Commit | Line | Data |
---|---|---|
975060c9 OM |
1 | #!/usr/bin/env python3 |
2 | """ | |
3 | Thingiverse bulk downloader | |
4 | """ | |
5 | ||
6 | import re | |
4a98996b | 7 | import sys |
975060c9 OM |
8 | import os |
9 | import argparse | |
10 | import unicodedata | |
11 | import requests | |
fa2f3251 | 12 | import logging |
6a777954 | 13 | import multiprocessing |
7b84ba6d | 14 | import enum |
fb28c59b | 15 | import datetime |
3c82f75b | 16 | from shutil import copyfile |
975060c9 | 17 | from bs4 import BeautifulSoup |
b497d705 OM |
18 | from dataclasses import dataclass |
19 | import selenium | |
20 | from selenium import webdriver | |
21 | from selenium.webdriver.common.by import By | |
22 | from selenium.webdriver.support.ui import WebDriverWait | |
23 | from selenium.webdriver.support import expected_conditions as EC | |
24 | from selenium.webdriver.firefox.options import Options | |
d194b140 | 25 | import atexit |
9828dabe | 26 | import py7zr |
975060c9 | 27 | |
ae598d73 OM |
28 | SEVENZIP_FILTERS = [{'id': py7zr.FILTER_LZMA2}] |
29 | ||
975060c9 OM |
30 | URL_BASE = "https://www.thingiverse.com" |
31 | URL_COLLECTION = URL_BASE + "/ajax/thingcollection/list_collected_things" | |
948bd56f | 32 | USER_COLLECTION = URL_BASE + "/ajax/user/designs" |
975060c9 OM |
33 | |
34 | ID_REGEX = re.compile(r'"id":(\d*),') | |
35 | TOTAL_REGEX = re.compile(r'"total":(\d*),') | |
36 | LAST_PAGE_REGEX = re.compile(r'"last_page":(\d*),') | |
37 | # This appears to be fixed at 12, but if it changes would screw the rest up. | |
38 | PER_PAGE_REGEX = re.compile(r'"per_page":(\d*),') | |
dd8c35f4 OM |
39 | NO_WHITESPACE_REGEX = re.compile(r'[-\s]+') |
40 | ||
6a777954 | 41 | DOWNLOADER_COUNT = 1 |
7b84ba6d | 42 | RETRY_COUNT = 3 |
6a777954 | 43 | |
65bd8b43 OM |
44 | MAX_PATH_LENGTH = 250 |
45 | ||
ae598d73 | 46 | VERSION = "0.9.0" |
dbdb1782 | 47 | |
b497d705 OM |
48 | |
49 | #BROWSER = webdriver.PhantomJS('./phantomjs') | |
50 | options = Options() | |
fb28c59b | 51 | options.add_argument("--headless") |
b497d705 OM |
52 | BROWSER = webdriver.Firefox(options=options) |
53 | ||
54 | BROWSER.set_window_size(1980, 1080) | |
55 | ||
56 | ||
57 | @dataclass | |
58 | class FileLink: | |
59 | name: str | |
ae598d73 OM |
60 | last_update: datetime.datetime |
61 | link: str | |
62 | ||
63 | class FileLinks: | |
64 | def __init__(self, initial_links=[]): | |
65 | self.links = [] | |
66 | self.last_update = None | |
67 | for link in initial_links: | |
68 | self.append(link) | |
69 | ||
70 | def __iter__(self): | |
71 | return iter(self.links) | |
72 | ||
73 | def __getitem__(self, item): | |
74 | return self.links[item] | |
75 | ||
76 | def __len__(self): | |
77 | return len(self.links) | |
78 | ||
79 | def append(self, link): | |
80 | try: | |
81 | self.last_update = max(self.last_update, link.last_update) | |
82 | except TypeError: | |
83 | self.last_update = link.last_update | |
84 | self.links.append(link) | |
b497d705 OM |
85 | |
86 | ||
7b84ba6d OM |
87 | class State(enum.Enum): |
88 | OK = enum.auto() | |
89 | FAILED = enum.auto() | |
90 | ALREADY_DOWNLOADED = enum.auto() | |
91 | ||
dbdb1782 | 92 | |
65bd8b43 OM |
93 | def fail_dir(dir_name): |
94 | """ When a download has failed, move it sideways. | |
95 | """ | |
96 | target_dir = "{}_failed".format(dir_name) | |
97 | inc = 0 | |
98 | while os.path.exists(target_dir): | |
99 | target_dir = "{}_failed_{}".format(dir_name, inc) | |
100 | inc += 1 | |
101 | os.rename(dir_name, target_dir) | |
102 | ||
103 | ||
104 | def truncate_name(file_name): | |
105 | """ Ensure the filename is not too long for, well windows basically. | |
106 | """ | |
107 | path = os.path.abspath(file_name) | |
108 | if len(path) <= MAX_PATH_LENGTH: | |
109 | return path | |
110 | to_cut = len(path) - (MAX_PATH_LENGTH + 3) | |
111 | base, extension = os.path.splitext(path) | |
112 | inc = 0 | |
113 | new_path = "{}_{}{}".format(base, inc, extension) | |
114 | while os.path.exists(new_path): | |
115 | new_path = "{}_{}{}".format(base, inc, extension) | |
116 | inc += 1 | |
117 | return new_path | |
118 | ||
119 | ||
dd8c35f4 OM |
120 | def strip_ws(value): |
121 | """ Remove whitespace from a string """ | |
122 | return str(NO_WHITESPACE_REGEX.sub('-', value)) | |
975060c9 | 123 | |
dbdb1782 | 124 | |
975060c9 OM |
125 | def slugify(value): |
126 | """ | |
d194b140 OM |
127 | Normalise string, removes invalid for filename charactersr |
128 | and converts string to lowercase. | |
975060c9 | 129 | """ |
d194b140 | 130 | value = unicodedata.normalize('NFKC', value).lower().strip() |
65bd8b43 OM |
131 | value = re.sub(r'[\\/<>:\?\*\|"]', '', value) |
132 | value = re.sub(r'\.*$', '', value) | |
133 | return value | |
975060c9 | 134 | |
b497d705 OM |
135 | class PageChecker(object): |
136 | def __init__(self): | |
137 | self.log = [] | |
138 | self.title = None | |
139 | self.file_count = None | |
140 | self.files = None | |
fb28c59b OM |
141 | self.images = None |
142 | self.license = None | |
b497d705 OM |
143 | |
144 | ||
145 | def __call__(self, _): | |
146 | try: | |
147 | self.log.append("call") | |
148 | if self.title is None: | |
149 | # first find the name | |
150 | name = EC._find_element(BROWSER, (By.CSS_SELECTOR, "[class^=ThingPage__modelName]")) | |
151 | if name is None: | |
152 | return False | |
153 | self.title = name.text | |
154 | ||
155 | if self.file_count is None: | |
156 | # OK. Do we know how many files we have to download? | |
157 | metrics = EC._find_elements(BROWSER, (By.CSS_SELECTOR, "[class^=MetricButton]")) | |
158 | self.log.append("got some metrics: {}".format(len(metrics))) | |
159 | cur_count = int([x.text.split("\n")[0] for x in metrics if x.text.endswith("\nThing Files")][0]) | |
160 | self.log.append(cur_count) | |
161 | if cur_count == 0: | |
162 | return False | |
163 | self.file_count = cur_count | |
164 | ||
165 | self.log.append("looking for {} files".format(self.file_count)) | |
166 | fileRows = EC._find_elements(BROWSER, (By.CSS_SELECTOR, "[class^=ThingFile__fileRow]")) | |
167 | self.log.append("found {} files".format(len(fileRows))) | |
fb28c59b OM |
168 | if len(fileRows) < self.file_count: |
169 | return False | |
170 | ||
171 | self.log.append("Looking for images") | |
172 | # By this point _should_ have loaded all the images | |
173 | self.images = EC._find_elements(BROWSER, (By.CSS_SELECTOR, "[class^=thumb]")) | |
174 | self.license = EC._find_element(BROWSER, (By.CSS_SELECTOR, "[class^=License__licenseText]")).text | |
175 | self.log.append("found {} images".format(len(self.images))) | |
176 | self.files = fileRows | |
177 | return True | |
b497d705 OM |
178 | except Exception: |
179 | return False | |
180 | ||
181 | ||
182 | ||
183 | ||
6a777954 OM |
184 | class Downloader(multiprocessing.Process): |
185 | """ | |
186 | Class to handle downloading the things we have found to get. | |
187 | """ | |
188 | ||
ae598d73 | 189 | def __init__(self, thing_queue, download_directory, compress): |
6a777954 OM |
190 | multiprocessing.Process.__init__(self) |
191 | # TODO: add parameters | |
192 | self.thing_queue = thing_queue | |
193 | self.download_directory = download_directory | |
ae598d73 | 194 | self.compress = compress |
6a777954 OM |
195 | |
196 | def run(self): | |
197 | """ actual download loop. | |
198 | """ | |
199 | while True: | |
200 | thing_id = self.thing_queue.get() | |
201 | if thing_id is None: | |
202 | logging.info("Shutting download queue") | |
203 | self.thing_queue.task_done() | |
204 | break | |
205 | logging.info("Handling id {}".format(thing_id)) | |
ae598d73 | 206 | Thing(thing_id).download(self.download_directory, self.compress) |
6a777954 OM |
207 | self.thing_queue.task_done() |
208 | return | |
209 | ||
7b84ba6d | 210 | |
6a777954 OM |
211 | |
212 | ||
dbdb1782 | 213 | |
3522a3bf | 214 | class Grouping: |
d66f1f78 | 215 | """ Holds details of a group of things for download |
3c82f75b OM |
216 | This is effectively (although not actually) an abstract class |
217 | - use Collection or Designs instead. | |
218 | """ | |
dbdb1782 | 219 | |
ae598d73 | 220 | def __init__(self, quick, compress): |
975060c9 OM |
221 | self.things = [] |
222 | self.total = 0 | |
223 | self.req_id = None | |
224 | self.last_page = 0 | |
225 | self.per_page = None | |
7b84ba6d OM |
226 | # Should we stop downloading when we hit a known datestamp? |
227 | self.quick = quick | |
ae598d73 | 228 | self.compress = compress |
948bd56f | 229 | # These should be set by child classes. |
3522a3bf OM |
230 | self.url = None |
231 | self.download_dir = None | |
948bd56f | 232 | self.collection_url = None |
975060c9 | 233 | |
3522a3bf OM |
234 | def _get_small_grouping(self, req): |
235 | """ Handle small groupings """ | |
975060c9 | 236 | soup = BeautifulSoup(req.text, features='lxml') |
dbdb1782 | 237 | links = soup.find_all('a', {'class': 'card-img-holder'}) |
975060c9 | 238 | self.things = [x['href'].split(':')[1] for x in links] |
fa2f3251 | 239 | self.total = len(self.things) |
975060c9 OM |
240 | |
241 | return self.things | |
242 | ||
3522a3bf OM |
243 | def get(self): |
244 | """ retrieve the things of the grouping. """ | |
975060c9 OM |
245 | if self.things: |
246 | # We've already done it. | |
247 | return self.things | |
248 | ||
3522a3bf OM |
249 | # Check for initialisation: |
250 | if not self.url: | |
fa2f3251 | 251 | logging.error("No URL set - object not initialised properly?") |
3522a3bf OM |
252 | raise ValueError("No URL set - object not initialised properly?") |
253 | ||
254 | # Get the internal details of the grouping. | |
fa2f3251 | 255 | logging.debug("Querying {}".format(self.url)) |
3522a3bf | 256 | c_req = requests.get(self.url) |
975060c9 OM |
257 | total = TOTAL_REGEX.search(c_req.text) |
258 | if total is None: | |
3522a3bf OM |
259 | # This is a small (<13) items grouping. Pull the list from this req. |
260 | return self._get_small_grouping(c_req) | |
975060c9 OM |
261 | self.total = total.groups()[0] |
262 | self.req_id = ID_REGEX.search(c_req.text).groups()[0] | |
263 | self.last_page = int(LAST_PAGE_REGEX.search(c_req.text).groups()[0]) | |
264 | self.per_page = PER_PAGE_REGEX.search(c_req.text).groups()[0] | |
265 | parameters = { | |
dbdb1782 OM |
266 | 'base_url': self.url, |
267 | 'page': '1', | |
268 | 'per_page': '12', | |
269 | 'id': self.req_id | |
975060c9 OM |
270 | } |
271 | for current_page in range(1, self.last_page + 1): | |
272 | parameters['page'] = current_page | |
948bd56f | 273 | req = requests.post(self.collection_url, parameters) |
975060c9 | 274 | soup = BeautifulSoup(req.text, features='lxml') |
dbdb1782 | 275 | links = soup.find_all('a', {'class': 'card-img-holder'}) |
975060c9 OM |
276 | self.things += [x['href'].split(':')[1] for x in links] |
277 | ||
278 | return self.things | |
279 | ||
280 | def download(self): | |
281 | """ Downloads all the files in a collection """ | |
282 | if not self.things: | |
3522a3bf OM |
283 | self.get() |
284 | ||
285 | if not self.download_dir: | |
dbdb1782 OM |
286 | raise ValueError( |
287 | "No download_dir set - invalidly initialised object?") | |
3522a3bf | 288 | |
975060c9 | 289 | base_dir = os.getcwd() |
975060c9 | 290 | try: |
3522a3bf | 291 | os.mkdir(self.download_dir) |
975060c9 | 292 | except FileExistsError: |
fa2f3251 | 293 | logging.info("Target directory {} already exists. Assuming a resume." |
dbdb1782 | 294 | .format(self.download_dir)) |
fa2f3251 | 295 | logging.info("Downloading {} thing(s).".format(self.total)) |
dbdb1782 | 296 | for idx, thing in enumerate(self.things): |
fb28c59b | 297 | logging.info("Downloading thing {} - {}".format(idx, thing)) |
ae598d73 | 298 | RC = Thing(thing).download(self.download_dir, self.compress) |
7b84ba6d OM |
299 | if self.quick and RC==State.ALREADY_DOWNLOADED: |
300 | logging.info("Caught up, stopping.") | |
301 | return | |
975060c9 | 302 | |
dbdb1782 | 303 | |
ae598d73 OM |
304 | |
305 | ||
306 | ||
3522a3bf OM |
307 | class Collection(Grouping): |
308 | """ Holds details of a collection. """ | |
dbdb1782 | 309 | |
ae598d73 OM |
310 | def __init__(self, user, name, directory, quick, compress): |
311 | Grouping.__init__(self, quick, compress) | |
3522a3bf OM |
312 | self.user = user |
313 | self.name = name | |
3c82f75b OM |
314 | self.url = "{}/{}/collections/{}".format( |
315 | URL_BASE, self.user, strip_ws(self.name)) | |
d66f1f78 | 316 | self.download_dir = os.path.join(directory, |
3c82f75b | 317 | "{}-{}".format(slugify(self.user), slugify(self.name))) |
948bd56f | 318 | self.collection_url = URL_COLLECTION |
3522a3bf | 319 | |
dbdb1782 | 320 | |
3522a3bf OM |
321 | class Designs(Grouping): |
322 | """ Holds details of all of a users' designs. """ | |
dbdb1782 | 323 | |
ae598d73 OM |
324 | def __init__(self, user, directory, quick, compress): |
325 | Grouping.__init__(self, quick, compress) | |
3522a3bf OM |
326 | self.user = user |
327 | self.url = "{}/{}/designs".format(URL_BASE, self.user) | |
dbdb1782 OM |
328 | self.download_dir = os.path.join( |
329 | directory, "{} designs".format(slugify(self.user))) | |
948bd56f | 330 | self.collection_url = USER_COLLECTION |
975060c9 | 331 | |
dbdb1782 | 332 | |
3c82f75b OM |
333 | class Thing: |
334 | """ An individual design on thingiverse. """ | |
dbdb1782 | 335 | |
3c82f75b OM |
336 | def __init__(self, thing_id): |
337 | self.thing_id = thing_id | |
338 | self.last_time = None | |
339 | self._parsed = False | |
340 | self._needs_download = True | |
341 | self.text = None | |
342 | self.title = None | |
343 | self.download_dir = None | |
ae598d73 OM |
344 | self.time_stamp = None |
345 | self._file_links = FileLinks() | |
975060c9 | 346 | |
3c82f75b OM |
347 | def _parse(self, base_dir): |
348 | """ Work out what, if anything needs to be done. """ | |
349 | if self._parsed: | |
350 | return | |
e36c2a07 | 351 | |
3c82f75b | 352 | url = "{}/thing:{}/files".format(URL_BASE, self.thing_id) |
e0e69fc6 | 353 | try: |
b497d705 | 354 | BROWSER.get(url) |
fb28c59b | 355 | wait = WebDriverWait(BROWSER, 60) |
b497d705 OM |
356 | pc = PageChecker() |
357 | wait.until(pc) | |
e0e69fc6 | 358 | except requests.exceptions.ConnectionError as error: |
8cdd1b54 OM |
359 | logging.error("Unable to connect for thing {}: {}".format( |
360 | self.thing_id, error)) | |
361 | return | |
fb28c59b OM |
362 | except selenium.common.exceptions.TimeoutException: |
363 | logging.error(pc.log) | |
364 | logging.error("Timeout trying to parse thing {}".format(self.thing_id)) | |
365 | return | |
e0e69fc6 | 366 | |
b497d705 | 367 | self.title = pc.title |
247c2cd5 OM |
368 | if not pc.files: |
369 | logging.error("No files found for thing {} - probably thingiverse being broken, try again later".format(self.thing_id)) | |
b497d705 | 370 | for link in pc.files: |
fb28c59b | 371 | logging.debug("Parsing link: {}".format(link.text)) |
b497d705 | 372 | link_link = link.find_element_by_xpath(".//a").get_attribute("href") |
fb28c59b OM |
373 | if link_link.endswith("/zip"): |
374 | # bulk link. | |
375 | continue | |
376 | try: | |
377 | link_title, link_details, _ = link.text.split("\n") | |
378 | except ValueError: | |
379 | # If it is a filetype that doesn't generate a picture, then we get an extra field at the start. | |
380 | _, link_title, link_details, _ = link.text.split("\n") | |
381 | ||
382 | #link_details will be something like '461 kb | Updated 06-11-2019 | 373 Downloads' | |
383 | #need to convert from M D Y to Y M D | |
1267e583 | 384 | link_date = [int(x) for x in link_details.split("|")[1].split()[-1].split("-")] |
fb28c59b | 385 | try: |
d194b140 | 386 | self._file_links.append(FileLink(link_title, datetime.datetime(link_date[2], link_date[0], link_date[1]), link_link)) |
fb28c59b OM |
387 | except ValueError: |
388 | logging.error(link_date) | |
389 | ||
390 | self._image_links=[x.find_element_by_xpath(".//img").get_attribute("src") for x in pc.images] | |
d194b140 | 391 | self._license = pc.license |
fb28c59b | 392 | self.pc = pc |
e0e69fc6 | 393 | |
e0e69fc6 | 394 | |
fb28c59b OM |
395 | self.old_download_dir = os.path.join(base_dir, slugify(self.title)) |
396 | self.download_dir = os.path.join(base_dir, "{} - {}".format(self.thing_id, slugify(self.title))) | |
3c82f75b | 397 | |
fa2f3251 OM |
398 | logging.debug("Parsing {} ({})".format(self.thing_id, self.title)) |
399 | ||
3c82f75b | 400 | if not os.path.exists(self.download_dir): |
fb28c59b | 401 | logging.info("Looking for old dir at {}".format(self.old_download_dir)) |
3b497b1a | 402 | if os.path.exists(self.old_download_dir): |
fb28c59b OM |
403 | logging.warning("Found previous style download directory. Moving it from {} to {}".format(self.old_download_dir, self.download_dir)) |
404 | os.rename(self.old_download_dir, self.download_dir) | |
3b497b1a M |
405 | else: |
406 | # Not yet downloaded | |
407 | self._parsed = True | |
408 | return | |
3c82f75b OM |
409 | |
410 | timestamp_file = os.path.join(self.download_dir, 'timestamp.txt') | |
411 | if not os.path.exists(timestamp_file): | |
412 | # Old download from before | |
dbdb1782 OM |
413 | logging.warning( |
414 | "Old-style download directory found. Assuming update required.") | |
3c82f75b OM |
415 | self._parsed = True |
416 | return | |
417 | ||
418 | try: | |
419 | with open(timestamp_file, 'r') as timestamp_handle: | |
b497d705 | 420 | # add the .split(' ')[0] to remove the timestamp from the old style timestamps |
fb28c59b OM |
421 | last_bits = [int(x) for x in timestamp_handle.readlines()[0].split(' ')[0].split("-")] |
422 | logging.warning(last_bits) | |
9828dabe OM |
423 | if last_bits[0] == 0: |
424 | last_bits[0] = 1 | |
425 | if last_bits[1] == 0: | |
426 | last_bits[1] = 1 | |
427 | if last_bits[2] == 0: | |
428 | last_bits[2] = 1980 | |
fb28c59b OM |
429 | try: |
430 | self.last_time = datetime.datetime(last_bits[0], last_bits[1], last_bits[2]) | |
431 | except ValueError: | |
432 | # This one appears to be M D Y | |
433 | self.last_time = datetime.datetime(last_bits[2], last_bits[0], last_bits[1]) | |
434 | ||
fa2f3251 | 435 | logging.info("last downloaded version: {}".format(self.last_time)) |
3c82f75b OM |
436 | except FileNotFoundError: |
437 | # Not run on this thing before. | |
dbdb1782 OM |
438 | logging.info( |
439 | "Old-style download directory found. Assuming update required.") | |
3c82f75b | 440 | self.last_time = None |
b497d705 | 441 | self._needs_download = True |
3c82f75b OM |
442 | self._parsed = True |
443 | return | |
444 | ||
445 | # OK, so we have a timestamp, lets see if there is anything new to get | |
ae598d73 OM |
446 | try: |
447 | if self._file_links.last_update > self.last_time: | |
dbdb1782 | 448 | logging.info( |
ae598d73 | 449 | "Found new/updated files {}".format(self._file_links.last_update)) |
3c82f75b OM |
450 | self._needs_download = True |
451 | self._parsed = True | |
452 | return | |
ae598d73 OM |
453 | except TypeError: |
454 | logging.warning("No files found for {}.".format(self.thing_id)) | |
b497d705 | 455 | |
3c82f75b | 456 | # Got here, so nope, no new files. |
3c82f75b OM |
457 | self._needs_download = False |
458 | self._parsed = True | |
459 | ||
ae598d73 | 460 | def download(self, base_dir, compress): |
7b84ba6d OM |
461 | """ Download all files for a given thing. |
462 | Returns True iff the thing is now downloaded (not iff it downloads the thing!) | |
463 | """ | |
3c82f75b OM |
464 | if not self._parsed: |
465 | self._parse(base_dir) | |
466 | ||
e0e69fc6 | 467 | if not self._parsed: |
8cdd1b54 OM |
468 | logging.error( |
469 | "Unable to parse {} - aborting download".format(self.thing_id)) | |
7b84ba6d | 470 | return State.FAILED |
e0e69fc6 | 471 | |
3c82f75b | 472 | if not self._needs_download: |
7b84ba6d OM |
473 | print("{} - {} already downloaded - skipping.".format(self.thing_id, self.title)) |
474 | return State.ALREADY_DOWNLOADED | |
3c82f75b | 475 | |
247c2cd5 OM |
476 | if not self._file_links: |
477 | print("{} - {} appears to have no files. Thingiverse acting up again?".format(self.thing_id, self.title)) | |
478 | return State.FAILED | |
479 | ||
3c82f75b OM |
480 | # Have we already downloaded some things? |
481 | timestamp_file = os.path.join(self.download_dir, 'timestamp.txt') | |
482 | prev_dir = None | |
483 | if os.path.exists(self.download_dir): | |
484 | if not os.path.exists(timestamp_file): | |
485 | # edge case: old style dir w/out timestamp. | |
fb28c59b | 486 | logging.warning("Old style download dir found at {}".format(self.title)) |
4f94efc8 OM |
487 | prev_count = 0 |
488 | target_dir = "{}_old".format(self.download_dir) | |
489 | while os.path.exists(target_dir): | |
490 | prev_count = prev_count + 1 | |
491 | target_dir = "{}_old_{}".format(self.download_dir, prev_count) | |
492 | os.rename(self.download_dir, target_dir) | |
3c82f75b | 493 | else: |
fb28c59b | 494 | prev_dir = "{}_{}".format(self.download_dir, slugify(self.last_time.__str__())) |
3c82f75b OM |
495 | os.rename(self.download_dir, prev_dir) |
496 | ||
497 | # Get the list of files to download | |
3c82f75b OM |
498 | |
499 | new_file_links = [] | |
500 | old_file_links = [] | |
ae598d73 | 501 | self.time_stamp = None |
3c82f75b OM |
502 | |
503 | if not self.last_time: | |
504 | # If we don't have anything to copy from, then it is all new. | |
b497d705 OM |
505 | logging.debug("No last time, downloading all files") |
506 | new_file_links = self._file_links | |
ae598d73 | 507 | self.time_stamp = new_file_links[0].last_update |
b497d705 OM |
508 | |
509 | for file_link in new_file_links: | |
ae598d73 OM |
510 | self.time_stamp = max(self.time_stamp, file_link.last_update) |
511 | logging.debug("New timestamp will be {}".format(self.time_stamp)) | |
3c82f75b | 512 | else: |
ae598d73 | 513 | self.time_stamp = self.last_time |
b497d705 OM |
514 | for file_link in self._file_links: |
515 | if file_link.last_update > self.last_time: | |
3c82f75b | 516 | new_file_links.append(file_link) |
ae598d73 | 517 | self.time_stamp = max(self.time_stamp, file_link.last_update) |
3c82f75b OM |
518 | else: |
519 | old_file_links.append(file_link) | |
3c82f75b | 520 | |
ae598d73 | 521 | logging.debug("new timestamp {}".format(self.time_stamp)) |
3c82f75b OM |
522 | |
523 | # OK. Time to get to work. | |
fa2f3251 | 524 | logging.debug("Generating download_dir") |
3c82f75b | 525 | os.mkdir(self.download_dir) |
b497d705 | 526 | filelist_file = os.path.join(self.download_dir, "filelist.txt") |
d194b140 | 527 | with open(filelist_file, 'w', encoding="utf-8") as fl_handle: |
b497d705 OM |
528 | for fl in self._file_links: |
529 | base_link = fl.link | |
530 | try: | |
531 | fl.link=requests.get(fl.link, allow_redirects=False).headers['location'] | |
fb28c59b OM |
532 | except Exception: |
533 | # Sometimes Thingiverse just gives us the direct link the first time. Not sure why. | |
534 | pass | |
b497d705 | 535 | |
fb28c59b | 536 | fl_handle.write("{},{},{}, {}\n".format(fl.link, fl.name, fl.last_update, base_link)) |
b497d705 OM |
537 | |
538 | ||
3c82f75b | 539 | # First grab the cached files (if any) |
fa2f3251 | 540 | logging.info("Copying {} unchanged files.".format(len(old_file_links))) |
3c82f75b | 541 | for file_link in old_file_links: |
b497d705 | 542 | old_file = os.path.join(prev_dir, file_link.name) |
65bd8b43 | 543 | new_file = truncate_name(os.path.join(self.download_dir, file_link.name)) |
3c82f75b | 544 | try: |
fa2f3251 | 545 | logging.debug("Copying {} to {}".format(old_file, new_file)) |
3c82f75b OM |
546 | copyfile(old_file, new_file) |
547 | except FileNotFoundError: | |
dbdb1782 OM |
548 | logging.warning( |
549 | "Unable to find {} in old archive, redownloading".format(file_link["title"])) | |
3c82f75b OM |
550 | new_file_links.append(file_link) |
551 | ||
552 | # Now download the new ones | |
dbdb1782 | 553 | logging.info("Downloading {} new files of {}".format( |
b497d705 | 554 | len(new_file_links), len(self._file_links))) |
3c82f75b | 555 | try: |
b497d705 | 556 | for file_link in new_file_links: |
65bd8b43 | 557 | file_name = truncate_name(os.path.join(self.download_dir, file_link.name)) |
dbdb1782 | 558 | logging.debug("Downloading {} from {} to {}".format( |
b497d705 OM |
559 | file_link.name, file_link.link, file_name)) |
560 | data_req = requests.get(file_link.link) | |
3c82f75b OM |
561 | with open(file_name, 'wb') as handle: |
562 | handle.write(data_req.content) | |
563 | except Exception as exception: | |
b497d705 | 564 | logging.error("Failed to download {} - {}".format(file_link.name, exception)) |
65bd8b43 | 565 | fail_dir(self.download_dir) |
7b84ba6d | 566 | return State.FAILED |
3c82f75b | 567 | |
b497d705 | 568 | |
b497d705 | 569 | # People like images. But this doesn't work yet. |
680039fe | 570 | image_dir = os.path.join(self.download_dir, 'images') |
fb28c59b | 571 | logging.info("Downloading {} images.".format(len(self._image_links))) |
680039fe OM |
572 | try: |
573 | os.mkdir(image_dir) | |
fb28c59b OM |
574 | for imagelink in self._image_links: |
575 | filename = os.path.basename(imagelink) | |
680039fe OM |
576 | if filename.endswith('stl'): |
577 | filename = "{}.png".format(filename) | |
fb28c59b | 578 | image_req = requests.get(imagelink) |
65bd8b43 | 579 | with open(truncate_name(os.path.join(image_dir, filename)), 'wb') as handle: |
680039fe OM |
580 | handle.write(image_req.content) |
581 | except Exception as exception: | |
582 | print("Failed to download {} - {}".format(filename, exception)) | |
65bd8b43 | 583 | fail_dir(self.download_dir) |
7b84ba6d | 584 | return State.FAILED |
680039fe | 585 | |
fb28c59b | 586 | """ |
4f75dd69 OM |
587 | # instructions are good too. |
588 | logging.info("Downloading readme") | |
589 | try: | |
8cdd1b54 OM |
590 | readme_txt = soup.find('meta', property='og:description')[ |
591 | 'content'] | |
592 | with open(os.path.join(self.download_dir, 'readme.txt'), 'w') as readme_handle: | |
4f75dd69 OM |
593 | readme_handle.write("{}\n".format(readme_txt)) |
594 | except (TypeError, KeyError) as exception: | |
595 | logging.warning("No readme? {}".format(exception)) | |
596 | except IOError as exception: | |
597 | logging.warning("Failed to write readme! {}".format(exception)) | |
598 | ||
fb28c59b | 599 | """ |
4f75dd69 OM |
600 | # Best get some licenses |
601 | logging.info("Downloading license") | |
602 | try: | |
fb28c59b | 603 | if self._license: |
65bd8b43 | 604 | with open(truncate_name(os.path.join(self.download_dir, 'license.txt')), 'w', encoding="utf-8") as license_handle: |
fb28c59b | 605 | license_handle.write("{}\n".format(self._license)) |
4f75dd69 OM |
606 | except IOError as exception: |
607 | logging.warning("Failed to write license! {}".format(exception)) | |
fb28c59b | 608 | |
3c82f75b OM |
609 | try: |
610 | # Now write the timestamp | |
d194b140 | 611 | with open(timestamp_file, 'w', encoding="utf-8") as timestamp_handle: |
ae598d73 | 612 | timestamp_handle.write(self.time_stamp.__str__()) |
3c82f75b OM |
613 | except Exception as exception: |
614 | print("Failed to write timestamp file - {}".format(exception)) | |
65bd8b43 | 615 | fail_dir(self.download_dir) |
7b84ba6d | 616 | return State.FAILED |
3c82f75b | 617 | self._needs_download = False |
fa2f3251 | 618 | logging.debug("Download of {} finished".format(self.title)) |
ae598d73 OM |
619 | if not compress: |
620 | return State.OK | |
621 | ||
622 | ||
623 | thing_dir = "{} - {} - {}".format(self.thing_id, | |
624 | slugify(self.title), | |
625 | self.time_stamp) | |
626 | file_name = os.path.join(base_dir, | |
627 | "{}.7z".format(thing_dir)) | |
628 | logging.debug("Compressing {} to {}".format( | |
629 | self.title, | |
630 | file_name)) | |
631 | #with libarchive.file_writer(filename, 'lzma', '7z') as archive: | |
632 | with py7zr.SevenZipFile(file_name, 'w', filters=SEVENZIP_FILTERS) as archive: | |
633 | #with py7zr.SevenZipFile(file_name, 'w' ) as archive: | |
634 | archive.writeall(self.download_dir, thing_dir) | |
635 | logging.debug("Compression of {} finished.".format(self.title)) | |
7b84ba6d | 636 | return State.OK |
975060c9 | 637 | |
dbdb1782 | 638 | |
ae598d73 OM |
639 | |
640 | ||
641 | def do_batch(batch_file, download_dir, quick, compress): | |
1ab49020 OM |
642 | """ Read a file in line by line, parsing each as a set of calls to this script.""" |
643 | with open(batch_file) as handle: | |
644 | for line in handle: | |
645 | line = line.strip() | |
cf280385 M |
646 | if not line: |
647 | # Skip empty lines | |
648 | continue | |
1ab49020 OM |
649 | logging.info("Handling instruction {}".format(line)) |
650 | command_arr = line.split() | |
651 | if command_arr[0] == "thing": | |
dbdb1782 OM |
652 | logging.debug( |
653 | "Handling batch thing instruction: {}".format(line)) | |
ae598d73 | 654 | Thing(command_arr[1]).download(download_dir, compress) |
1ab49020 OM |
655 | continue |
656 | if command_arr[0] == "collection": | |
dbdb1782 OM |
657 | logging.debug( |
658 | "Handling batch collection instruction: {}".format(line)) | |
659 | Collection(command_arr[1], command_arr[2], | |
ae598d73 | 660 | download_dir, quick, compress).download() |
1ab49020 OM |
661 | continue |
662 | if command_arr[0] == "user": | |
dbdb1782 OM |
663 | logging.debug( |
664 | "Handling batch collection instruction: {}".format(line)) | |
ae598d73 | 665 | Designs(command_arr[1], download_dir, quick, compress).download() |
1ab49020 OM |
666 | continue |
667 | logging.warning("Unable to parse current instruction. Skipping.") | |
668 | ||
dbdb1782 | 669 | |
975060c9 OM |
670 | def main(): |
671 | """ Entry point for script being run as a command. """ | |
672 | parser = argparse.ArgumentParser() | |
dbdb1782 OM |
673 | parser.add_argument("-l", "--log-level", choices=[ |
674 | 'debug', 'info', 'warning'], default='info', help="level of logging desired") | |
675 | parser.add_argument("-d", "--directory", | |
676 | help="Target directory to download into") | |
4f94efc8 OM |
677 | parser.add_argument("-f", "--log-file", |
678 | help="Place to log debug information to") | |
7b84ba6d OM |
679 | parser.add_argument("-q", "--quick", action="store_true", |
680 | help="Assume date ordering on posts") | |
ae598d73 OM |
681 | parser.add_argument("-c", "--compress", action="store_true", |
682 | help="Compress files") | |
683 | ||
7b84ba6d | 684 | |
dbdb1782 OM |
685 | subparsers = parser.add_subparsers( |
686 | help="Type of thing to download", dest="subcommand") | |
687 | collection_parser = subparsers.add_parser( | |
b7bfef68 | 688 | 'collection', help="Download one or more entire collection(s)") |
dbdb1782 | 689 | collection_parser.add_argument( |
b7bfef68 | 690 | "owner", help="The owner of the collection(s) to get") |
dbdb1782 | 691 | collection_parser.add_argument( |
b7bfef68 | 692 | "collections", nargs="+", help="Space seperated list of the name(s) of collection to get") |
dbdb1782 OM |
693 | thing_parser = subparsers.add_parser( |
694 | 'thing', help="Download a single thing.") | |
8cdd1b54 OM |
695 | thing_parser.add_argument( |
696 | "things", nargs="*", help="Space seperated list of thing ID(s) to download") | |
dbdb1782 | 697 | user_parser = subparsers.add_parser( |
b7bfef68 | 698 | "user", help="Download all things by one or more users") |
8cdd1b54 OM |
699 | user_parser.add_argument( |
700 | "users", nargs="+", help="A space seperated list of the user(s) to get the designs of") | |
dbdb1782 OM |
701 | batch_parser = subparsers.add_parser( |
702 | "batch", help="Perform multiple actions written in a text file") | |
703 | batch_parser.add_argument( | |
704 | "batch_file", help="The name of the file to read.") | |
680039fe | 705 | subparsers.add_parser("version", help="Show the current version") |
4a98996b | 706 | |
975060c9 | 707 | args = parser.parse_args() |
4a98996b OM |
708 | if not args.subcommand: |
709 | parser.print_help() | |
710 | sys.exit(1) | |
d66f1f78 OM |
711 | if not args.directory: |
712 | args.directory = os.getcwd() | |
4f94efc8 OM |
713 | |
714 | logger = logging.getLogger() | |
715 | formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s') | |
716 | logger.setLevel(logging.DEBUG) | |
717 | console_handler = logging.StreamHandler() | |
718 | console_handler.setLevel(args.log_level.upper()) | |
719 | ||
720 | logger.addHandler(console_handler) | |
721 | if args.log_file: | |
722 | file_handler = logging.FileHandler(args.log_file) | |
723 | file_handler.setLevel(logging.DEBUG) | |
724 | file_handler.setFormatter(formatter) | |
725 | logger.addHandler(file_handler) | |
fa2f3251 | 726 | |
6a777954 OM |
727 | |
728 | # Start downloader | |
729 | thing_queue = multiprocessing.JoinableQueue() | |
730 | logging.debug("starting {} downloader(s)".format(DOWNLOADER_COUNT)) | |
ae598d73 | 731 | downloaders = [Downloader(thing_queue, args.directory, args.compress) for _ in range(DOWNLOADER_COUNT)] |
6a777954 OM |
732 | for downloader in downloaders: |
733 | downloader.start() | |
734 | ||
735 | ||
4a98996b | 736 | if args.subcommand.startswith("collection"): |
b7bfef68 | 737 | for collection in args.collections: |
ae598d73 | 738 | Collection(args.owner, collection, args.directory, args.quick, args.compress).download() |
4a98996b | 739 | if args.subcommand == "thing": |
b7bfef68 | 740 | for thing in args.things: |
6a777954 | 741 | thing_queue.put(thing) |
3522a3bf | 742 | if args.subcommand == "user": |
b7bfef68 | 743 | for user in args.users: |
ae598d73 | 744 | Designs(user, args.directory, args.quick, args.compress).download() |
db8066ec OM |
745 | if args.subcommand == "version": |
746 | print("thingy_grabber.py version {}".format(VERSION)) | |
1ab49020 | 747 | if args.subcommand == "batch": |
ae598d73 | 748 | do_batch(args.batch_file, args.directory, args.quick, args.compress) |
1ab49020 | 749 | |
6a777954 OM |
750 | # Stop the downloader processes |
751 | for downloader in downloaders: | |
752 | thing_queue.put(None) | |
975060c9 | 753 | |
d194b140 OM |
754 | atexit.register(BROWSER.quit) |
755 | ||
0930777e OM |
756 | if __name__ == "__main__": |
757 | multiprocessing.freeze_support() | |
975060c9 | 758 | main() |