classifiers/example.serialized.ncc.ncc.ser.gz -map word=0,answer=1 \
175 | -testFile sample-conll-file.txt
176 |
177 | For a more exhaustive description of NERClassifierCombiner go to
178 | http://nlp.stanford.edu/software/ncc-faq.shtml
179 |
180 | PROGRAMMATIC USE
181 |
182 | The NERDemo file illustrates a couple of ways of calling the system
183 | programatically. You should get the same results from
184 |
185 | java -cp stanford-ner.jar:lib/*:. -mx300m NERDemo classifiers/english.all.3class.distsim.crf.ser.gz sample.txt
186 |
187 | as from using CRFClassifier. For more information on API calls, look in
188 | the enclosed javadoc directory: load index.html in a browser and look
189 | first at the edu.stanford.nlp.ie.crf package and CRFClassifier class.
190 | If you wish to train your own NER systems, look also at the
191 | edu.stanford.nlp.ie package NERFeatureFactory class.
192 |
193 |
194 | SERVER VERSION
195 |
196 | The NER code may also be run as a server listening on a socket:
197 |
198 | java -mx1000m -cp stanford-ner.jar:lib/* edu.stanford.nlp.ie.NERServer 1234
199 |
200 | You can specify which model to load with flags, either one on disk:
201 |
202 | java -mx1000m -cp stanford-ner.jar:lib/* edu.stanford.nlp.ie.NERServer -loadClassifier classifiers/all.3class.crf.ser.gz 1234
203 |
204 | Or if you have put a model inside the jar file:
205 |
206 | java -mx1000m -cp stanford-ner.jar:lib/* edu.stanford.nlp.ie.NERServer -loadJarClassifier all.3class.crf.ser.gz 1234
207 |
208 |
209 | RUNNING CLASSIFIERS FROM INSIDE A JAR FILE
210 |
211 | The software can run any serialized classifier from within a jar file by
212 | following the -loadClassifier flag by some resource available within a
213 | jar file on the CLASSPATH. An end user can make
214 | their own jar files with the desired NER models contained inside.
215 | This allows single jar file deployment.
216 |
217 |
218 | PERFORMANCE GUIDELINES
219 |
220 | Performance depends on many factors. Speed and memory use depend on
221 | hardware, operating system, and JVM. Accuracy depends on the data
222 | tested on. Nevertheless, in the belief that something is better than
223 | nothing, here are some statistics from one machine on one test set, in
224 | semi-realistic conditions (where the test data is somewhat varied).
225 |
226 | ner-eng-ie.crf-3-all2006-distsim.ser.gz (older version of ner-eng-ie.crf-3-all2008-distsim.ser.gz)
227 | Memory: 320MB (on a 32 bit machine)
228 | PERSON ORGANIZATION LOCATION
229 | 91.88 82.91 88.21
230 |
231 |
232 | --------------------
233 | CHANGES
234 | --------------------
235 |
236 | 2016-10-31 3.7.0 Improved Chinese NER
237 |
238 | 2015-12-09 3.6.0 Updated for compatibility
239 |
240 | 2015-04-20 3.5.2 synch standalone and CoreNLP functionality
241 |
242 | 2015-01-29 3.5.1 Substantial accuracy improvements
243 |
244 | 2014-10-26 3.5.0 Upgrade to Java 1.8
245 |
246 | 2014-08-27 3.4.1 Add Spanish models
247 |
248 | 2014-06-16 3.4 Fix serialization bug
249 |
250 | 2014-01-04 3.3.1 Bugfix release
251 |
252 | 2013-11-12 3.3.0 Update for compatibility
253 |
254 | 2013-11-12 3.3.0 Update for compatibility
255 |
256 | 2013-06-19 3.2.0 Improve handling of line-by-line input
257 |
258 | 2013-04-04 1.2.8 nthreads option
259 |
260 | 2012-11-11 1.2.7 Improved English 3 class model by including
261 | data from Wikipedia, release Chinese model
262 |
263 | 2012-07-09 1.2.6 Minor bug fixes
264 |
265 | 2012-05-22 1.2.5 Fix encoding issue
266 |
267 | 2012-04-07 1.2.4 Caseless version of English models supported
268 |
269 | 2012-01-06 1.2.3 Minor bug fixes
270 |
271 | 2011-09-14 1.2.2 Improved thread safety
272 |
273 | 2011-06-19 1.2.1 Models reduced in size but on average improved
274 | in accuracy (improved distsim clusters)
275 |
276 | 2011-05-16 1.2 Normal download includes 3, 4, and 7
277 | class models. Updated for compatibility
278 | with other software releases.
279 |
280 | 2009-01-16 1.1.1 Minor bug and usability fixes, changed API
281 |
282 | 2008-05-07 1.1 Additional feature flags, various code updates
283 |
284 | 2006-09-18 1.0 Initial release
285 |
286 |
--------------------------------------------------------------------------------
/assets/stanford-ner-2016-10-31/build.xml:
--------------------------------------------------------------------------------
1 |
2 |
3 |
10 |
11 |
12 |
13 |
14 |
15 |
16 |
17 |
18 |
19 |
20 |
21 |
22 |
38 |
39 |
40 |
41 |
42 |
43 |
44 |
45 |
46 |
47 |
48 |
49 |
50 |
56 |
57 |
59 |
60 |
61 |
62 |
63 |
64 |
70 |
71 |
72 |
73 |
74 |
75 |
76 |
77 |
78 |
84 |
85 |
86 |
87 |
88 |
89 |
90 |
91 |
92 |
93 |
94 |
95 |
96 |
97 |
98 |
99 |
100 |
108 |
109 |
111 |
112 |
113 |
114 |
123 |
124 |
125 |
126 |
127 |
128 |
129 |
130 |
135 |
136 |
137 |
138 |
139 |
140 |
141 |
149 |
150 |
152 |
153 |
162 | Stanford NLP Group]]>
163 |
164 |
165 |
166 |
167 |
168 |
169 |
170 |
171 |
172 |
173 |
174 |
175 |
185 |
186 |
187 |
188 |
189 |
190 |
191 |
192 |
193 |
194 |
--------------------------------------------------------------------------------
/assets/stanford-ner-2016-10-31/classifiers/english.all.3class.distsim.crf.ser.gz:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/sidtechnical/hakuna-metadata-1/9d0d4e48b57d6422468389e1e089818cdacf9eb7/assets/stanford-ner-2016-10-31/classifiers/english.all.3class.distsim.crf.ser.gz
--------------------------------------------------------------------------------
/assets/stanford-ner-2016-10-31/classifiers/english.all.3class.distsim.prop:
--------------------------------------------------------------------------------
1 | # trainFileList = /u/nlp/data/ner/column_data/all.3class.train.old2,/u/nlp/data/ner/column_data/english.extra.3class.train
2 | trainFileList = /u/nlp/data/ner/column_data/ace23.3class.train,/u/nlp/data/ner/column_data/muc6.3class.ptb.train,/u/nlp/data/ner/column_data/muc7.3class.ptb.train,/u/nlp/data/ner/column_data/conll.3class.train,/u/nlp/data/ner/column_data/wikiner.3class.train,/u/nlp/data/ner/column_data/ontonotes.3class.train,/u/nlp/data/ner/column_data/english.extra.3class.train
3 | testFile = /u/nlp/data/ner/column_data/all.3class.test
4 | serializeTo = english.all.3class.distsim.crf.ser.gz
5 |
6 | type = crf
7 |
8 | wordFunction = edu.stanford.nlp.process.AmericanizeFunction
9 |
10 | #distSimLexicon = /u/nlp/data/pos_tags_are_useless/englishGigaword.200.pruned
11 | #distSimLexicon = /u/nlp/data/pos_tags_are_useless/egw.bnc.200
12 | distSimLexicon = /u/nlp/data/pos_tags_are_useless/egw4-reut.512.clusters
13 | # right options for egw4-reut.512 (though effect of having or not is small)
14 | numberEquivalenceDistSim = true
15 | unknownWordDistSimClass = 0
16 | useDistSim = true
17 |
18 | map = word=0,answer=1
19 |
20 | saveFeatureIndexToDisk = true
21 |
22 | useClassFeature=true
23 | useWord=true
24 | #useWordPairs=true
25 | useNGrams=true
26 | noMidNGrams=true
27 | maxNGramLeng=6
28 | usePrev=true
29 | useNext=true
30 | #useTags=true
31 | #useWordTag=true
32 | useLongSequences=true
33 | useSequences=true
34 | usePrevSequences=true
35 | useTypeSeqs=true
36 | useTypeSeqs2=true
37 | useTypeySequences=true
38 | useOccurrencePatterns=true
39 | useLastRealWord=true
40 | useNextRealWord=true
41 | #useReverse=false
42 | normalize=true
43 | # normalizeTimex=true
44 | wordShape=chris2useLC
45 | useDisjunctive=true
46 | disjunctionWidth=5
47 | #useDisjunctiveShapeInteraction=true
48 |
49 | maxLeft=1
50 | readerAndWriter=edu.stanford.nlp.sequences.ColumnDocumentReaderAndWriter
51 |
52 | useObservedSequencesOnly=true
53 |
54 | useQN = true
55 | QNsize = 25
56 |
57 | # makes it go faster
58 | featureDiffThresh=0.05
59 |
--------------------------------------------------------------------------------
/assets/stanford-ner-2016-10-31/classifiers/english.conll.4class.distsim.crf.ser.gz:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/sidtechnical/hakuna-metadata-1/9d0d4e48b57d6422468389e1e089818cdacf9eb7/assets/stanford-ner-2016-10-31/classifiers/english.conll.4class.distsim.crf.ser.gz
--------------------------------------------------------------------------------
/assets/stanford-ner-2016-10-31/classifiers/english.conll.4class.distsim.prop:
--------------------------------------------------------------------------------
1 | # This is better than Jenny's either with or without distsim turned on
2 | # And using iob2 is better for optimal CoNLL performance.
3 | # Features titled "chris2009"
4 |
5 | trainFile = /u/nlp/data/ner/column_data/conll.4class.train
6 | # testFile = /u/nlp/data/ner/column_data/conll.4class.testa
7 | serializeTo = english.conll.4class.distsim.crf.ser.gz
8 |
9 | wordFunction = edu.stanford.nlp.process.AmericanizeFunction
10 |
11 | useDistSim = true
12 | distSimLexicon = /u/nlp/data/pos_tags_are_useless/egw4-reut.512.clusters
13 | # right options for egw4-reut.512 (though effect of having or not is small)
14 | numberEquivalenceDistSim = true
15 | unknownWordDistSimClass = 0
16 |
17 | map = word=0,answer=1
18 |
19 | saveFeatureIndexToDisk = true
20 |
21 | useTitle = true
22 | useClassFeature=true
23 | useWord=true
24 | # useWordPairs=true
25 | useNGrams=true
26 | noMidNGrams=true
27 | # maxNGramLeng=6 # Having them all helps, which is the default
28 | usePrev=true
29 | useNext=true
30 | # useTags=true
31 | # useWordTag=true
32 | useLongSequences=true
33 | useSequences=true
34 | usePrevSequences=true
35 | maxLeft=1
36 | useTypeSeqs=true
37 | useTypeSeqs2=true
38 | useTypeySequences=true
39 | useOccurrencePatterns=true
40 | useLastRealWord=true
41 | useNextRealWord=true
42 | #useReverse=false
43 | normalize=true
44 | # normalizeTimex=true
45 | # dan2 better than chris2 on CoNLL data...
46 | wordShape=dan2useLC
47 | useDisjunctive=true
48 | # disjunctionWidth 4 is better than 5 on CoNLL data
49 | disjunctionWidth=4
50 | #useDisjunctiveShapeInteraction=true
51 |
52 | type=crf
53 |
54 | readerAndWriter=edu.stanford.nlp.sequences.ColumnDocumentReaderAndWriter
55 |
56 | useObservedSequencesOnly=true
57 |
58 | sigma = 20
59 | useQN = true
60 | QNsize = 25
61 |
62 | # makes it go faster
63 | featureDiffThresh=0.05
64 |
--------------------------------------------------------------------------------
/assets/stanford-ner-2016-10-31/classifiers/english.muc.7class.distsim.crf.ser.gz:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/sidtechnical/hakuna-metadata-1/9d0d4e48b57d6422468389e1e089818cdacf9eb7/assets/stanford-ner-2016-10-31/classifiers/english.muc.7class.distsim.crf.ser.gz
--------------------------------------------------------------------------------
/assets/stanford-ner-2016-10-31/classifiers/english.muc.7class.distsim.prop:
--------------------------------------------------------------------------------
1 | trainFileList = /u/nlp/data/ner/column_data/muc6.ptb.train,/u/nlp/data/ner/column_data/muc7.ptb.train
2 | # testFile = /u/nlp/data/ner/column_data/muc7.ptb.devtest
3 | serializeTo = english.muc.7class.distsim.crf.ser.gz
4 |
5 | type=crf
6 |
7 | wordFunction = edu.stanford.nlp.process.AmericanizeFunction
8 |
9 | distSimLexicon = /u/nlp/data/pos_tags_are_useless/egw4-reut.512.clusters
10 | numberEquivalenceDistSim = true
11 | unknownWordDistSimClass = 0
12 | useDistSim = true
13 |
14 | map = word=0,answer=1
15 |
16 | saveFeatureIndexToDisk = true
17 |
18 | useClassFeature=true
19 | useWord=true
20 | #useWordPairs=true
21 | useNGrams=true
22 | noMidNGrams=true
23 | maxNGramLeng=6
24 | usePrev=true
25 | useNext=true
26 | #useTags=true
27 | #useWordTag=true
28 | useLongSequences=true
29 | useSequences=true
30 | usePrevSequences=true
31 | useTypeSeqs=true
32 | useTypeSeqs2=true
33 | useTypeySequences=true
34 | useOccurrencePatterns=true
35 | useLastRealWord=true
36 | useNextRealWord=true
37 | #useReverse=false
38 | normalize=true
39 | # normalizeTimex=true
40 | wordShape=chris2useLC
41 | useDisjunctive=true
42 | disjunctionWidth=5
43 | #useDisjunctiveShapeInteraction=true
44 |
45 | maxLeft=1
46 | readerAndWriter=edu.stanford.nlp.sequences.ColumnDocumentReaderAndWriter
47 |
48 | useObservedSequencesOnly=true
49 |
50 | useQN = true
51 | QNsize = 25
52 |
53 | # makes it go faster
54 | featureDiffThresh=0.05
55 |
--------------------------------------------------------------------------------
/assets/stanford-ner-2016-10-31/classifiers/example.serialized.ncc.ncc.ser.gz:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/sidtechnical/hakuna-metadata-1/9d0d4e48b57d6422468389e1e089818cdacf9eb7/assets/stanford-ner-2016-10-31/classifiers/example.serialized.ncc.ncc.ser.gz
--------------------------------------------------------------------------------
/assets/stanford-ner-2016-10-31/classifiers/example.serialized.ncc.prop:
--------------------------------------------------------------------------------
1 | ner.model=classifiers/english.conll.4class.distsim.crf.ser.gz,classifiers/english.muc.7class.distsim.crf.ser.gz,classifiers/english.all.3class.distsim.crf.ser.gz
2 | ner.useSUTime=false
3 | ner.combinationMode=HIGH_RECALL
4 | serializeTo=example.serialized.ncc.ncc.ser.gz
5 |
--------------------------------------------------------------------------------
/assets/stanford-ner-2016-10-31/lib/joda-time.jar:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/sidtechnical/hakuna-metadata-1/9d0d4e48b57d6422468389e1e089818cdacf9eb7/assets/stanford-ner-2016-10-31/lib/joda-time.jar
--------------------------------------------------------------------------------
/assets/stanford-ner-2016-10-31/lib/jollyday-0.4.9.jar:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/sidtechnical/hakuna-metadata-1/9d0d4e48b57d6422468389e1e089818cdacf9eb7/assets/stanford-ner-2016-10-31/lib/jollyday-0.4.9.jar
--------------------------------------------------------------------------------
/assets/stanford-ner-2016-10-31/lib/stanford-ner-resources.jar:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/sidtechnical/hakuna-metadata-1/9d0d4e48b57d6422468389e1e089818cdacf9eb7/assets/stanford-ner-2016-10-31/lib/stanford-ner-resources.jar
--------------------------------------------------------------------------------
/assets/stanford-ner-2016-10-31/ner-gui.bat:
--------------------------------------------------------------------------------
1 | java -mx1500m -cp "stanford-ner.jar;lib/*" edu.stanford.nlp.ie.crf.NERGUI
2 |
--------------------------------------------------------------------------------
/assets/stanford-ner-2016-10-31/ner-gui.command:
--------------------------------------------------------------------------------
1 | #!/bin/sh
2 | java -mx500m -cp `dirname $0`/stanford-ner.jar:`dirname $0`/lib/* edu.stanford.nlp.ie.crf.NERGUI
3 |
--------------------------------------------------------------------------------
/assets/stanford-ner-2016-10-31/ner-gui.sh:
--------------------------------------------------------------------------------
1 | #!/bin/sh
2 | scriptdir=`dirname $0`
3 |
4 | java -mx700m -cp "$scriptdir/stanford-ner.jar:lib/*" edu.stanford.nlp.ie.crf.NERGUI
5 |
--------------------------------------------------------------------------------
/assets/stanford-ner-2016-10-31/ner.bat:
--------------------------------------------------------------------------------
1 | java -mx1000m -cp stanford-ner.jar;lib/* edu.stanford.nlp.ie.crf.CRFClassifier -loadClassifier classifiers\english.all.3class.distsim.crf.ser.gz -textFile %1
2 |
--------------------------------------------------------------------------------
/assets/stanford-ner-2016-10-31/ner.sh:
--------------------------------------------------------------------------------
1 | #!/bin/sh
2 | scriptdir=`dirname $0`
3 |
4 | java -mx700m -cp "$scriptdir/stanford-ner.jar:$scriptdir/lib/*" edu.stanford.nlp.ie.crf.CRFClassifier -loadClassifier $scriptdir/classifiers/english.all.3class.distsim.crf.ser.gz -textFile $1
5 |
--------------------------------------------------------------------------------
/assets/stanford-ner-2016-10-31/sample-conll-file.txt:
--------------------------------------------------------------------------------
1 | John PERSON
2 | Kerry PERSON
3 | will O
4 | fly O
5 | to O
6 | Paris LOCATION
7 | this O
8 | weekend O
9 | . O
10 |
--------------------------------------------------------------------------------
/assets/stanford-ner-2016-10-31/sample-w-time.txt:
--------------------------------------------------------------------------------
1 | Barack Obama was born on August 4, 1961 in Honolulu, Hawaii which was 4 days
2 | ago.
3 |
--------------------------------------------------------------------------------
/assets/stanford-ner-2016-10-31/sample.ner.txt:
--------------------------------------------------------------------------------
1 | The/O fate/O of/O Lehman/ORGANIZATION Brothers/ORGANIZATION ,/O the/O beleaguered/O investment/O bank/O ,/O hung/O in/O the/O balance/O on/O Sunday/O as/O Federal/ORGANIZATION Reserve/ORGANIZATION officials/O and/O the/O leaders/O of/O major/O financial/O institutions/O continued/O to/O gather/O in/O emergency/O meetings/O trying/O to/O complete/O a/O plan/O to/O rescue/O the/O stricken/O bank/O ./O
2 | Several/O possible/O plans/O emerged/O from/O the/O talks/O ,/O held/O at/O the/O Federal/ORGANIZATION Reserve/ORGANIZATION Bank/ORGANIZATION of/ORGANIZATION New/ORGANIZATION York/ORGANIZATION and/O led/O by/O Timothy/PERSON R./PERSON Geithner/PERSON ,/O the/O president/O of/O the/O New/ORGANIZATION York/ORGANIZATION Fed/ORGANIZATION ,/O and/O Treasury/ORGANIZATION Secretary/O Henry/PERSON M./PERSON Paulson/PERSON Jr./PERSON ./O
3 |
--------------------------------------------------------------------------------
/assets/stanford-ner-2016-10-31/sample.txt:
--------------------------------------------------------------------------------
1 | The fate of Lehman Brothers, the beleaguered investment bank, hung in the balance on Sunday as Federal Reserve officials and the leaders of major financial institutions continued to gather in emergency meetings trying to complete a plan to rescue the stricken bank. Several possible plans emerged from the talks, held at the Federal Reserve Bank of New York and led by Timothy R. Geithner, the president of the New York Fed, and Treasury Secretary Henry M. Paulson Jr.
2 |
--------------------------------------------------------------------------------
/assets/stanford-ner-2016-10-31/stanford-ner-3.7.0-javadoc.jar:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/sidtechnical/hakuna-metadata-1/9d0d4e48b57d6422468389e1e089818cdacf9eb7/assets/stanford-ner-2016-10-31/stanford-ner-3.7.0-javadoc.jar
--------------------------------------------------------------------------------
/assets/stanford-ner-2016-10-31/stanford-ner-3.7.0-sources.jar:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/sidtechnical/hakuna-metadata-1/9d0d4e48b57d6422468389e1e089818cdacf9eb7/assets/stanford-ner-2016-10-31/stanford-ner-3.7.0-sources.jar
--------------------------------------------------------------------------------
/assets/stanford-ner-2016-10-31/stanford-ner-3.7.0.jar:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/sidtechnical/hakuna-metadata-1/9d0d4e48b57d6422468389e1e089818cdacf9eb7/assets/stanford-ner-2016-10-31/stanford-ner-3.7.0.jar
--------------------------------------------------------------------------------
/assets/stanford-ner-2016-10-31/stanford-ner.jar:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/sidtechnical/hakuna-metadata-1/9d0d4e48b57d6422468389e1e089818cdacf9eb7/assets/stanford-ner-2016-10-31/stanford-ner.jar
--------------------------------------------------------------------------------
/index.html:
--------------------------------------------------------------------------------
1 |
2 |
3 | Hakuna Metadata - Browsing history
4 |
5 |
6 |
7 |
8 |
9 |
10 |
11 |
12 |
13 |
14 |
15 |
16 |
17 |
18 |
19 |
Hakuna Metadata
20 |
Browsing history visualization
21 |
Explore more about your browsing history.
22 |
23 |
24 |
P.S: This tool works only if you store your browsing history and only if you have browsed Facebook, Google or Twitter.
25 |
26 |
While you are browsing, if the content of the websites that you visit is the "data", then your browsing history is your "metadata". This simple tool build some visualizations based on that metadata to explain the hidden power in it.
27 |
28 |
Note that, most of the following visualizations are interactive. You can zoom-in, zoom-out or click different parts of it to understand the graphs better.
29 |
30 |
31 |
32 |
Overall stats about the browsing history:
33 | Here is snapshot of what you have browsed the most, in terms of most visited domain names and suffixes.
34 |
Browsing patterns:
37 | Your browsing pattern can be seen in two forms. One as the anomalies - which gives an understanding of peaks in your usage, and the other as heatmap, which gives a snapshot of the lifestyle in an easily
38 | understandable manner.
39 |
Potential adwords:
45 | Here is the list of potential adwords genrated in two different ways. First, by crawling the most visited websited, followed by performing a simple Named-Entity Recognition. Second, by displaying your most searched keywords on Google.
46 |
Since every profile you visit in Facebook or Twitter is identified by unique URLs, the following graphs try to present them as a psuedo-social graph. Your browsing history (URLs) pertaining to Facebook or Twitter are first grouped by the number of times you have visited them (visit count), and then by Frecency, an indicator of frequency + recency.
55 |
56 |
In the links below to the graphs, start by clicking on the cicrles which are tagged with largest numbers and does not contain any other circles inside. These are probably your partners, family members or close friends. Now, try exploring those circles which contains several inner circles. You will probably notice people from different social circles (such as work place, school friends, role models, etc..) grouped together. This means even though they may not be connected directly with each other, you have similar amount of interest in them.
This tool is built to be used by complete tech novices. We just parsed the URLs in the browsing history to fetch the names of the people whose profile you have visited. You might notice some numbers instead than names for the same reason in the psuedo-social spheres.
66 |
67 |
If you have any issues or suggestion, please send an email to sidtechnical@gmail.com.
68 |
69 |
70 |
71 |
72 |
73 |
European Digital Rights
74 |
75 |
76 |
77 |
78 |
79 |
80 |
81 |
--------------------------------------------------------------------------------
/requirements:
--------------------------------------------------------------------------------
1 | sudo apt-get install python-pip
2 | sudo apt-get install python-tk
3 | sudo pip install pandas==0.18.1
4 | sudo pip install nltk==3.2.2
5 | sudo pip install plotly==1.13.0
6 | sudo pip install beautifulsoup4==4.4.1
7 | sudo pip install requests==2.13.0
8 | sudo pip install tldextract==1.5.1
9 | sudo pip install wordcloud==1.2.1
10 | sudo pip install pillow
11 | python -m nltk.downloader 'stopwords'
12 | python -m nltk.downloader 'punkt'
13 |
14 |
15 |
--------------------------------------------------------------------------------
/requirements-iOS:
--------------------------------------------------------------------------------
1 | brew install python
2 | brew install freetype libjpeg
3 | sudo pip install pillow
4 | sudo pip install pandas==0.18.1
5 | sudo pip install nltk==3.2.2
6 | sudo pip install plotly==1.13.0
7 | sudo pip install beautifulsoup4==4.4.1
8 | sudo pip install requests==2.13.0
9 | sudo pip install tldextract==1.5.1
10 | sudo pip install wordcloud==1.2.1
11 | python -m nltk.downloader 'stopwords'
12 | python -m nltk.downloader 'punkt'
--------------------------------------------------------------------------------
/tool-iOS.py:
--------------------------------------------------------------------------------
1 | import shutil, sqlite3, glob, re, json, unicodedata, string, dateutil, webbrowser, requests
2 |
3 | from os.path import expanduser
4 |
5 | import pandas as pd
6 | from pandas.tseries.resample import TimeGrouper
7 |
8 | from urlparse import urlparse, parse_qs
9 | from collections import defaultdict
10 |
11 | import nltk
12 | from nltk.tokenize import word_tokenize
13 | from nltk import FreqDist
14 | from nltk.corpus import stopwords
15 | from nltk.tag.stanford import StanfordNERTagger
16 | from nltk.internals import find_jars_within_path
17 |
18 | from bs4 import BeautifulSoup
19 |
20 | from plotly.offline.offline import *
21 | from plotly.graph_objs import *
22 |
23 | from wordcloud import WordCloud
24 |
25 | from nltk.internals import find_jars_within_path
26 | # parser = StanfordParser(model_path="path/to/englishPCFG.ser.gz")
27 | ##################### ENV setting #################################################################
28 |
29 |
30 | os.environ['CLASSPATH'] = "assets/stanford-ner-2016-10-31"
31 | st = StanfordNERTagger('assets/stanford-ner-2016-10-31/classifiers/english.all.3class.distsim.crf.ser.gz')
32 | # st._classpath = tuple(find_jars_within_path('assets/stanford-ner-2015-04-20'))
33 | ###################################################################################################
34 |
35 |
36 | ########################### Generic functions begins ##############################################
37 | #Copying the place.sqlite file to local folder to the current local direcotry
38 | def copy_browser_history_database():
39 | shutil.copy2(glob.glob(expanduser("~") + '/Library/Application Support/Firefox/Profiles/*/places.sqlite')[0] , "browser_history_database.sqlite3")
40 |
41 |
42 |
43 | # Create a dataframe from local copy of browser history database i.e. from the place.sqalite
44 | def create_browser_history_dataframe(browser_history_database):
45 | query = "select datetime(moz_historyvisits.visit_date/1000000, 'unixepoch', 'localtime') as recent_visit, moz_places.url as url_location, moz_places.title as name, moz_places.visit_count as visit_count, moz_places.frecency as frecency from moz_places, moz_historyvisits where moz_historyvisits.place_id = moz_places.id order by moz_historyvisits.visit_date desc;"
46 | con = sqlite3.connect(browser_history_database, timeout=5)
47 | browser_history_dataframe = pd.read_sql_query(query, con)
48 | con.close()
49 | return browser_history_dataframe
50 |
51 | # Seperate the URLs for further analysis
52 | def seperate_the_dataframes(dataframe,url_string):
53 | return dataframe[dataframe['url_location'].str.contains(url_string)]
54 |
55 | ########################### Generic functions ends ################################################
56 |
57 |
58 | ########################### Facebook functions begins ##############################################
59 | #Classifying the (Facebook) urls into photo, event, profile, group, search and messages
60 | def Facebook_URL_Categorizre(URL):
61 | # print "categorizing Facebook URLs"
62 | category_tag = ''
63 | if urlparse(URL).netloc=="www.facebook.com":
64 | if "photo" in urlparse(URL).path:
65 | category_tag = "photo"
66 | elif "search" in urlparse(URL).path and "message" not in urlparse(URL).path and "photo" not in urlparse(URL).path and "group" not in urlparse(URL).path:
67 | category_tag = "search"
68 | elif "group" in urlparse(URL).path:
69 | category_tag = "group"
70 | elif "message" in urlparse(URL).path:
71 | category_tag = "message"
72 | elif "events" in urlparse(URL).path:
73 | category_tag = "event"
74 | elif "posts" in urlparse(URL).path:
75 | category_tag = "posts"
76 | else:
77 | category_tag = "profile"
78 | return category_tag
79 |
80 |
81 |
82 | def cleanup_facebook_dataframe(dataframe):
83 | #Remove the repeated profile urls
84 | dataframe = dataframe[dataframe.url_location != "https://www.facebook.com/"]
85 | dataframe = dataframe[dataframe.url_location != "https://www.facebook.com/#"]
86 | dataframe = dataframe[dataframe.url_location != "https://www.facebook.com/?_rdr=p"]
87 | dataframe = dataframe[dataframe.url_location != "https://www.facebook.com/?_rdr=p#"]
88 | dataframe = dataframe[dataframe.url_location != "https://www.facebook.com/?q="]
89 | dataframe = dataframe[dataframe.url_location != "https://www.facebook.com/?ref=tn_tnmn"]
90 |
91 | repeated_facebook_pages_words = ["people","settings", "dyi?", "react", "help", "support", "utm_source", "preview_cover" , "/?q=#/", "video.php" , "recover" ,"react", "login", "password", "l.php?", "viewas", "insights", "story_id", "sharer.php" ,"about" ,"pages", "?stype=lo", "homepage", "app_data", "ft[qid]" , "safetycheck","l.php?u=https", "location=profile_browser", "?next=", "friends" ,"videos", "?entry_point=", "deactivate", "careers", "saved", "timeline", "page_user_activity", "notif_t=page_fan", "manager", "notifications", "media", "notif", "oauth"]
92 | facebook_pattern = '|'.join(map(re.escape, repeated_facebook_pages_words))
93 | dataframe = dataframe[~dataframe.url_location.str.contains(facebook_pattern)]
94 |
95 | return dataframe
96 |
97 | def url_cleanup(url):
98 | parsed_url = urlparse(url)
99 | qry = parsed_url.query
100 | path = parsed_url.path
101 | if 'profile.php' in path:
102 | result = re.search('id=(\d+)',qry)
103 | return 'https://www.facebook.com/'+result.group(1)
104 | else:
105 | return "https://www.facebook.com"+parsed_url.path
106 |
107 | def name_extractor(URL, Name):
108 | try:
109 | if not Name or 'Facebook' in Name:
110 | return urlparse(URL).path.split("/",1)[1] #Prints
111 | else:
112 | return(''.join(c for c in Name.split(' - ')[0] if c.isalpha() or c in ' .').strip())
113 | except IndexError:
114 | print URL, Name
115 |
116 | def create_json_for_circle_packing(Domain, dataframe):
117 | gp = dataframe.groupby(['visit_count'])
118 | dict_json = {"name": Domain}
119 | children = []
120 | for name, group in gp:
121 | temp = {"name": name, "children": []}
122 | rgp = group.groupby(['frecency'])
123 | for n, g in rgp:
124 | temp["children"].append({
125 | "name": n,
126 | "children": [
127 | {"name": row["real_name"],
128 | "size": row["visit_count"] * 1000 / len(g)}
129 | for _, row in g.iterrows()
130 | ]
131 | })
132 | children.append(temp)
133 |
134 | dict_json["children"] = children
135 | return dict_json
136 |
137 |
138 | ########################### Facebook functions ends ##############################################
139 |
140 | ########################### Twitter fucntions begin ##############################################
141 |
142 | def twitter_url_cleanup(url):
143 | parsed_url = urlparse(url)
144 | if not parsed_url.path or parsed_url.path!="/":
145 | return 'https://www.twitter.com/'+ parsed_url.path.split("/",1)[1].split("/",1)[0]
146 |
147 | def twitter_name_extractor(URL, Name):
148 | try:
149 | if 'on Twitter' in Name or 'Twitter / Notifications' in Name:
150 | return URL.split("https://www.twitter.com/",1)[1]
151 | elif not Name or Name!='Twitter / ?':
152 | real_name = Name.split("|",1)[0].split("(",1)[0]
153 | if not real_name or Name =='Twitter / ?':
154 | # print "It was empty"
155 | return URL.split("https://www.twitter.com/",1)[1] #real_name
156 | else:
157 | return real_name #URL.split("https://www.twitter.com/",1)[1]
158 | except:
159 | return URL.split("https://www.twitter.com/",1)[1]
160 |
161 | ########################### Twitter functions ends ##############################################
162 |
163 | ########################### Google functions begins ##############################################
164 |
165 | def Google_search_query_keywords(URL, Name):
166 | if not Name:
167 | parsed_url = urlparse(URL)
168 | if "google" in parsed_url.netloc and parsed_url.path=='/search':
169 |
170 | query_dict = parse_qs(parsed_url.query, keep_blank_values=True)
171 |
172 | for k, v in query_dict.iteritems():
173 | if k=="q":
174 | return v[0]
175 |
176 | else:
177 | return ""
178 |
179 | else:
180 | return Name.split("- Google Search",1)[0]
181 |
182 | ########################### Google functions ends ##############################################
183 |
184 |
185 |
186 |
187 |
188 | ########################### Browsing pattern functions starts ##############################################
189 |
190 | def Count_Unique_URLs(URL_List):
191 | return len(URL_List)
192 |
193 | def strip_time(DateValue):
194 | return DateValue.time()
195 |
196 | def strip_date(DateValue):
197 | return DateValue.date()
198 |
199 |
200 | ########################### Browsing pattern functions ends ##############################################
201 |
202 | ########################### NER functions starts #########################################################
203 |
204 | def netloc_extractor(URL):
205 | return urlparse(URL).netloc
206 |
207 | def remove_SE_SM(dataframe):
208 | SocMedia_SearchEngines = ["mail", "gmail.com", "drive", "dropbox" ,"soundcloud.com", "spotify.com", "youtube.com","github.com", "stackoverflow.com", "facebook.com","twitter.com","google","amazon", "duckduckgo", "disconnect", "airbnb", "booking", "linkedin"]
209 | dataframe = dataframe[~dataframe.netloc.str.contains('|'.join(SocMedia_SearchEngines))]
210 | return dataframe
211 |
212 | def grab_website_text(url_list):
213 | cert = "assets/certs.pem"
214 | text_blob = ""
215 | text_list_dummy =[]
216 |
217 | for url in url_list:
218 |
219 | try:
220 | result = requests.get(url, verify= cert)
221 | result.raise_for_status()
222 |
223 |
224 | html = result.content
225 |
226 | soup = BeautifulSoup(html)
227 |
228 | # remove all script and style elements
229 | for script in soup(["script", "style"]):
230 | script.extract()
231 |
232 | # get text
233 | try:
234 | text = soup.body.get_text()
235 | # break into lines and remove leading and trailing space on each
236 |
237 | lines = (line.strip() for line in text.splitlines())
238 |
239 | # break multi-headlines into a line each
240 | chunks = (phrase.strip() for line in lines for phrase in line.split(" "))
241 |
242 | # drop blank lines
243 | text = ' '.join(chunk for chunk in chunks if chunk)
244 | except AttributeError:
245 | text = ""
246 |
247 |
248 | text_list_dummy.append(text)
249 |
250 | except requests.exceptions.RequestException:
251 | text_list_dummy.append("")
252 |
253 | text_blob = '\n'.join(text_list_dummy)
254 | return text_blob
255 |
256 |
257 | def NER_string(NER_list):
258 | NER_str = ""
259 | for item in NER_list:
260 | NER_str +=str(item)
261 | NER_str += " | "
262 | return NER_str
263 |
264 | def create_stopword_free_text(text_to_process):
265 | stoplist = stopwords.words('english')
266 |
267 | more_sw = "a about above across after again against all almost alone along already also although always am among an and another any anybody anyone anything anywhere are area areas aren't around as ask asked asking asks at away b back backed backing backs be became because become becomes been before began behind being beings below best better between big both but by c came can cannot can't case cases certain certainly clear clearly come could couldn't d did didn't differ different differently do does doesn't doing done don't down downed downing downs during e each early either end ended ending ends enough even evenly ever every everybody everyone everything everywhere f face faces fact facts far felt few find finds first for four from full fully further furthered furthering furthers g gave general generally get gets give given gives go going good goods got great greater greatest group grouped grouping groups h had hadn't has hasn't have haven't having he he'd he'll her here here's hers herself he's high higher highest him himself his how however how's i i'd if i'll i'm important in interest interested interesting interests into is isn't it its it's itself i've j just k keep keeps kind knew know known knows l large largely last later latest least less let lets let's like likely long longer longest m made make making man many may me member members men might more most mostly mr mrs much must mustn't my myself n necessary need needed needing needs never new newer newest next no nobody non noone nor not nothing now nowhere number numbers o of off often old older oldest on once one only open opened opening opens or order ordered ordering orders other others ought our ours ourselves out over own p part parted parting parts per perhaps place places point pointed pointing points possible present presented presenting presents problem problems put puts q quite r rather really right room rooms s said same saw say says second seconds see seem seemed seeming seems sees several shall shan't she she'd she'll she's should shouldn't show showed showing shows side sides since small smaller smallest so some somebody someone something somewhere state states still such sure t take taken than that that's the their theirs them themselves then there therefore there's these they they'd they'll they're they've thing things think thinks this those though thought thoughts three through thus to today together too took toward turn turned turning turns two u under until up upon us use used uses v very w want wanted wanting wants was wasn't way ways we we'd well we'll wells went were we're weren't we've what what's when when's where where's whether which while who whole whom who's whose why why's will with within without won't work worked working works would wouldn't x y year years yes yet you you'd you'll young younger youngest your you're yours yourself yourselves you've z"
268 |
269 | stoplist += more_sw.split()
270 |
271 | # Tokenize the text into words using NLTK library
272 | scrapped_words = nltk.tokenize.word_tokenize(text_to_process)
273 |
274 | # Remove single-character tokens (mostly punctuation)
275 | scrapped_words = [word for word in scrapped_words if len(word) > 1]
276 |
277 | # Remove numbers
278 | scrapped_words = [word for word in scrapped_words if not word.isdigit()]
279 |
280 | # Lowercase all words (default_stopwords are lowercase too)
281 | scrapped_words = [word.lower() for word in scrapped_words]
282 |
283 | # Remove stopwords
284 | scrapped_words = [word for word in scrapped_words if word not in stoplist]
285 |
286 | punctuations = list(string.punctuation)
287 | punctuations.extend(("''", "//", "--","..."))
288 |
289 | #Remove punctuations
290 | scrapped_words = [word for word in scrapped_words if word not in punctuations]
291 |
292 | return NER_string(scrapped_words)
293 |
294 | def create_NER_strings(textblob_text):
295 | ne_tagged_sent = st.tag(textblob_text.split())
296 | Organization = []
297 | Location = []
298 | Person = []
299 | for x,y in ne_tagged_sent:
300 | if y == 'ORGANIZATION':
301 | Organization.append(x)
302 | elif y== 'LOCATION':
303 | Location.append(x)
304 | elif y == 'PERSON':
305 | Person.append(x)
306 |
307 | Org_values = NER_string(Organization)
308 | Per_values = NER_string(Person)
309 | Loc_values = NER_string(Location)
310 | return Org_values, Per_values, Loc_values
311 |
312 |
313 | ########################### NER functions ends #########################################################
314 |
315 |
316 |
317 | if __name__ == "__main__":
318 | print "################################################################################################"
319 | print "Please be patient. This might take a while. \nWhen the tool completes running, it automatically opens a browser tab and displays the visuals."
320 | print "\nUnless the program stops with errors, ignore the warnings/messages if any."
321 | print "\nIf you want to interrupt the program execution, please press CTRL+C."
322 | print "################################################################################################"
323 |
324 | #Copy Firefox Browser History database i.e place.sqlite to current folder
325 | copy_browser_history_database()
326 |
327 | # create the dataframe from local copy of brwoser history database
328 | browser_history_dataframe = create_browser_history_dataframe("browser_history_database.sqlite3")
329 |
330 | os.system("python assets/pages/stats.py")
331 |
332 |
333 | #Seperate Facebook URLs from the browser_history_dataframe
334 | facebook_df = seperate_the_dataframes(browser_history_dataframe,"facebook.com")
335 |
336 | #Clean up the facebook dataframe to remove unwanted urls
337 | facebook_df = cleanup_facebook_dataframe(facebook_df)
338 |
339 | #classify the urls into photo, event, profile, group, search, post and messages;
340 | # add a new column "category_tags to the facebook_df
341 | facebook_df['category_tags']= facebook_df.apply(lambda row: Facebook_URL_Categorizre(row['url_location']), axis=1)
342 |
343 | #Copy only the "profile" URLs to a new dataframe
344 | facebook_profile_df = facebook_df.loc[facebook_df['category_tags']=='profile']
345 |
346 | if len(facebook_profile_df) == 0:
347 | print "\nno facebook profile data found"
348 | else:
349 | #Remove duplicates and copy to a new dataframe
350 | facebook_profile_clean =facebook_profile_df.drop_duplicates(['url_location'])
351 |
352 | sorted_facebook_profile_clean = facebook_profile_clean.sort_values(['visit_count', 'frecency'], ascending=[False, False])
353 |
354 | current_user = sorted_facebook_profile_clean ['name'].iloc[0]
355 | current_user_url = sorted_facebook_profile_clean ['url_location'].iloc[0]
356 |
357 | facebook_profile_clean_without_current_user = sorted_facebook_profile_clean[~sorted_facebook_profile_clean.url_location.str.contains(current_user_url)]
358 |
359 | pd.options.mode.chained_assignment = None
360 | facebook_profile_clean_without_current_user['url_location']= facebook_profile_clean_without_current_user.apply(lambda row: url_cleanup(row['url_location']), axis=1)
361 |
362 | pd.options.mode.chained_assignment = None
363 | facebook_profile_clean_without_current_user['real_name']= facebook_profile_clean_without_current_user.apply(lambda row: name_extractor(row['url_location'], row['name']), axis=1)
364 |
365 | Facebook_Profile_list = facebook_profile_clean_without_current_user.drop_duplicates(['url_location'])
366 |
367 | Facebook_Profile_list_Final = Facebook_Profile_list[['real_name','url_location', 'visit_count','frecency']]
368 |
369 | facebook_json = create_json_for_circle_packing("Facebook", Facebook_Profile_list_Final.nlargest(100, 'visit_count'))
370 |
371 | with open('assets/pages/facebook_profiles.json', 'w') as outfile:
372 | json.dump(facebook_json, outfile)
373 |
374 | ######################## End of Facebook related script ###################################################
375 |
376 | ######################## Start of Twitter related script ##################################################
377 |
378 | twitter_df= browser_history_dataframe[browser_history_dataframe['url_location'].str.contains("https://twitter.com")]
379 |
380 | twitter_stop_words = ["notifications","following","careers","url", "jobs", "support","status","likes", "settings","moments","help","search","account","widgets","hashtag","intent", "about"]
381 | twitter_pattern = '|'.join(map(re.escape, twitter_stop_words))
382 | twitter_df = twitter_df[~twitter_df.url_location.str.contains(twitter_pattern)]
383 |
384 | if len(twitter_df) == 0:
385 | print "\nno twitter profile data found"
386 | else:
387 | twitter_df['url_location']= twitter_df.apply(lambda row: twitter_url_cleanup(row['url_location']), axis=1)
388 | twitter_df= twitter_df[twitter_df.url_location.notnull()]
389 | twitter_df2 = twitter_df.drop_duplicates(['url_location'])
390 |
391 | sorted_twitter_df = twitter_df2.sort_values(['visit_count', 'frecency'], ascending=[False, False])
392 |
393 | current_user_twitter = sorted_twitter_df['name'].iloc[0]
394 | current_user_url_twitter = sorted_twitter_df['url_location'].iloc[0]
395 |
396 | twitter_df_without_current_user = sorted_twitter_df[~sorted_twitter_df.url_location.str.contains(current_user_url_twitter)]
397 |
398 | pd.options.mode.chained_assignment = None
399 | twitter_df_without_current_user['real_name']= twitter_df_without_current_user.apply(lambda row: twitter_name_extractor(row['url_location'], row['name']), axis=1)
400 | Twitter_Profile_Final = twitter_df_without_current_user[['real_name','url_location', 'visit_count','frecency']]
401 |
402 | twitter_json = create_json_for_circle_packing("Twitter", Twitter_Profile_Final.nlargest(100, 'visit_count'))
403 |
404 | with open('assets/pages/twitter_profiles.json', 'w') as outfile:
405 | json.dump(twitter_json, outfile)
406 |
407 | #################### End of Twitter related script ###################################################
408 |
409 |
410 | #################### Start of Google related script ##################################################
411 | google_df= browser_history_dataframe[browser_history_dataframe['url_location'].str.contains("www.google.")]
412 |
413 | google_df = google_df[google_df.url_location != "https://www.google.com/"]
414 |
415 | google_stop_words = ["url","gmail","maps", "intl", "inputtools", "gfe_rd", "landing", "accounts" "textise"]
416 | google_pattern = '|'.join(map(re.escape, google_stop_words))
417 | google_df = google_df[~google_df.url_location.str.contains(google_pattern)]
418 |
419 |
420 | google_df['search_query']= google_df.apply(lambda row: Google_search_query_keywords(row['url_location'], row['name']), axis=1)
421 |
422 | google_df = google_df[google_df.search_query.notnull()]
423 | google_df = google_df.drop_duplicates(['search_query'])
424 |
425 | #Preparing the data for graph
426 | # Convert the column of search queries to a list
427 | query_list = google_df['search_query'].tolist()
428 |
429 | # Combine all the list elements to a text blob and then encode it
430 | query_list_text_dump = ' '.join(query_list)
431 |
432 | query_list_text = unicodedata.normalize('NFKD', query_list_text_dump).encode('ascii','ignore')
433 |
434 | # Tokenize the text into words using NLTK library
435 | stopwords2 = set(nltk.corpus.stopwords.words('english'))
436 |
437 | words = nltk.tokenize.word_tokenize(query_list_text)
438 |
439 | # Remove single-character tokens (mostly punctuation)
440 | words = [word for word in words if len(word) > 1]
441 |
442 | # Remove numbers
443 | words = [word for word in words if not word.isdigit()]
444 |
445 | # Lowercase all words (default_stopwords are lowercase too)
446 | words = [word.lower() for word in words]
447 |
448 | # Remove stopwords
449 | words = [word for word in words if word not in stopwords2]
450 |
451 | punctuations = list(string.punctuation)
452 | punctuations.extend(("''", "//", "--","..."))
453 |
454 | #Remove punctuations
455 | words = [word for word in words if word not in punctuations]
456 |
457 | #Word frequency count using NLTk module
458 | query_frequency_dist = nltk.FreqDist(words)
459 |
460 | # Create a dictionary to plot a graph
461 | query_freq_df_unsorted = pd.DataFrame.from_dict(query_frequency_dist, orient='index').reset_index()
462 | query_freq_df_unsorted = query_freq_df_unsorted.rename(columns={'index':'query_word', 0:'count'})
463 |
464 | # Sort the dictionary of query word frequency counts
465 | query_freq_df = query_freq_df_unsorted.sort_values(['count'], ascending=[False])
466 |
467 | query_freq_df_top = query_freq_df.nlargest(50, 'count')
468 |
469 | data = [Bar(x= query_freq_df_top['query_word'].tolist(), y= query_freq_df_top['count'].tolist())]
470 | # plotly.offline.plot(data, output_type='div', filename='/word_plot.html')
471 | plotly.offline.plot(data, auto_open=False, filename='assets/pages/word_plot.html')
472 |
473 | #################### End of Google related script ###################################################
474 |
475 |
476 | #################### Start of Browsing pattern related script #######################################
477 |
478 |
479 | # Seperating only required columns from the original df
480 | pd.options.mode.chained_assignment = None
481 | browshistory_required_cols_df = browser_history_dataframe[['recent_visit','url_location', 'visit_count']]
482 |
483 | browshistory_required_cols_df['recent_visit'] = pd.to_datetime(browshistory_required_cols_df['recent_visit'])
484 |
485 | Unique_URLs_df = browshistory_required_cols_df.set_index('recent_visit').url_location.resample('H').agg({'Unique_URLs': 'unique'})
486 |
487 | pd.options.mode.chained_assignment = None
488 | Unique_URLs_df['Unique_URL_Count'] = Unique_URLs_df.apply(lambda row: Count_Unique_URLs(row['Unique_URLs']), axis=1)
489 |
490 | Unique_URLs_df['datetimevalues'] = Unique_URLs_df.index
491 |
492 | Unique_URLs_df['TimeOnly'] = Unique_URLs_df.apply(lambda row: strip_time(row['datetimevalues']), axis=1)
493 | Unique_URLs_df['DateOnly'] = Unique_URLs_df.apply(lambda row: strip_date(row['datetimevalues']), axis=1)
494 |
495 | heatmap_data = [
496 | Heatmap(
497 | x= Unique_URLs_df["DateOnly"].tolist(),
498 | y= Unique_URLs_df["TimeOnly"].tolist(),
499 | z= Unique_URLs_df["Unique_URL_Count"].tolist(),
500 | colorscale='Viridis'
501 | # colorscale=[[0, 'rgb(166,206,227)'], [0.25, 'rgb(31,120,180)'], [0.45, 'rgb(178,223,138)'], [0.65, 'rgb(51,160,44)'], [0.85, 'rgb(251,154,153)'], [1, 'rgb(227,26,28)']]
502 | )
503 | ]
504 | plotly.offline.plot(heatmap_data, auto_open=False, filename='assets/pages/browspattern_heatmap.html')
505 |
506 |
507 | browspat_bar_data = [Bar(x= Unique_URLs_df.index.tolist(), y= Unique_URLs_df['Unique_URL_Count'].tolist())]
508 |
509 | plotly.offline.plot(browspat_bar_data, auto_open=False, filename='assets/pages/wordcount_plot.html')
510 |
511 |
512 | #################### End of Browsing pattern related script #########################################
513 |
514 | #################### Start of NER related script ####################################################
515 |
516 | # Extract netloc to seperate column
517 | browser_history_dataframe['netloc']= browser_history_dataframe.apply(lambda row: netloc_extractor(row['url_location']), axis=1)
518 |
519 | Without_SE_SM_df = remove_SE_SM(browser_history_dataframe)
520 |
521 | clean_URL_duplicates = Without_SE_SM_df.drop_duplicates(['url_location'])
522 | clean_null_URLS = clean_URL_duplicates[clean_URL_duplicates.url_location.notnull()]
523 | clean_null_netloc = clean_null_URLS [clean_null_URLS .netloc.notnull()]
524 |
525 | sorted_Without_SE_SM_df = clean_null_netloc.sort_values(['visit_count', 'frecency'], ascending=[False, False])
526 |
527 | #Select URLs which are most visited
528 | top_URLS_df = sorted_Without_SE_SM_df.nlargest(100, 'visit_count')
529 |
530 | URLs_to_scrape = top_URLS_df.url_location.unique()
531 |
532 | #Fetch text from the top visited URLS by crawling
533 | text_from_website = grab_website_text(URLs_to_scrape)
534 |
535 | #normalize by converting the unicode text to string
536 | text_to_analyze = unicodedata.normalize('NFKD', text_from_website).encode('ascii','ignore')
537 |
538 | stopword_free_text = create_stopword_free_text(text_to_analyze)
539 |
540 | # Create a world cloud of the overall text
541 | wc_org = WordCloud(max_words =1000, width=600, height=400).generate(stopword_free_text)
542 | wc_org.to_file("assets/img/wc_all.png")
543 |
544 | (Org_values, Per_values, Loc_values) = create_NER_strings(text_to_analyze)
545 |
546 |
547 | wc_org = WordCloud(max_words =1000,width=600 , height=400).generate(Org_values)
548 | wc_org.to_file("assets/img/wc_org.png")
549 |
550 | wc_per = WordCloud(max_words =1000, width=600 , height=400).generate(Per_values)
551 | wc_per.to_file("assets/img/wc_per.png")
552 |
553 | wc_loc = WordCloud(max_words =1000, width=600 ,height=400).generate(Loc_values)
554 | wc_loc.to_file("assets/img/wc_loc.png")
555 |
556 |
557 | #################### END of NER related script ####################################################
558 |
559 | cwd = os.getcwd()
560 | file_to_open = "file:"+cwd+"/index.html"
561 | webbrowser.open_new_tab(file_to_open)
562 |
563 |
564 |
565 |
566 |
--------------------------------------------------------------------------------
/tool.py:
--------------------------------------------------------------------------------
1 | import shutil, sqlite3, glob, re, json, unicodedata, string, dateutil, webbrowser, requests
2 |
3 | from os.path import expanduser
4 |
5 | import pandas as pd
6 | from pandas.tseries.resample import TimeGrouper
7 |
8 | from urlparse import urlparse, parse_qs
9 | from collections import defaultdict
10 |
11 | import nltk
12 | from nltk.tokenize import word_tokenize
13 | from nltk import FreqDist
14 | from nltk.corpus import stopwords
15 | from nltk.tag.stanford import StanfordNERTagger
16 |
17 | from bs4 import BeautifulSoup
18 |
19 | from plotly.offline.offline import *
20 | from plotly.graph_objs import *
21 |
22 | from wordcloud import WordCloud
23 |
24 |
25 | ##################### ENV setting #################################################################
26 | os.environ['CLASSPATH'] = "assets/stanford-ner-2016-10-31"
27 | st = StanfordNERTagger('assets/stanford-ner-2016-10-31/classifiers/english.all.3class.distsim.crf.ser.gz')
28 | ###################################################################################################
29 |
30 |
31 | ########################### Generic functions begins ##############################################
32 | #Copying the place.sqlite file to local folder to the current local direcotry
33 | def copy_browser_history_database():
34 | shutil.copy2(glob.glob(expanduser("~") + '/.mozilla/firefox/*/places.sqlite')[0] , "browser_history_database.sqlite3")
35 |
36 |
37 |
38 | # Create a dataframe from local copy of browser history database i.e. from the place.sqalite
39 | def create_browser_history_dataframe(browser_history_database):
40 | query = "select datetime(moz_historyvisits.visit_date/1000000, 'unixepoch', 'localtime') as recent_visit, moz_places.url as url_location, moz_places.title as name, moz_places.visit_count as visit_count, moz_places.frecency as frecency from moz_places, moz_historyvisits where moz_historyvisits.place_id = moz_places.id order by moz_historyvisits.visit_date desc;"
41 | con = sqlite3.connect(browser_history_database, timeout=5)
42 | browser_history_dataframe = pd.read_sql_query(query, con)
43 | con.close()
44 | return browser_history_dataframe
45 |
46 | # Seperate the URLs for further analysis
47 | def seperate_the_dataframes(dataframe,url_string):
48 | return dataframe[dataframe['url_location'].str.contains(url_string)]
49 |
50 | ########################### Generic functions ends ################################################
51 |
52 |
53 | ########################### Facebook functions begins ##############################################
54 | #Classifying the (Facebook) urls into photo, event, profile, group, search and messages
55 | def Facebook_URL_Categorizre(URL):
56 | # print "categorizing Facebook URLs"
57 | category_tag = ''
58 | if urlparse(URL).netloc=="www.facebook.com":
59 | if "photo" in urlparse(URL).path:
60 | category_tag = "photo"
61 | elif "search" in urlparse(URL).path and "message" not in urlparse(URL).path and "photo" not in urlparse(URL).path and "group" not in urlparse(URL).path:
62 | category_tag = "search"
63 | elif "group" in urlparse(URL).path:
64 | category_tag = "group"
65 | elif "message" in urlparse(URL).path:
66 | category_tag = "message"
67 | elif "events" in urlparse(URL).path:
68 | category_tag = "event"
69 | elif "posts" in urlparse(URL).path:
70 | category_tag = "posts"
71 | else:
72 | category_tag = "profile"
73 | return category_tag
74 |
75 |
76 |
77 | def cleanup_facebook_dataframe(dataframe):
78 | #Remove the repeated profile urls
79 | dataframe = dataframe[dataframe.url_location != "https://www.facebook.com/"]
80 | dataframe = dataframe[dataframe.url_location != "https://www.facebook.com/#"]
81 | dataframe = dataframe[dataframe.url_location != "https://www.facebook.com/?_rdr=p"]
82 | dataframe = dataframe[dataframe.url_location != "https://www.facebook.com/?_rdr=p#"]
83 | dataframe = dataframe[dataframe.url_location != "https://www.facebook.com/?q="]
84 | dataframe = dataframe[dataframe.url_location != "https://www.facebook.com/?ref=tn_tnmn"]
85 |
86 | repeated_facebook_pages_words = ["people","settings", "dyi?", "react", "help", "support", "utm_source", "preview_cover" , "/?q=#/", "video.php" , "recover" ,"react", "login", "password", "l.php?", "viewas", "insights", "story_id", "sharer.php" ,"about" ,"pages", "?stype=lo", "homepage", "app_data", "ft[qid]" , "safetycheck","l.php?u=https", "location=profile_browser", "?next=", "friends" ,"videos", "?entry_point=", "deactivate", "careers", "saved", "timeline", "page_user_activity", "notif_t=page_fan", "manager", "notifications", "media", "notif", "oauth"]
87 | facebook_pattern = '|'.join(map(re.escape, repeated_facebook_pages_words))
88 | dataframe = dataframe[~dataframe.url_location.str.contains(facebook_pattern)]
89 |
90 | return dataframe
91 |
92 | def url_cleanup(url):
93 | parsed_url = urlparse(url)
94 | qry = parsed_url.query
95 | path = parsed_url.path
96 | if 'profile.php' in path:
97 | result = re.search('id=(\d+)',qry)
98 | return 'https://www.facebook.com/'+result.group(1)
99 | else:
100 | return "https://www.facebook.com"+parsed_url.path
101 |
102 | def name_extractor(URL, Name):
103 | try:
104 | if not Name or 'Facebook' in Name:
105 | return urlparse(URL).path.split("/",1)[1] #Prints
106 | else:
107 | return(''.join(c for c in Name.split(' - ')[0] if c.isalpha() or c in ' .').strip())
108 | except IndexError:
109 | print URL, Name
110 |
111 | def create_json_for_circle_packing(Domain, dataframe):
112 | gp = dataframe.groupby(['visit_count'])
113 | dict_json = {"name": Domain}
114 | children = []
115 | for name, group in gp:
116 | temp = {"name": name, "children": []}
117 | rgp = group.groupby(['frecency'])
118 | for n, g in rgp:
119 | temp["children"].append({
120 | "name": n,
121 | "children": [
122 | {"name": row["real_name"],
123 | "size": row["visit_count"] * 1000 / len(g)}
124 | for _, row in g.iterrows()
125 | ]
126 | })
127 | children.append(temp)
128 |
129 | dict_json["children"] = children
130 | return dict_json
131 |
132 |
133 | ########################### Facebook functions ends ##############################################
134 |
135 | ########################### Twitter fucntions begin ##############################################
136 |
137 | def twitter_url_cleanup(url):
138 | parsed_url = urlparse(url)
139 | if not parsed_url.path or parsed_url.path!="/":
140 | return 'https://www.twitter.com/'+ parsed_url.path.split("/",1)[1].split("/",1)[0]
141 |
142 | def twitter_name_extractor(URL, Name):
143 | try:
144 | if 'on Twitter' in Name or 'Twitter / Notifications' in Name:
145 | return URL.split("https://www.twitter.com/",1)[1]
146 | elif not Name or Name!='Twitter / ?':
147 | real_name = Name.split("|",1)[0].split("(",1)[0]
148 | if not real_name or Name =='Twitter / ?':
149 | # print "It was empty"
150 | return URL.split("https://www.twitter.com/",1)[1] #real_name
151 | else:
152 | return real_name #URL.split("https://www.twitter.com/",1)[1]
153 | except:
154 | return URL.split("https://www.twitter.com/",1)[1]
155 |
156 | ########################### Twitter functions ends ##############################################
157 |
158 | ########################### Google functions begins ##############################################
159 |
160 | def Google_search_query_keywords(URL, Name):
161 | if not Name:
162 | parsed_url = urlparse(URL)
163 | if "google" in parsed_url.netloc and parsed_url.path=='/search':
164 |
165 | query_dict = parse_qs(parsed_url.query, keep_blank_values=True)
166 |
167 | for k, v in query_dict.iteritems():
168 | if k=="q":
169 | return v[0]
170 |
171 | else:
172 | return ""
173 |
174 | else:
175 | return Name.split("- Google Search",1)[0]
176 |
177 | ########################### Google functions ends ##############################################
178 |
179 |
180 |
181 |
182 |
183 | ########################### Browsing pattern functions starts ##############################################
184 |
185 | def Count_Unique_URLs(URL_List):
186 | return len(URL_List)
187 |
188 | def strip_time(DateValue):
189 | return DateValue.time()
190 |
191 | def strip_date(DateValue):
192 | return DateValue.date()
193 |
194 |
195 | ########################### Browsing pattern functions ends ##############################################
196 |
197 | ########################### NER functions starts #########################################################
198 |
199 | def netloc_extractor(URL):
200 | return urlparse(URL).netloc
201 |
202 | def remove_SE_SM(dataframe):
203 | SocMedia_SearchEngines = ["mail", "gmail.com", "drive", "dropbox" ,"soundcloud.com", "spotify.com", "youtube.com","github.com", "stackoverflow.com", "facebook.com","twitter.com","google","amazon", "duckduckgo", "disconnect", "airbnb", "booking", "linkedin"]
204 | dataframe = dataframe[~dataframe.netloc.str.contains('|'.join(SocMedia_SearchEngines))]
205 | return dataframe
206 |
207 | def grab_website_text(url_list):
208 | cert = "assets/certs.pem"
209 | text_blob = ""
210 | text_list_dummy =[]
211 |
212 | for url in url_list:
213 |
214 | try:
215 | result = requests.get(url, verify= cert)
216 | result.raise_for_status()
217 |
218 |
219 | html = result.content
220 |
221 | soup = BeautifulSoup(html)
222 |
223 | # remove all script and style elements
224 | for script in soup(["script", "style"]):
225 | script.extract()
226 |
227 | # get text
228 | try:
229 | text = soup.body.get_text()
230 | # break into lines and remove leading and trailing space on each
231 |
232 | lines = (line.strip() for line in text.splitlines())
233 |
234 | # break multi-headlines into a line each
235 | chunks = (phrase.strip() for line in lines for phrase in line.split(" "))
236 |
237 | # drop blank lines
238 | text = ' '.join(chunk for chunk in chunks if chunk)
239 | except AttributeError:
240 | text = ""
241 |
242 |
243 | text_list_dummy.append(text)
244 |
245 | except requests.exceptions.RequestException:
246 | text_list_dummy.append("")
247 |
248 | text_blob = '\n'.join(text_list_dummy)
249 | return text_blob
250 |
251 |
252 | def NER_string(NER_list):
253 | NER_str = ""
254 | for item in NER_list:
255 | NER_str +=str(item)
256 | NER_str += " | "
257 | return NER_str
258 |
259 | def create_stopword_free_text(text_to_process):
260 | stoplist = stopwords.words('english')
261 |
262 | more_sw = "a about above across after again against all almost alone along already also although always am among an and another any anybody anyone anything anywhere are area areas aren't around as ask asked asking asks at away b back backed backing backs be became because become becomes been before began behind being beings below best better between big both but by c came can cannot can't case cases certain certainly clear clearly come could couldn't d did didn't differ different differently do does doesn't doing done don't down downed downing downs during e each early either end ended ending ends enough even evenly ever every everybody everyone everything everywhere f face faces fact facts far felt few find finds first for four from full fully further furthered furthering furthers g gave general generally get gets give given gives go going good goods got great greater greatest group grouped grouping groups h had hadn't has hasn't have haven't having he he'd he'll her here here's hers herself he's high higher highest him himself his how however how's i i'd if i'll i'm important in interest interested interesting interests into is isn't it its it's itself i've j just k keep keeps kind knew know known knows l large largely last later latest least less let lets let's like likely long longer longest m made make making man many may me member members men might more most mostly mr mrs much must mustn't my myself n necessary need needed needing needs never new newer newest next no nobody non noone nor not nothing now nowhere number numbers o of off often old older oldest on once one only open opened opening opens or order ordered ordering orders other others ought our ours ourselves out over own p part parted parting parts per perhaps place places point pointed pointing points possible present presented presenting presents problem problems put puts q quite r rather really right room rooms s said same saw say says second seconds see seem seemed seeming seems sees several shall shan't she she'd she'll she's should shouldn't show showed showing shows side sides since small smaller smallest so some somebody someone something somewhere state states still such sure t take taken than that that's the their theirs them themselves then there therefore there's these they they'd they'll they're they've thing things think thinks this those though thought thoughts three through thus to today together too took toward turn turned turning turns two u under until up upon us use used uses v very w want wanted wanting wants was wasn't way ways we we'd well we'll wells went were we're weren't we've what what's when when's where where's whether which while who whole whom who's whose why why's will with within without won't work worked working works would wouldn't x y year years yes yet you you'd you'll young younger youngest your you're yours yourself yourselves you've z"
263 |
264 | stoplist += more_sw.split()
265 |
266 | # Tokenize the text into words using NLTK library
267 | scrapped_words = nltk.tokenize.word_tokenize(text_to_process)
268 |
269 | # Remove single-character tokens (mostly punctuation)
270 | scrapped_words = [word for word in scrapped_words if len(word) > 1]
271 |
272 | # Remove numbers
273 | scrapped_words = [word for word in scrapped_words if not word.isdigit()]
274 |
275 | # Lowercase all words (default_stopwords are lowercase too)
276 | scrapped_words = [word.lower() for word in scrapped_words]
277 |
278 | # Remove stopwords
279 | scrapped_words = [word for word in scrapped_words if word not in stoplist]
280 |
281 | punctuations = list(string.punctuation)
282 | punctuations.extend(("''", "//", "--","..."))
283 |
284 | #Remove punctuations
285 | scrapped_words = [word for word in scrapped_words if word not in punctuations]
286 |
287 | return NER_string(scrapped_words)
288 |
289 | def create_NER_strings(textblob_text):
290 | ne_tagged_sent = st.tag(textblob_text.split())
291 | Organization = []
292 | Location = []
293 | Person = []
294 | for x,y in ne_tagged_sent:
295 | if y == 'ORGANIZATION':
296 | Organization.append(x)
297 | elif y== 'LOCATION':
298 | Location.append(x)
299 | elif y == 'PERSON':
300 | Person.append(x)
301 |
302 | Org_values = NER_string(Organization)
303 | Per_values = NER_string(Person)
304 | Loc_values = NER_string(Location)
305 | return Org_values, Per_values, Loc_values
306 |
307 |
308 | ########################### NER functions ends #########################################################
309 |
310 |
311 |
312 | if __name__ == "__main__":
313 | print "################################################################################################"
314 | print "Please be patient. This might take a while. \nWhen the tool completes running, it automatically opens a browser tab and displays the visuals."
315 | print "\nUnless the program stops with errors, ignore the warnings/messages if any."
316 | print "\nIf you want to interrupt the program execution, please press CTRL+C."
317 | print "################################################################################################"
318 |
319 | #Copy Firefox Browser History database i.e place.sqlite to current folder
320 | copy_browser_history_database()
321 |
322 | # create the dataframe from local copy of brwoser history database
323 | browser_history_dataframe = create_browser_history_dataframe("browser_history_database.sqlite3")
324 |
325 | os.system("python assets/pages/stats.py")
326 |
327 |
328 | #Seperate Facebook URLs from the browser_history_dataframe
329 | facebook_df = seperate_the_dataframes(browser_history_dataframe,"facebook.com")
330 |
331 | #Clean up the facebook dataframe to remove unwanted urls
332 | facebook_df = cleanup_facebook_dataframe(facebook_df)
333 |
334 | #classify the urls into photo, event, profile, group, search, post and messages;
335 | # add a new column "category_tags to the facebook_df
336 | facebook_df['category_tags']= facebook_df.apply(lambda row: Facebook_URL_Categorizre(row['url_location']), axis=1)
337 |
338 | #Copy only the "profile" URLs to a new dataframe
339 | facebook_profile_df = facebook_df.loc[facebook_df['category_tags']=='profile']
340 |
341 | if len(facebook_profile_df) == 0:
342 | print "\nno facebook profile data found"
343 | else:
344 | #Remove duplicates and copy to a new dataframe
345 | facebook_profile_clean =facebook_profile_df.drop_duplicates(['url_location'])
346 |
347 | sorted_facebook_profile_clean = facebook_profile_clean.sort_values(['visit_count', 'frecency'], ascending=[False, False])
348 |
349 | current_user = sorted_facebook_profile_clean ['name'].iloc[0]
350 | current_user_url = sorted_facebook_profile_clean ['url_location'].iloc[0]
351 |
352 | facebook_profile_clean_without_current_user = sorted_facebook_profile_clean[~sorted_facebook_profile_clean.url_location.str.contains(current_user_url)]
353 |
354 | pd.options.mode.chained_assignment = None
355 | facebook_profile_clean_without_current_user['url_location']= facebook_profile_clean_without_current_user.apply(lambda row: url_cleanup(row['url_location']), axis=1)
356 |
357 | pd.options.mode.chained_assignment = None
358 | facebook_profile_clean_without_current_user['real_name']= facebook_profile_clean_without_current_user.apply(lambda row: name_extractor(row['url_location'], row['name']), axis=1)
359 |
360 | Facebook_Profile_list = facebook_profile_clean_without_current_user.drop_duplicates(['url_location'])
361 |
362 | Facebook_Profile_list_Final = Facebook_Profile_list[['real_name','url_location', 'visit_count','frecency']]
363 |
364 | facebook_json = create_json_for_circle_packing("Facebook", Facebook_Profile_list_Final.nlargest(100, 'visit_count'))
365 |
366 | with open('assets/pages/facebook_profiles.json', 'w') as outfile:
367 | json.dump(facebook_json, outfile)
368 |
369 | ######################## End of Facebook related script ###################################################
370 |
371 | ######################## Start of Twitter related script ##################################################
372 |
373 | twitter_df= browser_history_dataframe[browser_history_dataframe['url_location'].str.contains("https://twitter.com")]
374 |
375 | twitter_stop_words = ["notifications","following","careers","url", "jobs", "support","status","likes", "settings","moments","help","search","account","widgets","hashtag","intent", "about"]
376 | twitter_pattern = '|'.join(map(re.escape, twitter_stop_words))
377 | twitter_df = twitter_df[~twitter_df.url_location.str.contains(twitter_pattern)]
378 |
379 | if len(twitter_df) == 0:
380 | print "\nno twitter profile data found"
381 | else:
382 | twitter_df['url_location']= twitter_df.apply(lambda row: twitter_url_cleanup(row['url_location']), axis=1)
383 | twitter_df= twitter_df[twitter_df.url_location.notnull()]
384 | twitter_df2 = twitter_df.drop_duplicates(['url_location'])
385 |
386 | sorted_twitter_df = twitter_df2.sort_values(['visit_count', 'frecency'], ascending=[False, False])
387 |
388 | current_user_twitter = sorted_twitter_df['name'].iloc[0]
389 | current_user_url_twitter = sorted_twitter_df['url_location'].iloc[0]
390 |
391 | twitter_df_without_current_user = sorted_twitter_df[~sorted_twitter_df.url_location.str.contains(current_user_url_twitter)]
392 |
393 | pd.options.mode.chained_assignment = None
394 | twitter_df_without_current_user['real_name']= twitter_df_without_current_user.apply(lambda row: twitter_name_extractor(row['url_location'], row['name']), axis=1)
395 | Twitter_Profile_Final = twitter_df_without_current_user[['real_name','url_location', 'visit_count','frecency']]
396 |
397 | twitter_json = create_json_for_circle_packing("Twitter", Twitter_Profile_Final.nlargest(100, 'visit_count'))
398 |
399 | with open('assets/pages/twitter_profiles.json', 'w') as outfile:
400 | json.dump(twitter_json, outfile)
401 |
402 | #################### End of Twitter related script ###################################################
403 |
404 |
405 | #################### Start of Google related script ##################################################
406 | google_df= browser_history_dataframe[browser_history_dataframe['url_location'].str.contains("www.google.")]
407 |
408 | google_df = google_df[google_df.url_location != "https://www.google.com/"]
409 |
410 | google_stop_words = ["url","gmail","maps", "intl", "inputtools", "gfe_rd", "landing", "accounts" "textise"]
411 | google_pattern = '|'.join(map(re.escape, google_stop_words))
412 | google_df = google_df[~google_df.url_location.str.contains(google_pattern)]
413 |
414 |
415 | google_df['search_query']= google_df.apply(lambda row: Google_search_query_keywords(row['url_location'], row['name']), axis=1)
416 |
417 | google_df = google_df[google_df.search_query.notnull()]
418 | google_df = google_df.drop_duplicates(['search_query'])
419 |
420 | #Preparing the data for graph
421 | # Convert the column of search queries to a list
422 | query_list = google_df['search_query'].tolist()
423 |
424 | # Combine all the list elements to a text blob and then encode it
425 | query_list_text_dump = ' '.join(query_list)
426 |
427 | query_list_text = unicodedata.normalize('NFKD', query_list_text_dump).encode('ascii','ignore')
428 |
429 | # Tokenize the text into words using NLTK library
430 | stopwords2 = set(nltk.corpus.stopwords.words('english'))
431 |
432 | words = nltk.tokenize.word_tokenize(query_list_text)
433 |
434 | # Remove single-character tokens (mostly punctuation)
435 | words = [word for word in words if len(word) > 1]
436 |
437 | # Remove numbers
438 | words = [word for word in words if not word.isdigit()]
439 |
440 | # Lowercase all words (default_stopwords are lowercase too)
441 | words = [word.lower() for word in words]
442 |
443 | # Remove stopwords
444 | words = [word for word in words if word not in stopwords2]
445 |
446 | punctuations = list(string.punctuation)
447 | punctuations.extend(("''", "//", "--","..."))
448 |
449 | #Remove punctuations
450 | words = [word for word in words if word not in punctuations]
451 |
452 | #Word frequency count using NLTk module
453 | query_frequency_dist = nltk.FreqDist(words)
454 |
455 | # Create a dictionary to plot a graph
456 | query_freq_df_unsorted = pd.DataFrame.from_dict(query_frequency_dist, orient='index').reset_index()
457 | query_freq_df_unsorted = query_freq_df_unsorted.rename(columns={'index':'query_word', 0:'count'})
458 |
459 | # Sort the dictionary of query word frequency counts
460 | query_freq_df = query_freq_df_unsorted.sort_values(['count'], ascending=[False])
461 |
462 | query_freq_df_top = query_freq_df.nlargest(50, 'count')
463 |
464 | data = [Bar(x= query_freq_df_top['query_word'].tolist(), y= query_freq_df_top['count'].tolist())]
465 | # plotly.offline.plot(data, output_type='div', filename='/word_plot.html')
466 | plotly.offline.plot(data, auto_open=False, filename='assets/pages/word_plot.html')
467 |
468 | #################### End of Google related script ###################################################
469 |
470 |
471 | #################### Start of Browsing pattern related script #######################################
472 |
473 |
474 | # Seperating only required columns from the original df
475 | pd.options.mode.chained_assignment = None
476 | browshistory_required_cols_df = browser_history_dataframe[['recent_visit','url_location', 'visit_count']]
477 |
478 | browshistory_required_cols_df['recent_visit'] = pd.to_datetime(browshistory_required_cols_df['recent_visit'])
479 |
480 | Unique_URLs_df = browshistory_required_cols_df.set_index('recent_visit').url_location.resample('H').agg({'Unique_URLs': 'unique'})
481 |
482 | pd.options.mode.chained_assignment = None
483 | Unique_URLs_df['Unique_URL_Count'] = Unique_URLs_df.apply(lambda row: Count_Unique_URLs(row['Unique_URLs']), axis=1)
484 |
485 | Unique_URLs_df['datetimevalues'] = Unique_URLs_df.index
486 |
487 | Unique_URLs_df['TimeOnly'] = Unique_URLs_df.apply(lambda row: strip_time(row['datetimevalues']), axis=1)
488 | Unique_URLs_df['DateOnly'] = Unique_URLs_df.apply(lambda row: strip_date(row['datetimevalues']), axis=1)
489 |
490 | heatmap_data = [
491 | Heatmap(
492 | x= Unique_URLs_df["DateOnly"].tolist(),
493 | y= Unique_URLs_df["TimeOnly"].tolist(),
494 | z= Unique_URLs_df["Unique_URL_Count"].tolist(),
495 | colorscale='Viridis'
496 | # colorscale=[[0, 'rgb(166,206,227)'], [0.25, 'rgb(31,120,180)'], [0.45, 'rgb(178,223,138)'], [0.65, 'rgb(51,160,44)'], [0.85, 'rgb(251,154,153)'], [1, 'rgb(227,26,28)']]
497 | )
498 | ]
499 | plotly.offline.plot(heatmap_data, auto_open=False, filename='assets/pages/browspattern_heatmap.html')
500 |
501 |
502 | browspat_bar_data = [Bar(x= Unique_URLs_df.index.tolist(), y= Unique_URLs_df['Unique_URL_Count'].tolist())]
503 |
504 | plotly.offline.plot(browspat_bar_data, auto_open=False, filename='assets/pages/wordcount_plot.html')
505 |
506 |
507 | #################### End of Browsing pattern related script #########################################
508 |
509 | #################### Start of NER related script ####################################################
510 |
511 | # Extract netloc to seperate column
512 | browser_history_dataframe['netloc']= browser_history_dataframe.apply(lambda row: netloc_extractor(row['url_location']), axis=1)
513 |
514 | Without_SE_SM_df = remove_SE_SM(browser_history_dataframe)
515 |
516 | clean_URL_duplicates = Without_SE_SM_df.drop_duplicates(['url_location'])
517 | clean_null_URLS = clean_URL_duplicates[clean_URL_duplicates.url_location.notnull()]
518 | clean_null_netloc = clean_null_URLS [clean_null_URLS .netloc.notnull()]
519 |
520 | sorted_Without_SE_SM_df = clean_null_netloc.sort_values(['visit_count', 'frecency'], ascending=[False, False])
521 |
522 | #Select URLs which are most visited
523 | top_URLS_df = sorted_Without_SE_SM_df.nlargest(100, 'visit_count')
524 |
525 | URLs_to_scrape = top_URLS_df.url_location.unique()
526 |
527 | #Fetch text from the top visited URLS by crawling
528 | text_from_website = grab_website_text(URLs_to_scrape)
529 |
530 | #normalize by converting the unicode text to string
531 | text_to_analyze = unicodedata.normalize('NFKD', text_from_website).encode('ascii','ignore')
532 |
533 | stopword_free_text = create_stopword_free_text(text_to_analyze)
534 |
535 | # Create a world cloud of the overall text
536 | wc_org = WordCloud(max_words =1000, width=600, height=400).generate(stopword_free_text)
537 | wc_org.to_file("assets/img/wc_all.png")
538 |
539 | (Org_values, Per_values, Loc_values) = create_NER_strings(text_to_analyze)
540 |
541 |
542 | wc_org = WordCloud(max_words =1000,width=600 , height=400).generate(Org_values)
543 | wc_org.to_file("assets/img/wc_org.png")
544 |
545 | wc_per = WordCloud(max_words =1000, width=600 , height=400).generate(Per_values)
546 | wc_per.to_file("assets/img/wc_per.png")
547 |
548 | wc_loc = WordCloud(max_words =1000, width=600 ,height=400).generate(Loc_values)
549 | wc_loc.to_file("assets/img/wc_loc.png")
550 |
551 |
552 |
553 |
554 |
555 |
556 |
557 |
558 |
559 | #################### Start of NER related script ####################################################
560 |
561 |
562 |
563 | webbrowser.open_new_tab("index.html")
564 |
565 |
566 |
--------------------------------------------------------------------------------
72 |