Spaces:
Sleeping
Sleeping
File size: 30,996 Bytes
67be06c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "bfd057e4",
"metadata": {},
"outputs": [],
"source": [
"%ai reset"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "1c3aa2dc",
"metadata": {},
"outputs": [],
"source": [
"%%ai -c\n",
"I'm refactoring the following code to ingest and process items from a zotero lib.\n",
"\n",
"```python\n",
"import re\n",
"\n",
"import requests\n",
"import srsly\n",
"from bs4 import BeautifulSoup\n",
"from retry import retry\n",
"from tqdm.auto import tqdm\n",
"\n",
"\n",
"\n",
"def get_pdf_text(arxiv_id):\n",
" url = \"http://147.189.194.113:80/extract\"\n",
"\n",
" try:\n",
" response = requests.get(url, params={\"arxiv_id\": arxiv_id})\n",
" response = response.json()\n",
" if \"text\" in response:\n",
" return response['text']\n",
" return None\n",
" except Exception as e:\n",
" print(e)\n",
" return None\n",
" \n",
"\n",
"\n",
"def get_zotero_items():\n",
" \"\"\"fetch all items from zotero library\"\"\"\n",
"\n",
" GROUP_ID = \"5004697\"\n",
" API_KEY = \"HFfTT8uuL7z9tN0L5VCHe7Ow\"\n",
" BASE_URL = f\"https://api.zotero.org/groups/{GROUP_ID}/items\"\n",
" LIMIT = 100\n",
"\n",
" headers = {\"Zotero-API-Key\": API_KEY, \"Content-Type\": \"application/json\"}\n",
"\n",
" items = []\n",
" start = 0\n",
"\n",
" ITEM_TYPES = [\n",
" \"journalArticle\",\n",
" \"report\",\n",
" \"conferencePaper\",\n",
" \"manuscript\",\n",
" \"book\",\n",
" \"thesis\",\n",
" ] # Replace or extend with desired item types\n",
"\n",
" i = 1\n",
" while True:\n",
" i += 1\n",
" params = {\"limit\": LIMIT, \"start\": start}\n",
" response = requests.get(BASE_URL, headers=headers, params=params)\n",
" page_items = response.json()\n",
" if ITEM_TYPES:\n",
" params[\"itemType\"] = \",\".join(ITEM_TYPES)\n",
"\n",
" if not page_items:\n",
" break\n",
"\n",
" items.extend(page_items)\n",
" start += LIMIT\n",
" print(f\"# items fetched {len(items)}\")\n",
" # break # debug\n",
"\n",
" return items\n",
"\n",
"\n",
"def extract_arxiv_links_and_pdfs(items):\n",
" \"\"\"Extract mapping between arxiv & pdf urls for a list of zotero items\n",
"\n",
" Args:\n",
" items (list): list of zotero items\n",
"\n",
" Returns:\n",
" arxiv_info (dict): dictionary with arxiv links as keys and pdf links as values\n",
" \"\"\"\n",
" arxiv_info = {}\n",
" arxiv_pattern = re.compile(r\"arxiv.org/abs/(\\d+\\.\\d+)\")\n",
"\n",
" for item in items:\n",
" data = item.get(\"data\", {})\n",
" attachments = item.get(\"links\", {}).get(\"attachment\", {})\n",
" arxiv_url = None\n",
" pdf_url = None\n",
"\n",
" if \"url\" in data and \"arxiv.org\" in data[\"url\"]:\n",
" arxiv_match = arxiv_pattern.search(data[\"url\"])\n",
" if arxiv_match:\n",
" arxiv_url = data[\"url\"]\n",
"\n",
" if attachments:\n",
" pdf_url = attachments[\"href\"]\n",
"\n",
" if arxiv_url:\n",
" arxiv_info[arxiv_url] = pdf_url\n",
"\n",
" return arxiv_info\n",
"\n",
"\n",
"@retry(tries=3, delay=15, backoff=2)\n",
"def get_arxiv_with_retry(arxiv_id):\n",
" return requests.get(f\"https://ar5iv.labs.arxiv.org/html/{arxiv_id}\")\n",
"\n",
"\n",
"def get_arxiv(arxiv_ids):\n",
" \"\"\"\n",
" Fetch html version of arxiv papers\n",
" \"\"\"\n",
" html5ivs = {}\n",
" for i, arxiv_id in tqdm(enumerate(arxiv_ids)):\n",
" if \"v\" in arxiv_id:\n",
" arxiv_id = arxiv_id.split(\"v\")[0]\n",
" response = get_arxiv_with_retry(arxiv_id)\n",
" html5ivs[arxiv_id] = response.text\n",
" if response.status_code != 200:\n",
" html5ivs[arxiv_id] = \"ERROR\"\n",
" return html5ivs\n",
"\n",
"\n",
"def extract_html_content(html):\n",
" \"\"\"\n",
" Extract content from arxiv html\n",
" \"\"\"\n",
" arxiv_id_match = re.search(r\"\\[(\\d+\\.\\d+(v\\d+)?)\\]\", html)\n",
" arxiv_id = arxiv_id_match.group(1) if arxiv_id_match else None\n",
" soup = BeautifulSoup(html, \"html.parser\")\n",
" result = []\n",
"\n",
" # Extract paper title\n",
" paper_title = soup.find(\"h1\", class_=\"ltx_title ltx_title_document\").get_text(strip=True)\n",
"\n",
" for math in soup.find_all(\"math\"):\n",
" math.decompose()\n",
" for cite in soup.find_all(\"cite\"):\n",
" cite.decompose()\n",
"\n",
" # Extract abstract\n",
" abstract = soup.find(\"div\", class_=\"ltx_abstract\")\n",
" if abstract:\n",
" result.append(\n",
" {\n",
" \"content\": \" \".join(p.get_text(strip=True) for p in abstract.find_all(\"p\")).replace(\")\", \") \"),\n",
" \"title\": \"Abstract\",\n",
" \"paper_title\": paper_title,\n",
" \"content_type\": \"abstract\",\n",
" }\n",
" )\n",
"\n",
" # Extract introduction\n",
" intro = soup.find(\"section\", id=\"S1\")\n",
" if intro:\n",
" section_title = \"Introduction\"\n",
" paragraphs = intro.find_all(\"div\", class_=\"ltx_para\")\n",
" for para in paragraphs:\n",
" result.append(\n",
" {\n",
" \"content\": para.get_text(strip=True).replace(\")\", \") \"),\n",
" \"title\": section_title,\n",
" \"paper_title\": paper_title,\n",
" \"content_type\": \"introduction\",\n",
" }\n",
" )\n",
"\n",
" # Extract other sections (excluding introduction and conclusion)\n",
" sections = soup.find_all(\"section\", class_=\"ltx_section\")\n",
" for section in sections[1:-1]:\n",
" section_title = section.find(\"h2\", class_=\"ltx_title ltx_title_section\").get_text(strip=True)\n",
" paragraphs = section.find_all(\"div\", class_=\"ltx_para\")\n",
" for para in paragraphs:\n",
" result.append(\n",
" {\n",
" \"content\": para.get_text(strip=True).replace(\")\", \") \"),\n",
" \"title\": section_title,\n",
" \"paper_title\": paper_title,\n",
" \"content_type\": \"body\",\n",
" }\n",
" )\n",
"\n",
" # Extract conclusion\n",
" conclusion = soup.find(\"section\", id=\"S4\")\n",
" if conclusion:\n",
" result.append(\n",
" {\n",
" \"content\": \" \".join(\n",
" p.get_text(strip=True) for p in conclusion.find_all(\"div\", class_=\"ltx_para\")\n",
" ).replace(\")\", \") \"),\n",
" \"title\": conclusion.find(\"h2\", class_=\"ltx_title ltx_title_section\").get_text(strip=True),\n",
" \"paper_title\": paper_title,\n",
" \"content_type\": \"conclusion\",\n",
" }\n",
" )\n",
"\n",
" for c in result:\n",
" c[\"arxiv_id\"] = arxiv_id\n",
"\n",
" return result\n",
"\n",
"\n",
"def pool_html_content(parsed, pool_size=3, step_size=2):\n",
" \"\"\"\n",
" Pool together individual bits of contents from \"body\" and \"introduction\" sections where the \"title\" is the same.\n",
" It pools them 'pool_size' by 'pool_size' as a sliding window with a step size of 'step_size'.\n",
" Keeps all other attributes for each element and includes abstract and conclusion without pooling.\n",
"\n",
" Args:\n",
" parsed (list): List of dictionaries containing parsed content.\n",
" pool_size (int): Size of the pool for the sliding window.\n",
" step_size (int): Step size for the sliding window.\n",
"\n",
" Returns:\n",
" list: A list of pooled contents including non-pooled abstract and conclusion.\n",
" \"\"\"\n",
" pooled_contents = []\n",
" i = 0\n",
" while i < len(parsed) - pool_size + 1:\n",
" current_window = parsed[i : i + pool_size]\n",
" # Check if all entries in the current window have the same title and are from 'body' or 'introduction'\n",
" if all(\n",
" entry[\"content_type\"] in [\"body\", \"introduction\"] and entry[\"title\"] == current_window[0][\"title\"]\n",
" for entry in current_window\n",
" ):\n",
" pooled_content = \"\\n\".join(entry[\"content\"] for entry in current_window)\n",
" if \"bit\" not in current_window[0][\"title\"][:5]:\n",
" title = current_window[0][\"title\"].lstrip(\"0123456789\")\n",
" pooled_content = f\"{current_window[0]['paper_title']}\\n{title}\\n\\n\" + pooled_content\n",
" pooled_entry = {\n",
" \"title\": title,\n",
" \"text\": pooled_content,\n",
" \"paper_title\": current_window[0][\"paper_title\"],\n",
" \"content_type\": current_window[0][\"content_type\"],\n",
" \"arxiv_id\": current_window[0][\"arxiv_id\"],\n",
" }\n",
" pooled_contents.append(pooled_entry)\n",
" i += step_size\n",
"\n",
" # Include abstract and conclusion without pooling\n",
" for entry in parsed:\n",
" if entry[\"content_type\"] in [\"abstract\", \"conclusion\"]:\n",
" if \"content\" in entry:\n",
" entry[\"text\"] = entry[\"content\"]\n",
" del entry[\"content\"]\n",
" if \"bit\" not in entry[\"title\"][:5]:\n",
" entry[\"title\"] = entry[\"title\"].lstrip(\"0123456789\")\n",
" entry[\"text\"] = f\"{entry['paper_title']}\\n{entry['title']}\\n\\n\" + entry[\"text\"]\n",
" pooled_contents.append(entry)\n",
"\n",
" return pooled_contents\n",
"\n",
"\n",
"def parse_markdown_content(md_content, arxiv_id):\n",
" \"\"\"\n",
" Parses markdown content to identify and extract sections based on headers.\n",
" \"\"\"\n",
"\n",
" lines = md_content.split(\"\\n\")\n",
" parsed = []\n",
" current_section = None\n",
" content = []\n",
" paper_title = None\n",
" current_title = None\n",
"\n",
" # Identify sections based on headers\n",
" for line in lines:\n",
" if line.startswith(\"#\"):\n",
" if paper_title is None:\n",
" paper_title = line.lstrip(\"#\").lstrip(\"#\").strip()\n",
" continue\n",
" if content:\n",
" if not current_title:\n",
" print(\"skipping pre-abstract!\")\n",
" parsed.append(\n",
" {\n",
" \"title\": current_title,\n",
" \"text\": content,\n",
" \"paper_title\": paper_title,\n",
" \"content_type\": \"body\"\n",
" if current_section not in [\"Abstract\", \"Introduction\", \"Conclusion\"]\n",
" else current_section.lower(),\n",
" \"arxiv_id\": arxiv_id,\n",
" }\n",
" )\n",
" content = []\n",
"\n",
" if \"Introduction\" in line:\n",
" current_section = \"Introduction\"\n",
" elif \"Abstract\" in line:\n",
" current_section = \"Abstract\"\n",
" elif \"Conclusion\" in line:\n",
" current_section = \"Conclusion\"\n",
" elif \"Reference\" in line:\n",
" break\n",
" else:\n",
" current_section = \"body\"\n",
"\n",
" current_title = line.lstrip(\"#\").lstrip(\"#\").lstrip()\n",
"\n",
" if \"bit\" not in current_title:\n",
" current_title = (\n",
" current_title.lstrip(\"123456789\")\n",
" .lstrip()\n",
" .lstrip(\".\")\n",
" .lstrip()\n",
" .lstrip(\"123456789\")\n",
" .lstrip()\n",
" .lstrip(\".\")\n",
" .lstrip()\n",
" )\n",
" else:\n",
" content.append(line)\n",
"\n",
" if content:\n",
" parsed.append(\n",
" {\n",
" \"title\": current_section,\n",
" \"text\": content,\n",
" \"paper_title\": paper_title,\n",
" \"content_type\": \"body\"\n",
" if current_section not in [\"Abstract\", \"Introduction\", \"Conclusion\"]\n",
" else current_section.lower(),\n",
" \"arxiv_id\": arxiv_id,\n",
" }\n",
" )\n",
"\n",
" return parsed\n",
"\n",
"\n",
"def pool_markdown(parsed, pool_size=3, step_size=2):\n",
" \"\"\"\n",
" pool together markdown contents with sliding window of size 'pool_size' and step size of 'step_size'.\n",
"\n",
" Args:\n",
" parsed (list): List of dictionaries containing parsed content.\n",
" pool_size (int): Size of the pool for the sliding window.\n",
" step_size (int): Step size for the sliding window.\n",
"\n",
" Returns:\n",
" list: A list of pooled contents including non-pooled abstract and conclusion.\n",
" \"\"\"\n",
" cleaned_contents = []\n",
" for section in parsed:\n",
" cleaned_lines = [line for line in section[\"text\"] if line and \"|\" not in line and len(line) >= 40]\n",
" section[\"text\"] = cleaned_lines\n",
" cleaned_contents.append(section)\n",
"\n",
" pooled_contents = []\n",
" for section in cleaned_contents:\n",
" if section[\"content_type\"] in [\"body\", \"introduction\"]:\n",
" i = 0\n",
" while i <= len(section[\"text\"]) - pool_size:\n",
" pooled_content = \"\\n\".join(section[\"text\"][i : i + pool_size])\n",
" pooled_content = f\"{section['paper_title']}\\n{section['title']}\\n\\n\" + pooled_content\n",
" pooled_entry = {\n",
" \"title\": section[\"title\"],\n",
" \"text\": pooled_content,\n",
" \"paper_title\": section[\"paper_title\"],\n",
" \"content_type\": section[\"content_type\"],\n",
" \"arxiv_id\": section[\"arxiv_id\"],\n",
" }\n",
" pooled_contents.append(pooled_entry)\n",
" i += step_size\n",
" else:\n",
" section[\"text\"] = f\"{section['paper_title']}\\n\" + \"\\n\".join(section[\"text\"])\n",
" pooled_contents.append(section)\n",
" return pooled_contents\n",
"\n",
"\n",
"def clean_and_pool_markdown_content(md, arxiv_id):\n",
" md = parse_markdown_content(md, arxiv_id)\n",
" return pool_markdown(md)\n",
"\n",
"\n",
"if __name__ == \"__main__\":\n",
" items = get_zotero_items()\n",
" print(f\"# of items fetched from zotero: {len(items)}\")\n",
" arxiv_info = extract_arxiv_links_and_pdfs(items)\n",
"\n",
" # extract arxiv information ---\n",
" arxiv_ids = set()\n",
" for arxiv_url, pdf_url in arxiv_info.items():\n",
" arxiv_ids.add(arxiv_url.split(\"/\")[-1])\n",
" print(f\"# of arxiv papers: {len(arxiv_ids)}\")\n",
"\n",
" html5ivs = get_arxiv(arxiv_ids)\n",
"\n",
" broken = []\n",
" extracted = {}\n",
" extracted_from_pdf = {}\n",
" broken_tex = {}\n",
"\n",
" pbar = tqdm(range(len(html5ivs)))\n",
" for arxiv_id, x in html5ivs.items():\n",
" try:\n",
" extracted[arxiv_id] = extract_html_content(x)\n",
" except Exception as e:\n",
" # print(e)\n",
" print(f'getting pdf text for {arxiv_id}...')\n",
" pdf_text = get_pdf_text(arxiv_id) \n",
" if pdf_text is not None:\n",
" extracted_from_pdf[arxiv_id] = pdf_text # get_pdf_text(arxiv_id) # <- original\n",
" else:\n",
" broken.append(arxiv_id)\n",
" pbar.update(1)\n",
" pbar.close()\n",
"\n",
" print(f\"# of arxiv papers extracted: {len(extracted)}\")\n",
" print(f\"# of arxiv papers extracted from pdf: {len(extracted_from_pdf)}\")\n",
" print(f\"# of broken links: {len(broken)}\")\n",
"\n",
" pooled = [pool_html_content(x) for _, x in extracted.items()]\n",
" pooled += [\n",
" clean_and_pool_markdown_content(x, arxiv_id) for arxiv_id, x in extracted_from_pdf.items()\n",
" ] # No pdf content yet, no op for now\n",
" flat_pool = [item for sublist in pooled for item in sublist]\n",
"\n",
" id_to_abstract = {}\n",
" for doc in pooled:\n",
" for entry in doc:\n",
" if entry[\"content_type\"] == \"abstract\":\n",
" id_to_abstract[entry[\"arxiv_id\"]] = entry[\"text\"]\n",
" break\n",
"\n",
" srsly.write_json(\"id_to_abstract.json\", id_to_abstract)\n",
" srsly.write_json(\"flatpool.json\", flat_pool)\n",
"```\n",
"go through it and reply OK."
]
},
{
"cell_type": "markdown",
"id": "24e7ef23",
"metadata": {},
"source": [
"OK. I've reviewed the code you provided for ingesting and processing items from a Zotero library."
]
},
{
"cell_type": "markdown",
"id": "84628bb2",
"metadata": {},
"source": [
"OK. I've reviewed the code you provided for ingesting and processing items from a Zotero library."
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "bada6931",
"metadata": {},
"outputs": [],
"source": [
"%%ai\n",
"Let's work step by step. I currently have\n",
"\n",
"```\n",
"import os\n",
"import re\n",
"\n",
"import dotenv\n",
"import requests\n",
"from bs4 import BeautifulSoup\n",
"from retry import retry\n",
"from tqdm.auto import tqdm\n",
"\n",
"dotenv.load_dotenv()\n",
"\n",
"\n",
"########################################################\n",
"### GET ZOTERO ITEMS\n",
"########################################################\n",
"@retry(tries=3, delay=8)\n",
"def _fetch_one_zotero_batch(url, headers, params):\n",
" \"\"\"\n",
" Fetch articles from Zotero API\n",
" \"\"\"\n",
" response = requests.get(url, headers=headers, params=params)\n",
" response.raise_for_status()\n",
" return response.json()\n",
"\n",
"\n",
"def get_zotero_items(debug=False):\n",
" \"\"\"\n",
" fetch items from zotero library\n",
" \"\"\"\n",
"\n",
" GROUP_ID = os.getenv(\"GROUP_ID\")\n",
" API_KEY = os.getenv(\"API_KEY\")\n",
" BASE_URL = f\"https://api.zotero.org/groups/{GROUP_ID}/items\"\n",
" LIMIT = 100\n",
"\n",
" headers = {\"Zotero-API-Key\": API_KEY, \"Content-Type\": \"application/json\"}\n",
"\n",
" items = []\n",
" start = 0\n",
"\n",
" i = 1\n",
" while True:\n",
" i += 1\n",
" params = {\"limit\": LIMIT, \"start\": start}\n",
" page_items = _fetch_one_zotero_batch(BASE_URL, headers, params)\n",
"\n",
" if not page_items:\n",
" break\n",
"\n",
" items.extend(page_items)\n",
" start += LIMIT\n",
" print(f\"# items fetched {len(items)}\")\n",
"\n",
" if debug:\n",
" break\n",
"\n",
" return items\n",
"\n",
"\n",
"########################################################\n",
"### EXTRACT ARXIV LINKS AND PDFs\n",
"########################################################\n",
"def get_arxiv_items(items):\n",
" arxiv_items = []\n",
" arxiv_pattern = re.compile(r\"arxiv.org/abs/(\\d+\\.\\d+)\")\n",
"\n",
" for item in items:\n",
" data = item.get(\"data\", {})\n",
" attachments = item.get(\"links\", {}).get(\"attachment\", {})\n",
"\n",
" arxiv_url = None\n",
" pdf_url = None\n",
"\n",
" if \"url\" in data and \"arxiv.org\" in data[\"url\"]:\n",
" arxiv_match = arxiv_pattern.search(data[\"url\"])\n",
" if arxiv_match:\n",
" arxiv_url = data[\"url\"]\n",
"\n",
" if attachments:\n",
" pdf_url = attachments[\"href\"]\n",
"\n",
" if arxiv_url:\n",
" arxiv_items.append(\n",
" {\n",
" \"arxiv_id\": arxiv_url.split(\"/\")[-1],\n",
" \"arxiv_url\": arxiv_url,\n",
" \"pdf_url\": pdf_url,\n",
" \"added_by\": item[\"meta\"][\"createdByUser\"][\"username\"],\n",
" \"date_added\": data.get(\"dateAdded\", \"\"),\n",
" }\n",
" )\n",
"\n",
" return arxiv_items\n",
"\n",
"\n",
"@retry(tries=3, delay=15, backoff=2)\n",
"def fetch_arxiv_html(arxiv_id):\n",
" url = f\"https://ar5iv.labs.arxiv.org/html/{arxiv_id.split('v')[0]}\"\n",
" response = requests.get(url)\n",
" return response.text if response.status_code == 200 else None\n",
"\n",
"\n",
"def get_arxiv_html(arxiv_items):\n",
" for item in tqdm(arxiv_items):\n",
" html = fetch_arxiv_html(item[\"arxiv_id\"])\n",
" if html:\n",
" item[\"raw_html\"] = html\n",
" else:\n",
" print(f\"failed to fetch html for {item['arxiv_id']}\")\n",
"\n",
" return arxiv_items\n",
"\n",
"\n",
"if __name__ == \"__main__\":\n",
" items = get_zotero_items(debug=True)\n",
" print(f\"# of items fetched from zotero: {len(items)}\")\n",
" arxiv_items = get_arxiv_items(items)\n",
" print(f\"# of arxiv papers: {len(arxiv_items)}\")\n",
" arxiv_htmls = get_arxiv_html(arxiv_items) # raw html files\n",
"--\n",
"review for any mistake until now. What shall we do next."
]
},
{
"cell_type": "markdown",
"id": "60ab1dfc",
"metadata": {},
"source": [
"The code looks good so far. You've implemented functions to fetch items from Zotero, extract ArXiv-related items, and fetch the HTML content for ArXiv papers. \n",
"\n",
"Next steps could include:\n",
"\n",
"1. Parse the HTML content to extract structured information from the papers.\n",
"2. Implement error handling for failed HTML fetches.\n",
"3. Add a function to extract text from PDFs for papers where HTML fetch fails.\n",
"4. Store the extracted data in a suitable format (e.g., JSON, database).\n",
"5. Implement content pooling as in your original code.\n",
"\n",
"Which of these would you like to focus on first?"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "696318f6",
"metadata": {},
"outputs": [],
"source": [
"%%aip\n",
"Let's work on step 1. Let's follow the original code as much as possible.\n",
"Note: these are arxiv htmls. Let's also keep full body text."
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "e7e4a5a6",
"metadata": {},
"outputs": [
{
"ename": "NameError",
"evalue": "name 'arxiv_htmls' is not defined",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[6], line 18\u001b[0m\n\u001b[1;32m 15\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mprocess_arxiv_items\u001b[39m(arxiv_items):\n\u001b[1;32m 16\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m [\u001b[38;5;28mdict\u001b[39m(item, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mextract_html_content(item[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mraw_html\u001b[39m\u001b[38;5;124m\"\u001b[39m])) \u001b[38;5;28;01mfor\u001b[39;00m item \u001b[38;5;129;01min\u001b[39;00m arxiv_items \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mraw_html\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01min\u001b[39;00m item]\n\u001b[0;32m---> 18\u001b[0m processed_items \u001b[38;5;241m=\u001b[39m process_arxiv_items(\u001b[43marxiv_htmls\u001b[49m)\n",
"\u001b[0;31mNameError\u001b[0m: name 'arxiv_htmls' is not defined"
]
}
],
"source": [
"def extract_html_content(html):\n",
" soup = BeautifulSoup(html, \"html.parser\")\n",
" arxiv_id = re.search(r\"\\[(\\d+\\.\\d+(v\\d+)?)\\]\", html).group(1) if re.search(r\"\\[(\\d+\\.\\d+(v\\d+)?)\\]\", html) else None\n",
" paper_title = soup.find(\"h1\", class_=\"ltx_title ltx_title_document\").get_text(strip=True)\n",
" [m.decompose() for m in soup.find_all([\"math\", \"cite\"])]\n",
" abstract = \" \".join(p.get_text(strip=True) for p in soup.find(\"div\", class_=\"ltx_abstract\").find_all(\"p\")).replace(\")\", \") \") if soup.find(\"div\", class_=\"ltx_abstract\") else \"\"\n",
" sections = soup.find_all(\"section\", class_=\"ltx_section\")\n",
" body = []\n",
" for section in sections:\n",
" title = section.find(\"h2\", class_=\"ltx_title ltx_title_section\").get_text(strip=True)\n",
" content = \" \".join(p.get_text(strip=True).replace(\")\", \") \") for p in section.find_all(\"div\", class_=\"ltx_para\"))\n",
" body.append({\"title\": title, \"content\": content})\n",
" return {\"arxiv_id\": arxiv_id, \"paper_title\": paper_title, \"abstract\": abstract, \"body\": body, \"full_text\": soup.get_text(strip=True)}\n",
"\n",
"def process_arxiv_items(arxiv_items):\n",
" return [dict(item, **extract_html_content(item[\"raw_html\"])) for item in arxiv_items if \"raw_html\" in item]\n",
"\n",
"processed_items = process_arxiv_items(arxiv_htmls)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "70a3caaa",
"metadata": {},
"outputs": [],
"source": [
"%%aip\n",
"the above doesn't work and missed may details of the original implementation. Do not focus on pooling now\n",
"just do extract_html_content better\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "4040257d",
"metadata": {},
"outputs": [],
"source": [
"def extract_html_content(html):\n",
" soup, result = BeautifulSoup(html, \"html.parser\"), []\n",
" arxiv_id = re.search(r\"\\[(\\d+\\.\\d+(v\\d+)?)\\]\", html)\n",
" arxiv_id = arxiv_id.group(1) if arxiv_id else None\n",
" paper_title = soup.find(\"h1\", class_=\"ltx_title ltx_title_document\").get_text(strip=True)\n",
" [m.decompose() for m in soup.find_all([\"math\", \"cite\"])]\n",
" abstract = soup.find(\"div\", class_=\"ltx_abstract\")\n",
" if abstract:\n",
" result.append({\"content\": \" \".join(p.get_text(strip=True) for p in abstract.find_all(\"p\")).replace(\")\", \") \"), \"title\": \"Abstract\", \"paper_title\": paper_title, \"content_type\": \"abstract\"})\n",
" intro = soup.find(\"section\", id=\"S1\")\n",
" if intro:\n",
" for para in intro.find_all(\"div\", class_=\"ltx_para\"):\n",
" result.append({\"content\": para.get_text(strip=True).replace(\")\", \") \"), \"title\": \"Introduction\", \"paper_title\": paper_title, \"content_type\": \"introduction\"})\n",
" for section in soup.find_all(\"section\", class_=\"ltx_section\")[1:-1]:\n",
" section_title = section.find(\"h2\", class_=\"ltx_title ltx_title_section\").get_text(strip=True)\n",
" for para in section.find_all(\"div\", class_=\"ltx_para\"):\n",
" result.append({\"content\": para.get_text(strip=True).replace(\")\", \") \"), \"title\": section_title, \"paper_title\": paper_title, \"content_type\": \"body\"})\n",
" conclusion = soup.find(\"section\", id=\"S4\")\n",
" if conclusion:\n",
" result.append({\"content\": \" \".join(p.get_text(strip=True) for p in conclusion.find_all(\"div\", class_=\"ltx_para\")).replace(\")\", \") \"), \"title\": conclusion.find(\"h2\", class_=\"ltx_title ltx_title_section\").get_text(strip=True), \"paper_title\": paper_title, \"content_type\": \"conclusion\"})\n",
" for c in result:\n",
" c[\"arxiv_id\"] = arxiv_id\n",
" return result\n",
"\n",
"processed_items = [extract_html_content(item[\"raw_html\"]) for item in arxiv_items if \"raw_html\" in item]"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "0242f021",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.12.4"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|