├── .gitignore ├── LICENSE ├── README.md ├── idp ├── __init__.py ├── parser │ ├── __init__.py │ ├── actorsparser.py │ ├── actressesparser.py │ ├── baseparser.py │ ├── directorsparser.py │ ├── genresparser.py │ ├── moviesparser.py │ ├── parsinghelper.py │ ├── plotparser.py │ ├── ratingsparser.py │ └── triviaparser.py ├── settings.py.example └── utils │ ├── __init__.py │ ├── dbscripthelper.py │ ├── decorators.py │ ├── filehandler.py │ ├── freebaseagent.py │ ├── listdownloader.py │ ├── loggerinitializer.py │ ├── regexhelper.py │ └── test │ ├── __init__.py │ └── filehandler_test.py ├── imdb_parse_path.txt ├── imdbparser.py └── samples ├── movies.list └── movies.list.gz /.gitignore: -------------------------------------------------------------------------------- 1 | *.py[cod] 2 | 3 | # C extensions 4 | *.so 5 | 6 | # Packages 7 | *.egg 8 | *.egg-info 9 | dist 10 | build 11 | eggs 12 | parts 13 | bin 14 | var 15 | sdist 16 | develop-eggs 17 | .installed.cfg 18 | lib 19 | lib64 20 | 21 | # Installer logs 22 | pip-log.txt 23 | 24 | # Unit test / coverage reports 25 | .coverage 26 | .tox 27 | nosetests.xml 28 | 29 | # Translations 30 | *.mo 31 | 32 | # Mr Developer 33 | .mr.developer.cfg 34 | .project 35 | .pydevproject 36 | 37 | #Temp files 38 | *~ 39 | *.tmp 40 | 41 | #swap files of vim 42 | *.swp 43 | 44 | #dont commit settings file 45 | idp/settings.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 | 635 | Copyright (C) 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 | Copyright (C) 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 | . -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | imdb-data-parser 2 | ================ 3 | 4 | Parses the IMDB dumps into CSV and Relational Database insert queries 5 | Uses IMDB dumps from: http://www.imdb.com/interfaces 6 | 7 | imdb-data-parser is a free software licensed by GPLv3. 8 | 9 | 10 | Requirements 11 | ================ 12 | * Python 3.x 13 | 14 | Configuring 15 | ================ 16 | All configuration data stays at `idp/settings.py.example` 17 | 18 | You need to copy this file as `settings.py` and edit this file before running the project 19 | 20 | cd idp 21 | cp settings.py.example settings.py 22 | your_favourite_editor settings.py 23 | 24 | You also need to have dump files at `INPUT_DIR` and you can download dump files from one of the FTP addresses on http://www.imdb.com/interfaces. 25 | 26 | Besides that you can make `imdb-data-parser` dowload dumps for you by giving `-u` argument: 27 | 28 | ~/imdb-data-parser$ ./imdbparser.py -u 29 | 30 | Executing 31 | --------- 32 | 33 | ~/imdb-data-parser$ ./imdbparser.py 34 | 35 | You can use -h parameter to see list of optional arguments 36 | 37 | ~/imdb-data-parser$ ./imdbparser.py -h 38 | 39 | SQL Dumps 40 | --------- 41 | You can use mode parameter to create SQL dumps 42 | 43 | ~/imdb-data-parser$ ./imdbparser.py -h 44 | 45 | Default configuration of MySQL doesn't allow insert data more than 16MB. You need to change your mysql max_allowed_packet size to insert sql dumps. 46 | 47 | max_allowed_packet = 256M 48 | 49 | Our movies data includes series, videos, tv shows for now. You can exclude them by this command: 50 | 51 | grep -v '("\\"' movies.list.sql | grep -v '\\(VG\\)' | grep -v "\\(TV\\)" | grep -v "{" | grep -v "????" | grep -v "(V\\\)" > movies.sql 52 | 53 | Note: SQL dumps tested with only mysql. 54 | -------------------------------------------------------------------------------- /idp/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dedeler/imdb-data-parser/20671ab98e2065bbe0a32aef0402776934a2863b/idp/__init__.py -------------------------------------------------------------------------------- /idp/parser/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dedeler/imdb-data-parser/20671ab98e2065bbe0a32aef0402776934a2863b/idp/parser/__init__.py -------------------------------------------------------------------------------- /idp/parser/actorsparser.py: -------------------------------------------------------------------------------- 1 | """ 2 | This file is part of imdb-data-parser. 3 | 4 | imdb-data-parser is free software: you can redistribute it and/or modify 5 | it under the terms of the GNU General Public License as published by 6 | the Free Software Foundation, either version 3 of the License, or 7 | (at your option) any later version. 8 | 9 | imdb-data-parser is distributed in the hope that it will be useful, 10 | but WITHOUT ANY WARRANTY; without even the implied warranty of 11 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 12 | GNU General Public License for more details. 13 | 14 | You should have received a copy of the GNU General Public License 15 | along with imdb-data-parser. If not, see . 16 | """ 17 | 18 | from .baseparser import * 19 | 20 | 21 | class ActorsParser(BaseParser): 22 | """ 23 | RegExp: /(.*?)\t+((.*? \(\S{4,}\)) ?(\(\S+\))? ?(?!\{\{SUSPENDED\}\})(\{(.*?) ?(\(\S+?\))?\})? ?(\{\{SUSPENDED\}\})?)\s*(\(.*?\))?\s*(\(.*\))?\s*(\[.*\])?\s*(<.*>)?$/gm 24 | pattern: (.*?)\t+((.*? \(\S{4,}\)) ?(\(\S+\))? ?(?!\{\{SUSPENDED\}\})(\{(.*?) ?(\(\S+?\))?\})? ?(\{\{SUSPENDED\}\})?)\s*(\(.*?\))?\s*(\(.*\))?\s*(\[.*\])?\s*(<.*>)?$ 25 | flags: gm 26 | 12 capturing groups: 27 | group 1: (.*?) surname, name 28 | group 2: #TITLE (UNIQUE KEY) 29 | group 3: (.*? \(\S{4,}\)) movie name + year 30 | group 4: (\(\S+\)) type ex:(TV) 31 | group 5: (\{(.*?) ?(\(\S+?\))?\}) series info ex: {Ally Abroad (#3.1)} 32 | group 6: (.*?) episode name ex: Ally Abroad 33 | group 7: (\(\S+?\)) episode number ex: (#3.1) 34 | group 8: (\{\{SUSPENDED\}\}) is suspended? 35 | group 9: (\(.*?\)) info 1 36 | group 10: (\(.*\)) info 2 37 | group 11: (\[.*\]) role 38 | group 12: () 39 | """ 40 | 41 | # properties 42 | base_matcher_pattern = '(.*?)\t+((.*? \(\S{4,}\)) ?(\(\S+\))? ?(?!\{\{SUSPENDED\}\})(\{(.*?) ?(\(\S+?\))?\})? ?(\{\{SUSPENDED\}\})?)\s*(\(.*?\))?\s*(\(.*\))?\s*(\[.*\])?\s*(<.*>)?$' 43 | input_file_name = "actors.list" 44 | number_of_lines_to_be_skipped = 239 45 | db_table_info = { 46 | 'tablename' : 'actors', 47 | 'columns' : [ 48 | {'colname' : 'name', 'colinfo' : DbScriptHelper.keywords['string'] + '(127)'}, 49 | {'colname' : 'surname', 'colinfo' : DbScriptHelper.keywords['string'] + '(127)'}, 50 | {'colname' : 'title', 'colinfo' : DbScriptHelper.keywords['string'] + '(255) NOT NULL'}, 51 | {'colname' : 'info_1', 'colinfo' : DbScriptHelper.keywords['string'] + '(127)'}, 52 | {'colname' : 'info_2', 'colinfo' : DbScriptHelper.keywords['string'] + '(127)'}, 53 | {'colname' : 'role', 'colinfo' : DbScriptHelper.keywords['string'] + '(127)'} 54 | ], 55 | 'constraints' : 'PRIMARY KEY(title)' 56 | } 57 | end_of_dump_delimiter = "" 58 | 59 | name = "" 60 | surname = "" 61 | 62 | def __init__(self, preferences_map): 63 | super(ActorsParser, self).__init__(preferences_map) 64 | self.first_one = True 65 | 66 | def parse_into_tsv(self, matcher): 67 | is_match = matcher.match(self.base_matcher_pattern) 68 | 69 | if(is_match): 70 | if(len(matcher.group(1).strip()) > 0): 71 | namelist = matcher.group(1).split(', ') 72 | if(len(namelist) == 2): 73 | self.name = namelist[1] 74 | self.surname = namelist[0] 75 | else: 76 | self.name = namelist[0] 77 | self.surname = "" 78 | 79 | self.tsv_file.write(self.name + self.seperator + self.surname + self.seperator + self.concat_regex_groups([2,9,10,11], None, matcher) + "\n") 80 | elif(len(matcher.get_last_string()) == 1): 81 | pass 82 | else: 83 | logging.critical("This line is fucked up: " + matcher.get_last_string()) 84 | self.fucked_up_count += 1 85 | 86 | def parse_into_db(self, matcher): 87 | is_match = matcher.match(self.base_matcher_pattern) 88 | 89 | if(is_match): 90 | if(len(matcher.group(1).strip()) > 0): 91 | namelist = matcher.group(1).split(', ') 92 | if(len(namelist) == 2): 93 | self.name = namelist[1] 94 | self.surname = namelist[0] 95 | else: 96 | self.name = namelist[0] 97 | self.surname = "" 98 | 99 | if(self.first_one): 100 | self.sql_file.write("(\"" + self.name + "\", \"" + self.surname + "\", " + self.concat_regex_groups([2,9,10,11], [2,3,4,5], matcher) + ")") 101 | self.first_one = False; 102 | else: 103 | self.sql_file.write(",\n(\"" + self.name + "\", \"" + self.surname + "\", " + self.concat_regex_groups([2,9,10,11], [2,3,4,5], matcher) + ")") 104 | 105 | elif(len(matcher.get_last_string()) == 1): 106 | pass 107 | else: 108 | logging.critical("This line is fucked up: " + matcher.get_last_string()) 109 | self.fucked_up_count += 1 110 | -------------------------------------------------------------------------------- /idp/parser/actressesparser.py: -------------------------------------------------------------------------------- 1 | """ 2 | This file is part of imdb-data-parser. 3 | 4 | imdb-data-parser is free software: you can redistribute it and/or modify 5 | it under the terms of the GNU General Public License as published by 6 | the Free Software Foundation, either version 3 of the License, or 7 | (at your option) any later version. 8 | 9 | imdb-data-parser is distributed in the hope that it will be useful, 10 | but WITHOUT ANY WARRANTY; without even the implied warranty of 11 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 12 | GNU General Public License for more details. 13 | 14 | You should have received a copy of the GNU General Public License 15 | along with imdb-data-parser. If not, see . 16 | """ 17 | 18 | from .baseparser import * 19 | 20 | 21 | class ActressesParser(BaseParser): 22 | """ 23 | RegExp: /(.*?)\t+((.*? \(\S{4,}\)) ?(\(\S+\))? ?(?!\{\{SUSPENDED\}\})(\{(.*?) ?(\(\S+?\))?\})? ?(\{\{SUSPENDED\}\})?)\s*(\(.*?\))?\s*(\(.*\))?\s*(\[.*\])?\s*(<.*>)?$/gm 24 | pattern: (.*?)\t+((.*? \(\S{4,}\)) ?(\(\S+\))? ?(?!\{\{SUSPENDED\}\})(\{(.*?) ?(\(\S+?\))?\})? ?(\{\{SUSPENDED\}\})?)\s*(\(.*?\))?\s*(\(.*\))?\s*(\[.*\])?\s*(<.*>)?$ 25 | flags: gm 26 | 12 capturing groups: 27 | group 1: (.*?) surname, name 28 | group 2: #TITLE (UNIQUE KEY) 29 | group 3: (.*? \(\S{4,}\)) movie name + year 30 | group 4: (\(\S+\)) type ex:(TV) 31 | group 5: (\{(.*?) ?(\(\S+?\))?\}) series info ex: {Ally Abroad (#3.1)} 32 | group 6: (.*?) episode name ex: Ally Abroad 33 | group 7: (\(\S+?\)) episode number ex: (#3.1) 34 | group 8: (\{\{SUSPENDED\}\}) is suspended? 35 | group 9: (\(.*?\)) info 1 36 | group 10: (\(.*\)) info 2 37 | group 11: (\[.*\]) role 38 | group 12: () 39 | """ 40 | 41 | # properties 42 | base_matcher_pattern = '(.*?)\t+((.*? \(\S{4,}\)) ?(\(\S+\))? ?(?!\{\{SUSPENDED\}\})(\{(.*?) ?(\(\S+?\))?\})? ?(\{\{SUSPENDED\}\})?)\s*(\(.*?\))?\s*(\(.*\))?\s*(\[.*\])?\s*(<.*>)?$' 43 | input_file_name = "actresses.list" 44 | number_of_lines_to_be_skipped = 241 45 | db_table_info = { 46 | 'tablename' : 'actresses', 47 | 'columns' : [ 48 | {'colname' : 'name', 'colinfo' : DbScriptHelper.keywords['string'] + '(127)'}, 49 | {'colname' : 'surname', 'colinfo' : DbScriptHelper.keywords['string'] + '(127)'}, 50 | {'colname' : 'title', 'colinfo' : DbScriptHelper.keywords['string'] + '(255) NOT NULL'}, 51 | {'colname' : 'info_1', 'colinfo' : DbScriptHelper.keywords['string'] + '(127)'}, 52 | {'colname' : 'info_2', 'colinfo' : DbScriptHelper.keywords['string'] + '(127)'}, 53 | {'colname' : 'role', 'colinfo' : DbScriptHelper.keywords['string'] + '(127)'} 54 | ], 55 | 'constraints' : 'PRIMARY KEY(title)' 56 | } 57 | end_of_dump_delimiter = "" 58 | 59 | name = "" 60 | surname = "" 61 | 62 | def __init__(self, preferences_map): 63 | super(ActressesParser, self).__init__(preferences_map) 64 | self.first_one = True 65 | 66 | def parse_into_tsv(self, matcher): 67 | is_match = matcher.match(self.base_matcher_pattern) 68 | 69 | if(is_match): 70 | if(len(matcher.group(1).strip()) > 0): 71 | namelist = matcher.group(1).split(', ') 72 | if(len(namelist) == 2): 73 | self.name = namelist[1] 74 | self.surname = namelist[0] 75 | else: 76 | self.name = namelist[0] 77 | self.surname = "" 78 | 79 | self.tsv_file.write(self.name + self.seperator + self.surname + self.seperator + self.concat_regex_groups([2,9,10,11], None, matcher) + "\n") 80 | elif(len(matcher.get_last_string()) == 1): 81 | pass 82 | else: 83 | logging.critical("This line is fucked up: " + matcher.get_last_string()) 84 | self.fucked_up_count += 1 85 | 86 | def parse_into_db(self, matcher): 87 | is_match = matcher.match(self.base_matcher_pattern) 88 | 89 | if(is_match): 90 | if(len(matcher.group(1).strip()) > 0): 91 | namelist = matcher.group(1).split(', ') 92 | if(len(namelist) == 2): 93 | self.name = namelist[1] 94 | self.surname = namelist[0] 95 | else: 96 | self.name = namelist[0] 97 | self.surname = "" 98 | 99 | if(self.first_one): 100 | self.sql_file.write("(\"" + self.name + "\", \"" + self.surname + "\", " + self.concat_regex_groups([2,9,10,11], [2,3,4,5], matcher) + ")") 101 | self.first_one = False; 102 | else: 103 | self.sql_file.write(",\n(\"" + self.name + "\", \"" + self.surname + "\", " + self.concat_regex_groups([2,9,10,11], [2,3,4,5], matcher) + ")") 104 | 105 | elif(len(matcher.get_last_string()) == 1): 106 | pass 107 | else: 108 | logging.critical("This line is fucked up: " + matcher.get_last_string()) 109 | self.fucked_up_count += 1 110 | -------------------------------------------------------------------------------- /idp/parser/baseparser.py: -------------------------------------------------------------------------------- 1 | """ 2 | This file is part of imdb-data-parser. 3 | 4 | imdb-data-parser is free software: you can redistribute it and/or modify 5 | it under the terms of the GNU General Public License as published by 6 | the Free Software Foundation, either version 3 of the License, or 7 | (at your option) any later version. 8 | 9 | imdb-data-parser is distributed in the hope that it will be useful, 10 | but WITHOUT ANY WARRANTY; without even the implied warranty of 11 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 12 | GNU General Public License for more details. 13 | 14 | You should have received a copy of the GNU General Public License 15 | along with imdb-data-parser. If not, see . 16 | """ 17 | 18 | import re 19 | import logging 20 | from abc import * 21 | from ..utils.filehandler import FileHandler 22 | from ..utils.regexhelper import RegExHelper 23 | from ..utils.decorators import duration_logged 24 | from ..utils.dbscripthelper import DbScriptHelper 25 | 26 | 27 | class BaseParser(metaclass=ABCMeta): 28 | """ 29 | Base class for all parser classes 30 | 31 | This class holds common methods for all parser classes and 32 | must be implemented by any Parser class 33 | 34 | Implementing classes' responsibilities are as follows: 35 | * Implement parse_into_tsv function 36 | * Implement parse_into_db function 37 | * Calculate fuckedUpCount and store in self.fuckedUpCount 38 | * Define following properties: 39 | - baseMatcherPattern 40 | - inputFileName 41 | - numberOfLinesToBeSkipped 42 | - scripts 43 | """ 44 | 45 | seperator = "\t" #TODO: get from settings 46 | 47 | def __init__(self, preferences_map): 48 | self.mode = preferences_map['mode'] 49 | self.filehandler = FileHandler(self.input_file_name, preferences_map) 50 | self.input_file = self.filehandler.get_input_file() 51 | 52 | if (self.mode == "TSV"): 53 | self.tsv_file = self.filehandler.get_tsv_file() 54 | elif (self.mode == "SQL"): 55 | self.sql_file = self.filehandler.get_sql_file() 56 | self.scripthelper = DbScriptHelper(self.db_table_info) 57 | self.sql_file.write(self.scripthelper.scripts['drop']) 58 | self.sql_file.write(self.scripthelper.scripts['create']) 59 | self.sql_file.write(self.scripthelper.scripts['insert']) 60 | 61 | @abstractmethod 62 | def parse_into_tsv(self, matcher): 63 | raise NotImplemented 64 | 65 | @abstractmethod 66 | def parse_into_db(self, matcher): 67 | raise NotImplemented 68 | 69 | @duration_logged 70 | def start_processing(self): 71 | ''' 72 | Actual parsing and generation of scripts (tsv & sql) are done here. 73 | ''' 74 | 75 | self.fucked_up_count = 0 76 | counter = 0 77 | number_of_processed_lines = 0 78 | 79 | for line in self.input_file : #assuming the file is opened in the subclass before here 80 | if(number_of_processed_lines >= self.number_of_lines_to_be_skipped): 81 | #end of data 82 | if(self.end_of_dump_delimiter != "" and self.end_of_dump_delimiter in line): 83 | break 84 | 85 | matcher = RegExHelper(line) 86 | 87 | if(self.mode == "TSV"): 88 | ''' 89 | give the matcher directly to implementing class 90 | and let it decide what to do when regEx is matched and unmatched 91 | ''' 92 | self.parse_into_tsv(matcher) 93 | elif(self.mode == "SQL"): 94 | self.parse_into_db(matcher) 95 | else: 96 | raise NotImplemented("Mode: " + self.mode) 97 | 98 | number_of_processed_lines += 1 99 | 100 | #print("Processed lines: %d\r" % (number_of_processed_lines), end="") 101 | 102 | self.input_file.close() 103 | 104 | if(self.mode == "SQL"): 105 | self.sql_file.write(";\n COMMIT;") 106 | self.sql_file.close() 107 | 108 | if 'outputFile' in locals(): 109 | self.output_file.flush() 110 | self.output_file.close() 111 | 112 | # fuckedUpCount is calculated in implementing class 113 | logging.info("Finished with " + str(self.fucked_up_count) + " fucked up line") 114 | 115 | def concat_regex_groups(self, group_list, col_list, matcher): 116 | ret_val = "" 117 | if col_list == None: 118 | ret_val = self.seperator.join('%s' % (matcher.group(i)) for i in group_list) 119 | else: 120 | for i in range(len(group_list)): 121 | if DbScriptHelper.keywords['string'] in self.db_table_info['columns'][col_list[i]]['colinfo']: 122 | ret_val += "\"" + re.escape(matcher.group(group_list[i])) + "\", " 123 | else: 124 | ret_val += matcher.group(group_list[i]) + ", " 125 | ret_val = ret_val[:-2] 126 | return ret_val 127 | 128 | ##### Below methods force associated properties to be defined in any derived class ##### 129 | 130 | @abstractproperty 131 | def base_matcher_pattern(self): 132 | raise NotImplemented 133 | 134 | @abstractproperty 135 | def input_file_name(self): 136 | raise NotImplemented 137 | 138 | @abstractproperty 139 | def number_of_lines_to_be_skipped(self): 140 | raise NotImplemented 141 | 142 | @abstractproperty 143 | def db_table_info(self): 144 | raise NotImplemented 145 | 146 | @abstractproperty 147 | def end_of_dump_delimiter(self): 148 | raise NotImplemented 149 | -------------------------------------------------------------------------------- /idp/parser/directorsparser.py: -------------------------------------------------------------------------------- 1 | """ 2 | This file is part of imdb-data-parser. 3 | 4 | imdb-data-parser is free software: you can redistribute it and/or modify 5 | it under the terms of the GNU General Public License as published by 6 | the Free Software Foundation, either version 3 of the License, or 7 | (at your option) any later version. 8 | 9 | imdb-data-parser is distributed in the hope that it will be useful, 10 | but WITHOUT ANY WARRANTY; without even the implied warranty of 11 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 12 | GNU General Public License for more details. 13 | 14 | You should have received a copy of the GNU General Public License 15 | along with imdb-data-parser. If not, see . 16 | """ 17 | 18 | from .baseparser import * 19 | 20 | 21 | class DirectorsParser(BaseParser): 22 | """ 23 | RegExp: /(.*?)\t+((.*? \(\S{4,}\)) ?(\(\S+\))? ?(?!\{\{SUSPENDED\}\})(\{(.*?) ?(\(\S+?\))?\})? ?(\{\{SUSPENDED\}\})?)\s*(\(.*\)|EDIT)?\s*(<.*>)?$/gm 24 | pattern: (.*?)\t+((.*? \(\S{4,}\)) ?(\(\S+\))? ?(?!\{\{SUSPENDED\}\})(\{(.*?) ?(\(\S+?\))?\})? ?(\{\{SUSPENDED\}\})?)\s*(\(.*\)|EDIT)?\s*(<.*>)?$ 25 | flags: gm 26 | 10 capturing groups: 27 | group 1: (.*?) surname, name 28 | group 2: #TITLE (UNIQUE KEY) 29 | group 3: (.*? \(\S{4,}\)) movie name + year 30 | group 4: (\(\S+\)) type ex:(TV) 31 | group 5: (\{(.*?) ?(\(\S+?\))?\}) series info ex: {Ally Abroad (#3.1)} 32 | group 6: (.*?) episode name ex: Ally Abroad 33 | group 7: (\(\S+?\)) episode number ex: (#3.1) 34 | group 8: (\{\{SUSPENDED\}\}) is suspended? 35 | group 9: (\(.*\)) info 36 | group 10: () 37 | """ 38 | 39 | # properties 40 | base_matcher_pattern = '(.*?)\t+((.*? \(\S{4,}\)) ?(\(\S+\))? ?(?!\{\{SUSPENDED\}\})(\{(.*?) ?(\(\S+?\))?\})? ?(\{\{SUSPENDED\}\})?)\s*(\(.*\)|EDIT)?\s*(<.*>)?$' 41 | input_file_name = "directors.list" 42 | number_of_lines_to_be_skipped = 235 43 | db_table_info = { 44 | 'tablename' : 'directors', 45 | 'columns' : [ 46 | {'colname' : 'name', 'colinfo' : DbScriptHelper.keywords['string'] + '(127)'}, 47 | {'colname' : 'surname', 'colinfo' : DbScriptHelper.keywords['string'] + '(127)'}, 48 | {'colname' : 'title', 'colinfo' : DbScriptHelper.keywords['string'] + '(255) NOT NULL'}, 49 | {'colname' : 'info', 'colinfo' : DbScriptHelper.keywords['string'] + '(127)'} 50 | ], 51 | 'constraints' : 'PRIMARY KEY(title)' 52 | } 53 | end_of_dump_delimiter = "" 54 | 55 | name = "" 56 | surname = "" 57 | 58 | def __init__(self, preferences_map): 59 | super(DirectorsParser, self).__init__(preferences_map) 60 | self.first_one = True 61 | 62 | def parse_into_tsv(self, matcher): 63 | is_match = matcher.match(self.base_matcher_pattern) 64 | 65 | if(is_match): 66 | if(len(matcher.group(1).strip()) > 0): 67 | namelist = matcher.group(1).split(', ') 68 | if(len(namelist) == 2): 69 | self.name = namelist[1] 70 | self.surname = namelist[0] 71 | else: 72 | self.name = namelist[0] 73 | self.surname = "" 74 | 75 | self.tsv_file.write(self.name + self.seperator + self.surname + self.seperator + self.concat_regex_groups([2,9], None, matcher) + "\n") 76 | elif(len(matcher.get_last_string()) == 1): 77 | pass 78 | else: 79 | logging.critical("This line is fucked up: " + matcher.get_last_string()) 80 | self.fucked_up_count += 1 81 | 82 | def parse_into_db(self, matcher): 83 | is_match = matcher.match(self.base_matcher_pattern) 84 | 85 | if(is_match): 86 | if(len(matcher.group(1).strip()) > 0): 87 | namelist = matcher.group(1).split(', ') 88 | if(len(namelist) == 2): 89 | self.name = namelist[1] 90 | self.surname = namelist[0] 91 | else: 92 | self.name = namelist[0] 93 | self.surname = "" 94 | 95 | if(self.first_one): 96 | self.sql_file.write("(\"" + self.name + "\", \"" + self.surname + "\", " + self.concat_regex_groups([2,9], [2,3], matcher) + ")") 97 | self.first_one = False; 98 | else: 99 | self.sql_file.write(",\n(\"" + self.name + "\", \"" + self.surname + "\", " + self.concat_regex_groups([2,9], [2,3], matcher) + ")") 100 | 101 | elif(len(matcher.get_last_string()) == 1): 102 | pass 103 | else: 104 | logging.critical("This line is fucked up: " + matcher.get_last_string()) 105 | self.fucked_up_count += 1 106 | -------------------------------------------------------------------------------- /idp/parser/genresparser.py: -------------------------------------------------------------------------------- 1 | """ 2 | This file is part of imdb-data-parser. 3 | 4 | imdb-data-parser is free software: you can redistribute it and/or modify 5 | it under the terms of the GNU General Public License as published by 6 | the Free Software Foundation, either version 3 of the License, or 7 | (at your option) any later version. 8 | 9 | imdb-data-parser is distributed in the hope that it will be useful, 10 | but WITHOUT ANY WARRANTY; without even the implied warranty of 11 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 12 | GNU General Public License for more details. 13 | 14 | You should have received a copy of the GNU General Public License 15 | along with imdb-data-parser. If not, see . 16 | """ 17 | 18 | from .baseparser import * 19 | 20 | 21 | class GenresParser(BaseParser): 22 | """ 23 | RegExp: /((.*? \(\S{4,}\)) ?(\(\S+\))? ?(?!\{\{SUSPENDED\}\})(\{(.*?) ?(\(\S+?\))?\})? ?(\{\{SUSPENDED\}\})?)\t+(.*)$/gm 24 | pattern: ((.*? \(\S{4,}\)) ?(\(\S+\))? ?(?!\{\{SUSPENDED\}\})(\{(.*?) ?(\(\S+?\))?\})? ?(\{\{SUSPENDED\}\})?)\t+(.*)$ 25 | flags: gm 26 | 8 capturing groups: 27 | group 1: #TITLE (UNIQUE KEY) 28 | group 2: (.*? \(\S{4,}\)) movie name + year 29 | group 3: (\(\S+\)) type ex:(TV) 30 | group 4: (\{(.*?) ?(\(\S+?\))?\}) series info ex: {Ally Abroad (#3.1)} 31 | group 5: (.*?) episode name ex: Ally Abroad 32 | group 6: ((\(\S+?\)) episode number ex: (#3.1) 33 | group 7: (\{\{SUSPENDED\}\}) is suspended? 34 | group 8: (.*) genre 35 | """ 36 | 37 | # properties 38 | base_matcher_pattern = "((.*? \(\S{4,}\)) ?(\(\S+\))? ?(?!\{\{SUSPENDED\}\})(\{(.*?) ?(\(\S+?\))?\})? ?(\{\{SUSPENDED\}\})?)\t+(.*)$" 39 | input_file_name = "genres.list" 40 | number_of_lines_to_be_skipped = 378 41 | db_table_info = { 42 | 'tablename' : 'genres', 43 | 'columns' : [ 44 | {'colname' : 'title', 'colinfo' : DbScriptHelper.keywords['string'] + '(255) NOT NULL'}, 45 | {'colname' : 'genre', 'colinfo' : DbScriptHelper.keywords['string'] + '(127)'} 46 | ], 47 | 'constraints' : 'PRIMARY KEY(title)' 48 | } 49 | end_of_dump_delimiter = "" 50 | 51 | def __init__(self, preferences_map): 52 | super(GenresParser, self).__init__(preferences_map) 53 | self.first_one = True 54 | 55 | def parse_into_tsv(self, matcher): 56 | is_match = matcher.match(self.base_matcher_pattern) 57 | 58 | if(is_match): 59 | self.tsv_file.write(self.concat_regex_groups([1,8], None, matcher) + "\n") 60 | else: 61 | logging.critical("This line is fucked up: " + matcher.get_last_string()) 62 | self.fucked_up_count += 1 63 | 64 | def parse_into_db(self, matcher): 65 | is_match = matcher.match(self.base_matcher_pattern) 66 | 67 | if(is_match): 68 | if(self.first_one): 69 | self.sql_file.write("(" + self.concat_regex_groups([1,8], [0,1], matcher) + ")") 70 | self.first_one = False; 71 | else: 72 | self.sql_file.write(",\n(" + self.concat_regex_groups([1,8], [0,1], matcher) + ")") 73 | else: 74 | logging.critical("This line is fucked up: " + matcher.get_last_string()) 75 | self.fucked_up_count += 1 76 | -------------------------------------------------------------------------------- /idp/parser/moviesparser.py: -------------------------------------------------------------------------------- 1 | """ 2 | This file is part of imdb-data-parser. 3 | 4 | imdb-data-parser is free software: you can redistribute it and/or modify 5 | it under the terms of the GNU General Public License as published by 6 | the Free Software Foundation, either version 3 of the License, or 7 | (at your option) any later version. 8 | 9 | imdb-data-parser is distributed in the hope that it will be useful, 10 | but WITHOUT ANY WARRANTY; without even the implied warranty of 11 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 12 | GNU General Public License for more details. 13 | 14 | You should have received a copy of the GNU General Public License 15 | along with imdb-data-parser. If not, see . 16 | """ 17 | 18 | from .baseparser import * 19 | 20 | 21 | class MoviesParser(BaseParser): 22 | """ 23 | Parses movies.list dump 24 | 25 | RegExp: /((.*? \(\S{4,}\)) ?(\(\S+\))? ?(?!\{\{SUSPENDED\}\})(\{(.*?) ?(\(\S+?\))?\})? ?(\{\{SUSPENDED\}\})?)\t+(.*)$/gm 26 | pattern: ((.*? \(\S{4,}\)) ?(\(\S+\))? ?(?!\{\{SUSPENDED\}\})(\{(.*?) ?(\(\S+?\))?\})? ?(\{\{SUSPENDED\}\})?)\t+(.*)$ 27 | flags: gm 28 | 8 capturing groups: 29 | group 1: #TITLE (UNIQUE KEY) 30 | group 2: (.*? \(\S{4,}\)) movie name + year 31 | group 3: (\(\S+\)) type ex:(TV) 32 | group 4: (\{(.*?) ?(\(\S+?\))?\}) series info ex: {Ally Abroad (#3.1)} 33 | group 5: (.*?) episode name ex: Ally Abroad 34 | group 6: ((\(\S+?\)) episode number ex: (#3.1) 35 | group 7: (\{\{SUSPENDED\}\}) is suspended? 36 | group 8: (.*) year 37 | """ 38 | 39 | # properties 40 | base_matcher_pattern = "((.*? \(\S{4,}\)) ?(\(\S+\))? ?(?!\{\{SUSPENDED\}\})(\{(.*?) ?(\(\S+?\))?\})? ?(\{\{SUSPENDED\}\})?)\t+(.*)$" 41 | input_file_name = "movies.list" 42 | #FIXME: zafer: I think using a static number is critical for us. If imdb sends a new file with first 10 line fucked then we're also fucked 43 | number_of_lines_to_be_skipped = 15 44 | db_table_info = { 45 | 'tablename' : 'movies', 46 | 'columns' : [ 47 | {'colname' : 'title', 'colinfo' : DbScriptHelper.keywords['string'] + '(255) NOT NULL'}, 48 | {'colname' : 'full_name', 'colinfo' : DbScriptHelper.keywords['string'] + '(127)'}, 49 | {'colname' : 'type', 'colinfo' : DbScriptHelper.keywords['string'] + '(20)'}, 50 | {'colname' : 'ep_name', 'colinfo' : DbScriptHelper.keywords['string'] + '(127)'}, 51 | {'colname' : 'ep_num', 'colinfo' : DbScriptHelper.keywords['string'] + '(20)'}, 52 | {'colname' : 'suspended', 'colinfo' : DbScriptHelper.keywords['string'] + '(20)'}, 53 | {'colname' : 'year', 'colinfo' : DbScriptHelper.keywords['string'] + '(20)'} 54 | ], 55 | 'constraints' : 'PRIMARY KEY(title)' 56 | } 57 | end_of_dump_delimiter = "--------------------------------------------------------------------------------" 58 | 59 | def __init__(self, preferences_map): 60 | super(MoviesParser, self).__init__(preferences_map) 61 | self.first_one = True 62 | 63 | def parse_into_tsv(self, matcher): 64 | is_match = matcher.match(self.base_matcher_pattern) 65 | 66 | if(is_match): 67 | self.tsv_file.write(self.concat_regex_groups([1,2,3,5,6,7,8], None, matcher) + "\n") 68 | else: 69 | logging.critical("This line is fucked up: " + matcher.get_last_string()) 70 | self.fucked_up_count += 1 71 | 72 | def parse_into_db(self, matcher): 73 | is_match = matcher.match(self.base_matcher_pattern) 74 | 75 | if(is_match): 76 | if(self.first_one): 77 | self.sql_file.write("(" + self.concat_regex_groups([1,2,3,5,6,7,8], [0,1,2,3,4,5,6], matcher) + ")") 78 | self.first_one = False; 79 | else: 80 | self.sql_file.write(",\n(" + self.concat_regex_groups([1,2,3,5,6,7,8], [0,1,2,3,4,5,6], matcher) + ")") 81 | else: 82 | logging.critical("This line is fucked up: " + matcher.get_last_string()) 83 | self.fucked_up_count += 1 84 | -------------------------------------------------------------------------------- /idp/parser/parsinghelper.py: -------------------------------------------------------------------------------- 1 | """ 2 | This file is part of imdb-data-parser. 3 | 4 | imdb-data-parser is free software: you can redistribute it and/or modify 5 | it under the terms of the GNU General Public License as published by 6 | the Free Software Foundation, either version 3 of the License, or 7 | (at your option) any later version. 8 | 9 | imdb-data-parser is distributed in the hope that it will be useful, 10 | but WITHOUT ANY WARRANTY; without even the implied warranty of 11 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 12 | GNU General Public License for more details. 13 | 14 | You should have received a copy of the GNU General Public License 15 | along with imdb-data-parser. If not, see . 16 | """ 17 | 18 | import logging 19 | import traceback 20 | from idp import settings 21 | 22 | 23 | class ParsingHelper(object): 24 | """ 25 | ParsingHelper manages parsing order 26 | """ 27 | 28 | @staticmethod 29 | def parse_one(item, preferences_map): 30 | 31 | def get_parser_class_for(item_name): 32 | """ 33 | Thanks to http://stackoverflow.com/a/452981 34 | """ 35 | kls = "idp.parser." + item_name + "parser." + item_name.title() + "Parser" 36 | parts = kls.split('.') 37 | module = ".".join(parts[:-1]) 38 | m = __import__( module ) 39 | for comp in parts[1:]: 40 | m = getattr(m, comp) 41 | return m 42 | 43 | try: 44 | ParserClass = get_parser_class_for(item) 45 | except Exception as e: 46 | logging.error("No parser found for: " + item + "\n\tException is: " + str(e)) 47 | return 1 48 | logging.info("___________________") 49 | logging.info("Parsing " + item + "...") 50 | parser = ParserClass(preferences_map) 51 | try: 52 | parser.start_processing() 53 | except Exception as e: 54 | logging.error("Exception occured while parsing item: " + item + "\n\tException is: " + str(e)) 55 | traceback.print_exc() 56 | logging.info("Parsing finished for item: " + item) 57 | 58 | @staticmethod 59 | def parse_all(preferences_map): 60 | for item in settings.LISTS: 61 | ParsingHelper.parse_one(item, preferences_map) 62 | logging.info("All parsing finished.") 63 | 64 | if __name__ == "__main__": 65 | """ 66 | For debugging purposes 67 | """ 68 | print("Parsing only one file for debugging purposes...") 69 | preferences_map = { 70 | "mode":"TSV", 71 | "inputDir": "../../samples/imdb_lists/", 72 | "outputDir": "../../samples/idp_files/" 73 | } 74 | ParsingHelper.parse_one("movies", preferences_map) 75 | -------------------------------------------------------------------------------- /idp/parser/plotparser.py: -------------------------------------------------------------------------------- 1 | """ 2 | This file is part of imdb-data-parser. 3 | 4 | imdb-data-parser is free software: you can redistribute it and/or modify 5 | it under the terms of the GNU General Public License as published by 6 | the Free Software Foundation, either version 3 of the License, or 7 | (at your option) any later version. 8 | 9 | imdb-data-parser is distributed in the hope that it will be useful, 10 | but WITHOUT ANY WARRANTY; without even the implied warranty of 11 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 12 | GNU General Public License for more details. 13 | 14 | You should have received a copy of the GNU General Public License 15 | along with imdb-data-parser. If not, see . 16 | """ 17 | 18 | from .baseparser import * 19 | 20 | 21 | class PlotParser(BaseParser): 22 | """ 23 | RegExp: /(.+?): (.*)/g 24 | pattern: (.+?): (.*) 25 | flags: g 26 | 2 capturing groups: 27 | group 1: (.+?) type of the line 28 | group 2: (.*) if the line-type is PL then this line is plot, not the whole but one line of it 29 | if the line-type is MV then this line is movie 30 | """ 31 | 32 | # properties 33 | base_matcher_pattern = "(.+?): (.*)" 34 | input_file_name = "plot.list" 35 | number_of_lines_to_be_skipped = 15 36 | db_table_info = { 37 | 'tablename' : 'plot', 38 | 'columns' : [ 39 | {'colname' : 'title', 'colinfo' : DbScriptHelper.keywords['string'] + '(255) NOT NULL'}, 40 | {'colname' : 'plot', 'colinfo' : DbScriptHelper.keywords['string'] + '(4000)'} 41 | ], 42 | 'constraints' : 'PRIMARY KEY(title)' 43 | } 44 | end_of_dump_delimiter = "" 45 | 46 | def __init__(self, preferences_map): 47 | super(PlotParser, self).__init__(preferences_map) 48 | self.first_one = True 49 | 50 | # specific to this class 51 | self.title = "" 52 | self.plot = "" 53 | 54 | def parse_into_tsv(self, matcher): 55 | is_match = matcher.match(self.base_matcher_pattern) 56 | 57 | if(is_match): 58 | if(matcher.group(1) == "MV"): #Title 59 | if(self.title != ""): 60 | self.tsv_file.write(self.title + self.seperator + self.plot + "\n") 61 | 62 | self.plot = "" 63 | self.title = matcher.group(2) 64 | 65 | elif(matcher.group(1) == "PL"): #Descriptive text 66 | self.plot += matcher.group(2) 67 | elif(matcher.group(1) == "BY"): 68 | pass 69 | else: 70 | logging.critical("Unhandled abbreviation: " + matcher.group(1) + " in " + line) 71 | #else: 72 | #just ignore this part, useless lines 73 | 74 | """ 75 | FIXME: this parsing misses the last entry 76 | need to execute following just after looping the input file's lines: 77 | # Covers the last item 78 | outputFile.write(title + self.seperator + plot + "\n") 79 | 80 | consider writing to the file in "BY:" condition 81 | """ 82 | 83 | def parse_into_db(self, matcher): 84 | is_match = matcher.match(self.base_matcher_pattern) 85 | 86 | if(is_match): 87 | if(matcher.group(1) == "MV"): #Title 88 | if(self.title != ""): 89 | if(self.first_one): 90 | self.sql_file.write("(\"" + self.title + "\", \"" + self.plot + "\")") 91 | self.first_one = False; 92 | else: 93 | self.sql_file.write(",\n(\"" + self.title + "\", \"" + self.plot + "\")") 94 | 95 | self.plot = "" 96 | self.title = matcher.group(2) 97 | 98 | elif(matcher.group(1) == "PL"): #Descriptive text 99 | self.plot += matcher.group(2) 100 | elif(matcher.group(1) == "BY"): 101 | pass 102 | else: 103 | logging.critical("Unhandled abbreviation: " + matcher.group(1) + " in " + line) 104 | -------------------------------------------------------------------------------- /idp/parser/ratingsparser.py: -------------------------------------------------------------------------------- 1 | """ 2 | This file is part of imdb-data-parser. 3 | 4 | imdb-data-parser is free software: you can redistribute it and/or modify 5 | it under the terms of the GNU General Public License as published by 6 | the Free Software Foundation, either version 3 of the License, or 7 | (at your option) any later version. 8 | 9 | imdb-data-parser is distributed in the hope that it will be useful, 10 | but WITHOUT ANY WARRANTY; without even the implied warranty of 11 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 12 | GNU General Public License for more details. 13 | 14 | You should have received a copy of the GNU General Public License 15 | along with imdb-data-parser. If not, see . 16 | """ 17 | 18 | from .baseparser import * 19 | 20 | 21 | class RatingsParser(BaseParser): 22 | """ 23 | RegExp: /\s*(\S*)\s*(\S*)\s*(\S*)\s*((.*? \(\S{4,}\)) ?(\(\S+\))? ?(?!\{\{SUSPENDED\}\})(\{(.*?) ?(\(\S+?\))?\})? ?(\{\{SUSPENDED\}\})?)$/gm 24 | pattern: \s*(\S*)\s*(\S*)\s*(\S*)\s*((.*? \(\S{4,}\)) ?(\(\S+\))? ?(?!\{\{SUSPENDED\}\})(\{(.*?) ?(\(\S+?\))?\})? ?(\{\{SUSPENDED\}\})?)$ 25 | flags: gm 26 | 10 capturing groups: 27 | group 1: (\S*) distribution 28 | group 2: (\S*) votes 29 | group 3: (\S*) rank 30 | group 4: #TITLE (UNIQUE KEY) 31 | group 5: (.*? \(\S{4,}\)) movie name + year 32 | group 6: (\(.+\)) type ex:(TV) 33 | group 7: (\{(.*?)\s?(\(.+?\))\}) series info ex: {Ally Abroad (#3.1)} 34 | group 8: (.*?) episode name ex: Ally Abroad 35 | group 9: (\(.+?\)) episode number ex: (#3.1) 36 | group 10: (\{\{SUSPENDED\}\}) is suspended? 37 | """ 38 | 39 | # properties 40 | base_matcher_pattern = "\s*(\S*)\s*(\S*)\s*(\S*)\s*((.*? \(\S{4,}\)) ?(\(\S+\))? ?(?!\{\{SUSPENDED\}\})(\{(.*?) ?(\(\S+?\))?\})? ?(\{\{SUSPENDED\}\})?)$" 41 | input_file_name = "ratings.list" 42 | number_of_lines_to_be_skipped = 28 43 | db_table_info = { 44 | 'tablename' : 'ratings', 45 | 'columns' : [ 46 | {'colname' : 'distribution', 'colinfo' : DbScriptHelper.keywords['string'] + '(127) NOT NULL'}, 47 | {'colname' : 'votes', 'colinfo' : DbScriptHelper.keywords['string'] + '(127)'}, 48 | {'colname' : 'rank', 'colinfo' : DbScriptHelper.keywords['string'] + '(127)'}, 49 | {'colname' : 'title', 'colinfo' : DbScriptHelper.keywords['string'] + '(255) NOT NULL'} 50 | ], 51 | 'constraints' : 'PRIMARY KEY(title)' 52 | } 53 | end_of_dump_delimiter = "" 54 | 55 | def __init__(self, preferences_map): 56 | super(RatingsParser, self).__init__(preferences_map) 57 | self.first_one = True 58 | 59 | def parse_into_tsv(self, matcher): 60 | is_match = matcher.match(self.base_matcher_pattern) 61 | 62 | if(is_match): 63 | self.tsv_file.write(self.concat_regex_groups([1,2,3,4], None, matcher) + "\n") 64 | else: 65 | logging.critical("This line is fucked up: " + matcher.get_last_string()) 66 | self.fucked_up_count += 1 67 | 68 | def parse_into_db(self, matcher): 69 | is_match = matcher.match(self.base_matcher_pattern) 70 | 71 | if(is_match): 72 | if(self.first_one): 73 | self.sql_file.write("(" + self.concat_regex_groups([1,2,3,4], [0,1,2,3], matcher) + ")") 74 | self.first_one = False; 75 | else: 76 | self.sql_file.write(",\n(" + self.concat_regex_groups([1,2,3,4], [0,1,2,3], matcher) + ")") 77 | else: 78 | logging.critical("This line is fucked up: " + matcher.get_last_string()) 79 | self.fucked_up_count += 1 80 | -------------------------------------------------------------------------------- /idp/parser/triviaparser.py: -------------------------------------------------------------------------------- 1 | """ 2 | This file is part of imdb-data-parser. 3 | 4 | imdb-data-parser is free software: you can redistribute it and/or modify 5 | it under the terms of the GNU General Public License as published by 6 | the Free Software Foundation, either version 3 of the License, or 7 | (at your option) any later version. 8 | 9 | imdb-data-parser is distributed in the hope that it will be useful, 10 | but WITHOUT ANY WARRANTY; without even the implied warranty of 11 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 12 | GNU General Public License for more details. 13 | 14 | You should have received a copy of the GNU General Public License 15 | along with imdb-data-parser. If not, see . 16 | """ 17 | 18 | from .baseparser import * 19 | 20 | 21 | class TriviaParser(BaseParser): 22 | """ 23 | RegExp: /((.+?) (.*))|\n/g 24 | pattern: ((.+?) (.*))|\n 25 | flags: g 26 | 2 capturing groups: 27 | group 1: (.+?) type of the line 28 | group 2: (.*) if the line-type is - then this line is plot, not the whole but one line of it 29 | if the line-type is # then this line is movie 30 | """ 31 | 32 | # properties 33 | base_matcher_pattern = "((.+?) (.*))|\n" 34 | input_file_name = "trivia.list" 35 | number_of_lines_to_be_skipped = 15 36 | db_table_info = { 37 | 'tablename' : 'trivia', 38 | 'columns' : [ 39 | { 40 | 'colname' : '', 41 | 'colinfo' : DbScriptHelper.keywords['string'] + '(255) NOT NULL' 42 | } 43 | ], 44 | 'constraints' : '' 45 | } 46 | end_of_dump_delimiter = "" 47 | 48 | title = "" 49 | trivia = "" 50 | 51 | def __init__(self, preferences_map): 52 | super(TriviaParser, self).__init__(preferences_map) 53 | self.first_one = True 54 | 55 | def parse_into_tsv(self, matcher): 56 | is_match = matcher.match(self.base_matcher_pattern) 57 | 58 | if(is_match): 59 | if(matcher.group(2) == "#"): #Title 60 | self.title = matcher.group(3) 61 | elif(matcher.group(2) == "-"): #Descriptive text 62 | self.trivia = matcher.group(3) 63 | elif(matcher.group(2) == " "): 64 | self.trivia += ' ' + matcher.group(3) 65 | else: 66 | self.tsv_file.write(self.title + self.seperator + self.trivia + "\n") 67 | else: 68 | logging.critical("This line is fucked up: " + matcher.get_last_string()) 69 | self.fucked_up_count += 1 70 | 71 | def parse_into_db(self, matcher): 72 | #TODO 73 | pass 74 | -------------------------------------------------------------------------------- /idp/settings.py.example: -------------------------------------------------------------------------------- 1 | """ 2 | This file is part of imdb-data-parser. 3 | 4 | imdb-data-parser is free software: you can redistribute it and/or modify 5 | it under the terms of the GNU General Public License as published by 6 | the Free Software Foundation, either version 3 of the License, or 7 | (at your option) any later version. 8 | 9 | imdb-data-parser is distributed in the hope that it will be useful, 10 | but WITHOUT ANY WARRANTY; without even the implied warranty of 11 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 12 | GNU General Public License for more details. 13 | 14 | You should have received a copy of the GNU General Public License 15 | along with imdb-data-parser. If not, see . 16 | """ 17 | 18 | INPUT_DIR = "/path/to/lists/files/" 19 | OUTPUT_DIR = "/path/to/tsv/outputs/" 20 | 21 | INTERFACES_SERVER = "ftp.fu-berlin.de" 22 | INTERFACES_DIRECTORY = "pub/misc/movies/database/" 23 | #alternative servers: 24 | #ftp://ftp.funet.fi/pub/mirrors/ftp.imdb.com/pub/ 25 | #ftp://ftp.sunet.se/pub/tv+movies/imdb/ 26 | 27 | LISTS = [ 28 | "directors", 29 | "genres", 30 | "movies", 31 | "plot", 32 | "actors", 33 | "actresses", 34 | "aka-names", 35 | "aka-titles", 36 | "ratings" 37 | ] 38 | -------------------------------------------------------------------------------- /idp/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dedeler/imdb-data-parser/20671ab98e2065bbe0a32aef0402776934a2863b/idp/utils/__init__.py -------------------------------------------------------------------------------- /idp/utils/dbscripthelper.py: -------------------------------------------------------------------------------- 1 | """ 2 | This file is part of imdb-data-parser. 3 | 4 | imdb-data-parser is free software: you can redistribute it and/or modify 5 | it under the terms of the GNU General Public License as published by 6 | the Free Software Foundation, either version 3 of the License, or 7 | (at your option) any later version. 8 | 9 | imdb-data-parser is distributed in the hope that it will be useful, 10 | but WITHOUT ANY WARRANTY; without even the implied warranty of 11 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 12 | GNU General Public License for more details. 13 | 14 | You should have received a copy of the GNU General Public License 15 | along with imdb-data-parser. If not, see . 16 | """ 17 | 18 | import os 19 | 20 | 21 | class DbScriptHelper(object): 22 | keywords = { 23 | 'string': "VARCHAR", 24 | 'number': "NUMERIC", 25 | 'date': "DATE" 26 | } 27 | 28 | scripts = { 29 | 'drop': "DROP TABLE ", 30 | 'create': "CREATE TABLE ", 31 | 'insert': "INSERT INTO " 32 | } 33 | 34 | def __init__(self, db_table_info): 35 | self.scripts = { 36 | 'drop': "DROP TABLE ", 37 | 'create': "CREATE TABLE ", 38 | 'insert': "INSERT INTO " 39 | } 40 | self.scripts['drop'] += db_table_info['tablename'] + ";" + os.linesep 41 | self.scripts['create'] += db_table_info['tablename'] + "(" + ', '.join(filter(None, (', '.join('%s %s' % (col['colname'], col['colinfo']) for col in db_table_info['columns']), db_table_info['constraints']))) + ") CHARACTER SET utf8 COLLATE utf8_bin;" + os.linesep 42 | self.scripts['insert'] += db_table_info['tablename'] + "(" + ', '.join(col['colname'] for col in db_table_info['columns']) + ") VALUES" + os.linesep -------------------------------------------------------------------------------- /idp/utils/decorators.py: -------------------------------------------------------------------------------- 1 | """ 2 | This file is part of imdb-data-parser. 3 | 4 | imdb-data-parser is free software: you can redistribute it and/or modify 5 | it under the terms of the GNU General Public License as published by 6 | the Free Software Foundation, either version 3 of the License, or 7 | (at your option) any later version. 8 | 9 | imdb-data-parser is distributed in the hope that it will be useful, 10 | but WITHOUT ANY WARRANTY; without even the implied warranty of 11 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 12 | GNU General Public License for more details. 13 | 14 | You should have received a copy of the GNU General Public License 15 | along with imdb-data-parser. If not, see . 16 | """ 17 | 18 | import datetime 19 | import logging 20 | 21 | 22 | def duration_logged(func): 23 | ''' 24 | As the name suggests, calculates the execution duration of the function which is annotated by this decorator 25 | ''' 26 | def inner(*args, **kwargs): 27 | start_time = datetime.datetime.now() 28 | ret_val = func(*args, **kwargs) 29 | end_time = datetime.datetime.now() 30 | duration = (end_time - start_time).total_seconds() #difference of 2 datetime is a timedelta 31 | logging.info("Parsing took " + str(duration) + " seconds") 32 | return ret_val 33 | return inner -------------------------------------------------------------------------------- /idp/utils/filehandler.py: -------------------------------------------------------------------------------- 1 | """ 2 | This file is part of imdb-data-parser. 3 | 4 | imdb-data-parser is free software: you can redistribute it and/or modify 5 | it under the terms of the GNU General Public License as published by 6 | the Free Software Foundation, either version 3 of the License, or 7 | (at your option) any later version. 8 | 9 | imdb-data-parser is distributed in the hope that it will be useful, 10 | but WITHOUT ANY WARRANTY; without even the implied warranty of 11 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 12 | GNU General Public License for more details. 13 | 14 | You should have received a copy of the GNU General Public License 15 | along with imdb-data-parser. If not, see . 16 | """ 17 | 18 | import gzip 19 | import os.path 20 | import logging 21 | from ..settings import * 22 | 23 | 24 | class FileHandler(object): 25 | def __init__(self, list_name, preferences_map): 26 | self.list_name = list_name 27 | self.preferences_map = preferences_map 28 | 29 | def full_path(self): 30 | return os.path.join(self.preferences_map['input_dir'], self.list_name) 31 | 32 | def tsv_path(self): 33 | return os.path.join(self.preferences_map['output_dir'], self.list_name) + ".tsv" 34 | 35 | def sql_path(self): 36 | return os.path.join(self.preferences_map['output_dir'], self.list_name) + ".sql" 37 | 38 | def get_input_file(self): 39 | full_file_path = self.full_path() 40 | logging.info("Trying to find file: %s", full_file_path) 41 | if os.path.isfile(full_file_path): 42 | logging.info("File found: %s", full_file_path) 43 | return open(full_file_path, "r", encoding='iso-8859-1') 44 | 45 | logging.error("File cannot be found: %s", full_file_path) 46 | 47 | logging.info("Trying to find file: %s", full_file_path + ".gz") 48 | if os.path.isfile(full_file_path + ".gz"): 49 | logging.info("File found: %s", full_file_path + ".gz") 50 | if extract(full_file_path + ".gz") == 0: 51 | return open(full_file_path, "r", encoding='iso-8859-1') 52 | else: 53 | raise RuntimeError("Unknown error occured") 54 | 55 | logging.error("File cannot be found: %s", full_file_path + ".gz") 56 | 57 | raise RuntimeError("FileNotFoundError: %s", full_file_path) 58 | 59 | #this part removed until python 3.3 becomes available for ubuntu LTS and debian 60 | # 61 | # print("Trying to find file:", full_file_path) 62 | # if os.path.isfile(full_file_path): 63 | # print("File found:", full_file_path) 64 | # return gzip.open(full_file_path, 'rt') 65 | # print("File cannot be found:", full_file_path) 66 | 67 | def get_tsv_file(self): 68 | return open(self.tsv_path(), "w", encoding='utf-8') 69 | 70 | def get_sql_file(self): 71 | return open(self.sql_path(), "w", encoding='utf-8') 72 | 73 | def extract(gzip_path): 74 | try: 75 | logging.info("Started to extract list: %s", gzip_path) 76 | with gzip.open(gzip_path, "rb") as f: 77 | file_content = f.read() 78 | list_file = open(gzip_path[:-3], "wb") 79 | list_file.write(file_content) 80 | list_file.close() 81 | logging.info(gzip_path + " list extracted successfully") 82 | except Exception as e: 83 | logging.error("Error when extracting list: " + gzip_path + "\n\t" + str(e)) 84 | return 1 85 | return 0 86 | 87 | def get_full_path(filename, isCompressed = False): 88 | """ 89 | constructs a full path for a dump file in the INPUT_DIR 90 | filename should be without '.list' 91 | """ 92 | if(isCompressed): 93 | return os.path.join(INPUT_DIR, filename) + ".gz" 94 | else: 95 | return os.path.join(INPUT_DIR, filename) -------------------------------------------------------------------------------- /idp/utils/freebaseagent.py: -------------------------------------------------------------------------------- 1 | """ 2 | This file is part of imdb-data-parser. 3 | 4 | imdb-data-parser is free software: you can redistribute it and/or modify 5 | it under the terms of the GNU General Public License as published by 6 | the Free Software Foundation, either version 3 of the License, or 7 | (at your option) any later version. 8 | 9 | imdb-data-parser is distributed in the hope that it will be useful, 10 | but WITHOUT ANY WARRANTY; without even the implied warranty of 11 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 12 | GNU General Public License for more details. 13 | 14 | You should have received a copy of the GNU General Public License 15 | along with imdb-data-parser. If not, see . 16 | """ 17 | 18 | import json 19 | import urllib 20 | 21 | 22 | class FreebaseAgent(object): 23 | """Helper class to retrieve IMDb ids from freebase. 24 | 25 | Currently only supports movies. TV series support will 26 | hopefully be added if need arises. 27 | """ 28 | 29 | def __init__(self): 30 | super(FreebaseAgent, self).__init__() 31 | self.API_KEY = 'YOUR-API-KEY-GOES-HERE' #TODO read these values from config 32 | self.topic_service_url = 'https://www.googleapis.com/freebase/v1/topic' 33 | self.search_service_url = 'https://www.googleapis.com/freebase/v1/search' 34 | 35 | def get_imdb_id(self, movie_name): 36 | """Returns the IMDb id of a movie, given its title. 37 | 38 | The returned title is the one with the highest 39 | freebase confidence score. 40 | 41 | Returns None if no such movie exists in freebase. 42 | """ 43 | mid = self.get_topic_id(movie_name) 44 | topic = self.get_topic(mid) 45 | return topic 46 | 47 | def get_topic_id(self, name, entity_type='/film/film'): 48 | """Gets the topic id (aka mid, freebase id) of a title. 49 | """ 50 | params = { 51 | 'query': name, 52 | 'type': entity_type, 53 | 'limit': 1 54 | } 55 | url = self.search_service_url + '?' + urllib.urlencode(params) 56 | response = json.loads(urllib.urlopen(url).read()) 57 | 58 | for result in response.get('result'): 59 | mid = result.get('mid', None) 60 | return mid 61 | return None 62 | 63 | def get_topic(self, mid): 64 | """Gets the IMDb id of a freebase topic. Returns None if no 65 | such thing exists. 66 | """ 67 | params = { 68 | 'filter': '/type/object/key' 69 | } 70 | url = self.topic_service_url + mid + '?' + urllib.urlencode(params) 71 | topic = json.loads(urllib.urlopen(url).read()) 72 | 73 | for property in topic['property']: 74 | for value in topic['property'][property]['values']: 75 | if value['text'].startswith('/authority/imdb/title'): 76 | return value['text'].split('/')[-1] 77 | 78 | 79 | if __name__ == "__main__": 80 | import argparse 81 | 82 | parser = argparse.ArgumentParser(description="Retrieve imdb id from freebase.") 83 | parser.add_argument('movieName', help='The name of the movie') 84 | args = parser.parse_args() 85 | 86 | agent = FreebaseAgent() 87 | mid = agent.getTopicId(args.movieName) 88 | print 'freebase topic id (mid) is', mid 89 | topic = agent.getTopic(mid) 90 | print 'imdb id is', topic, 'so the url is http://www.imdb.com/title/'+topic 91 | print agent.getImdbId(args.movieName) -------------------------------------------------------------------------------- /idp/utils/listdownloader.py: -------------------------------------------------------------------------------- 1 | """ 2 | This file is part of imdb-data-parser. 3 | 4 | imdb-data-parser is free software: you can redistribute it and/or modify 5 | it under the terms of the GNU General Public License as published by 6 | the Free Software Foundation, either version 3 of the License, or 7 | (at your option) any later version. 8 | 9 | imdb-data-parser is distributed in the hope that it will be useful, 10 | but WITHOUT ANY WARRANTY; without even the implied warranty of 11 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 12 | GNU General Public License for more details. 13 | 14 | You should have received a copy of the GNU General Public License 15 | along with imdb-data-parser. If not, see . 16 | """ 17 | 18 | import gzip 19 | import logging 20 | import os 21 | from ftplib import FTP 22 | from .filehandler import FileHandler 23 | from ..settings import * 24 | 25 | 26 | def download(): 27 | logging.info("Lists will downloaded from server:" + INTERFACES_SERVER) 28 | 29 | ftp = FTP(INTERFACES_SERVER) 30 | ftp.login() 31 | 32 | download_count = 0 33 | 34 | for list_item in LISTS: 35 | try: 36 | logging.info("Started to download list:" + list_item) 37 | r = ftp.retrbinary("RETR " + INTERFACES_DIRECTORY + list_item + ".list.gz", open(os.path.join(INPUT_DIR, list_item + ".list.gz"), "wb").write) 38 | logging.info(list_item + "list downloaded successfully") 39 | download_count = download_count + 1 40 | FileHandler.extract(FileHandler.get_full_path(list_item + ".list", True)) 41 | except Exception as e: 42 | logging.error("There is a problem when downloading list " + list_item + "\n\t" + str(e)) 43 | 44 | logging.info(str(download_count) + " lists are downloaded") 45 | ftp.quit() 46 | -------------------------------------------------------------------------------- /idp/utils/loggerinitializer.py: -------------------------------------------------------------------------------- 1 | """ 2 | This file is part of imdb-data-parser. 3 | 4 | imdb-data-parser is free software: you can redistribute it and/or modify 5 | it under the terms of the GNU General Public License as published by 6 | the Free Software Foundation, either version 3 of the License, or 7 | (at your option) any later version. 8 | 9 | imdb-data-parser is distributed in the hope that it will be useful, 10 | but WITHOUT ANY WARRANTY; without even the implied warranty of 11 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 12 | GNU General Public License for more details. 13 | 14 | You should have received a copy of the GNU General Public License 15 | along with imdb-data-parser. If not, see . 16 | """ 17 | 18 | import logging 19 | import os.path 20 | 21 | 22 | def initialize_logger(preferences_map): 23 | logger = logging.getLogger() 24 | logger.setLevel(logging.INFO) 25 | 26 | # create console handler and set level to info 27 | ch = logging.StreamHandler() 28 | ch.setLevel(logging.INFO) 29 | formatter = logging.Formatter("%(levelname)s - %(message)s") 30 | ch.setFormatter(formatter) 31 | logger.addHandler(ch) 32 | 33 | # create error file handler and set level to error 34 | ch = logging.FileHandler(os.path.join(preferences_map['output_dir'], "imdbparserError.log"),"w", encoding=None, delay="true") 35 | ch.setLevel(logging.ERROR) 36 | formatter = logging.Formatter("%(levelname)s - %(message)s") 37 | ch.setFormatter(formatter) 38 | logger.addHandler(ch) 39 | 40 | # create info file handler and set level to info 41 | ch = logging.FileHandler(os.path.join(preferences_map['output_dir'], "imdbparserAll.log"),"w") 42 | ch.setLevel(logging.INFO) 43 | formatter = logging.Formatter("%(levelname)s - %(message)s") 44 | ch.setFormatter(formatter) 45 | logger.addHandler(ch) -------------------------------------------------------------------------------- /idp/utils/regexhelper.py: -------------------------------------------------------------------------------- 1 | """ 2 | This file is part of imdb-data-parser. 3 | 4 | imdb-data-parser is free software: you can redistribute it and/or modify 5 | it under the terms of the GNU General Public License as published by 6 | the Free Software Foundation, either version 3 of the License, or 7 | (at your option) any later version. 8 | 9 | imdb-data-parser is distributed in the hope that it will be useful, 10 | but WITHOUT ANY WARRANTY; without even the implied warranty of 11 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 12 | GNU General Public License for more details. 13 | 14 | You should have received a copy of the GNU General Public License 15 | along with imdb-data-parser. If not, see . 16 | """ 17 | 18 | import re 19 | 20 | 21 | class RegExHelper(object): 22 | def __init__(self, matchstring): 23 | self.matchstring = matchstring 24 | 25 | def match(self,regexp): 26 | self.rematch = re.match(regexp, self.matchstring) 27 | return bool(self.rematch) 28 | 29 | def group(self,i): 30 | if self.rematch.group(i) is None: 31 | return "" 32 | else: 33 | return self.rematch.group(i) 34 | 35 | def get_last_string(self): 36 | """ 37 | returns the last string that is examined 38 | """ 39 | return self.matchstring -------------------------------------------------------------------------------- /idp/utils/test/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dedeler/imdb-data-parser/20671ab98e2065bbe0a32aef0402776934a2863b/idp/utils/test/__init__.py -------------------------------------------------------------------------------- /idp/utils/test/filehandler_test.py: -------------------------------------------------------------------------------- 1 | import unittest 2 | from ..filehandler import * 3 | from ... import settings 4 | 5 | class FileHandlerTests(unittest.TestCase): 6 | def setUp(self): 7 | self.list = 'movies' 8 | 9 | def test_get_full_path(self): 10 | self.assertEqual(get_full_path(self.list), settings.INPUT_DIR+self.list) 11 | 12 | 13 | if __name__ == '__main__': 14 | unittest.main() 15 | -------------------------------------------------------------------------------- /imdb_parse_path.txt: -------------------------------------------------------------------------------- 1 | /* 2 | This file is part of imdb-data-parser. 3 | 4 | imdb-data-parser is free software: you can redistribute it and/or modify 5 | it under the terms of the GNU General Public License as published by 6 | the Free Software Foundation, either version 3 of the License, or 7 | (at your option) any later version. 8 | 9 | imdb-data-parser is distributed in the hope that it will be useful, 10 | but WITHOUT ANY WARRANTY; without even the implied warranty of 11 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 12 | GNU General Public License for more details. 13 | 14 | You should have received a copy of the GNU General Public License 15 | along with imdb-data-parser. If not, see . 16 | */ 17 | 18 | 19 | 20 | /******************************************************************************** 21 | * * 22 | * -> optional * 23 | * #TITLE = name (year) }/> * 24 | * * 25 | ********************************************************************************/ 26 | 27 | movies -> #TITLE Year 28 | 29 | ratings -> Dist.Num Votes Rank #TITLE 30 | 31 | genres -> #TITLE Genre 32 | 33 | language -> #TITLE Language 34 | 35 | run-time -> #TITLE time 36 | 37 | aka-title -> #TITLE 38 | (aka #TITLE) 39 | ..................... 40 | .....................\n\n 41 | 42 | countries -> #TITLE Country 43 | 44 | taglines -> # #TITLE 45 | TagLine 46 | ....... 47 | .......\n\n 48 | 49 | plot -> -------------------------- 50 | MV: #TITLE 51 | 52 | PL: PlotLine1 53 | PL: PlotLine2 54 | PL: ......... 55 | 56 | BY: By\n\n 57 | 58 | trivia -> # #TITLE 59 | - trivia1 60 | ........... 61 | ........... 62 | 63 | - trivia2 64 | ........... 65 | ...........\n\n 66 | 67 | directors -> Lastname, Firstname #TITLE 68 | #TITLE \n\n 69 | 70 | actors -> Lastname, Firstname #TITLE /> 71 | #TITLE /> 72 | 73 | actress -> Lastname, Firstname #TITLE /> 74 | #TITLE /> 75 | -------------------------------------------------------------------------------- /imdbparser.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python3 2 | 3 | """ 4 | This file is part of imdb-data-parser. 5 | 6 | imdb-data-parser is free software: you can redistribute it and/or modify 7 | it under the terms of the GNU General Public License as published by 8 | the Free Software Foundation, either version 3 of the License, or 9 | (at your option) any later version. 10 | 11 | imdb-data-parser is distributed in the hope that it will be useful, 12 | but WITHOUT ANY WARRANTY; without even the implied warranty of 13 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 14 | GNU General Public License for more details. 15 | 16 | You should have received a copy of the GNU General Public License 17 | along with imdb-data-parser. If not, see . 18 | """ 19 | 20 | """ 21 | Dealing with ": No such file or directory" error: 22 | http://stackoverflow.com/a/8735625/878361 23 | """ 24 | 25 | import sys 26 | import argparse 27 | import datetime 28 | from idp.utils.loggerinitializer import * 29 | from idp.parser.parsinghelper import ParsingHelper 30 | from idp.settings import * 31 | 32 | 33 | # check python version 34 | if sys.version_info.major != 3: 35 | sys.exit("Error: wrong version! You need to install python3 to run this application properly.") 36 | 37 | parser = argparse.ArgumentParser(description="an IMDB data parser") 38 | parser.add_argument('-m', '--mode', help='Parsing mode, defines output of parsing process. Default: TSV', choices=['TSV', 'SQL']) 39 | parser.add_argument('-i', '--input_dir', help='source directory of interface lists') 40 | parser.add_argument('-o', '--output_dir', help='destination directory for outputs') 41 | parser.add_argument('-u', '--update_lists', action='store_true', help='downloads lists from server') 42 | 43 | args = parser.parse_args() 44 | 45 | # preparing preferences map 46 | if args.mode: 47 | mode = args.mode 48 | else: #default 49 | mode = "TSV" 50 | 51 | if args.input_dir: 52 | input_dir = args.input_dir 53 | else: 54 | input_dir = INPUT_DIR 55 | 56 | postfix = datetime.datetime.now().strftime("%Y-%m-%d_%H%M%S") + '_ImdbParserOutput' 57 | if args.input_dir: 58 | output_dir = os.path.join(args.output_dir, postfix) 59 | else: 60 | output_dir = os.path.join(OUTPUT_DIR, postfix) 61 | 62 | if not os.path.exists(output_dir): 63 | os.makedirs(output_dir) 64 | 65 | preferences_map = { 66 | "mode":mode, 67 | "input_dir": input_dir, 68 | "output_dir": output_dir 69 | } 70 | 71 | initialize_logger(preferences_map) 72 | 73 | logging.info("mode:%s", mode) 74 | logging.info("input_dir:%s", input_dir) 75 | logging.info("output_dir:%s", output_dir) 76 | logging.info("update_lists:%s", args.update_lists) 77 | 78 | if args.update_lists: 79 | from idp.utils import listdownloader 80 | logging.info("Downloading IMDB dumps, this may take a while depending on your connection speed") 81 | listdownloader.download() 82 | 83 | logging.info("Parsing, please wait. This may take very long time...") 84 | 85 | ParsingHelper.parse_all(preferences_map) 86 | 87 | logging.info("Check out output folder: %s", output_dir) 88 | print ("All done, enjoy ;)") #don't print this via logger, this is part of the program 89 | -------------------------------------------------------------------------------- /samples/movies.list: -------------------------------------------------------------------------------- 1 | dummy 2 | dummy 3 | dummy 4 | dummy 5 | dummy 6 | dummy 7 | dummy 8 | dummy 9 | dummy 10 | dummy 11 | dummy 12 | dummy 13 | dummy 14 | dummy 15 | dummy 16 | "$9.99" (2003) {Winter Wonderland (#3.1)} 2005 17 | "$weepstake$" (1979) 1979-???? 18 | "$weepstake$" (1979) {(#1.1)} 1979 19 | "' Horse Trials '" (2011) 2011-???? 20 | "'80s Videos: A to Z" (2009) 2009-???? 21 | "'Allo 'Allo!" (1982) 1982-1992 22 | "'Allo 'Allo!" (1982) {A Bun in the Oven (#8.0)} 1991 23 | "'Til Death" (2006) {(#3.22)} {{SUSPENDED}} ???? 24 | "'Til Death" (2006) {Ally Abroad (#4.22)} 2010 25 | Anno 2006 (2007) (TV) 2007 26 | Anno 2008 - 15 let TV Nova (2009) (TV) 2009 27 | Anno 2009 (2010) (TV) 2010 28 | Anno 2020 - I gladiatori del futuro (1984) 1984 29 | Anno 2033 (1973) 1973 30 | Anno 2070 (2011) (VG) 2011 31 | Anno 79: La distruzione di Ercolano (1962) 1962 32 | Anno domini (1991) 1991 33 | Anniversary (1992) (V) 1992 34 | Anniversary (2002) {{SUSPENDED}} 2002 35 | Apocalypse (2011) (V) {{SUSPENDED}} 2011 36 | "'Allo 'Allo!" (1982) {A Bun in the Oven (#8.0)} {{SUSPENDED}} 1991 -------------------------------------------------------------------------------- /samples/movies.list.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dedeler/imdb-data-parser/20671ab98e2065bbe0a32aef0402776934a2863b/samples/movies.list.gz --------------------------------------------------------------------------------