121 lines
5.0 KiB
Python
121 lines
5.0 KiB
Python
"""一次性修复: 纠正被误标为全文 PDF 的历史记录(Elsevier 摘要预览页 / 损坏文件)。
|
|
|
|
背景:
|
|
Elsevier Article API 对未授权 / in-press 文章, application/pdf 端点会返回仅含
|
|
摘要的 1 页预览 PDF(魔数仍是 %PDF、体积也不小); 另有部分历史记录把 HTML 错误页 /
|
|
被截断的垃圾当 PDF 存了。旧抓取逻辑只校验魔数 + 体积, 都会误标 has_fulltext_pdf=True。
|
|
|
|
本命令核对本地 PDF, 分两类处理:
|
|
- 预览页(1 页): has_fulltext_pdf 置回 False; 文件**仅在 --delete-file 时**删除。
|
|
- 损坏文件(非 PDF / pypdf 解析失败): has_fulltext_pdf 置回 False; 文件**总是删除**
|
|
(dry-run 除外), 因为它根本不是有效全文, 留着无用且会污染下游解析。
|
|
两类在缺少 XML 全文(has_fulltext_xml=False)时, 一并把 has_fulltext 回退 False,
|
|
让其重新进入下载链路去找真正的全文; 并追加 fail_reason 标记供抓取任务排除。
|
|
|
|
安全前提:
|
|
"损坏"只在铁证下判定 —— 文件不以 %PDF 开头, 或已装 pypdf 且解析直接失败。
|
|
若未装 pypdf 且魔数正常但页数判不出, 归为 unknown, **不处理、绝不删除**。
|
|
强烈建议先 `pip install pypdf` 再跑, 否则只能处理魔数明显不符的坏文件。
|
|
|
|
用法:
|
|
python manage.py fix_preview_pdf --dry-run
|
|
python manage.py fix_preview_pdf # 纠正标记 + 删除坏文件, 保留预览页文件
|
|
python manage.py fix_preview_pdf --delete-file # 并删除预览页文件
|
|
"""
|
|
import os
|
|
|
|
from django.core.management.base import BaseCommand
|
|
|
|
from apps.resm.models import Paper
|
|
from apps.resm.tasks import _inspect_pdf
|
|
|
|
|
|
class Command(BaseCommand):
|
|
help = "纠正被误标为全文的 Elsevier 预览页 / 损坏 PDF"
|
|
|
|
def add_arguments(self, parser):
|
|
parser.add_argument("--dry-run", action="store_true",
|
|
help="只统计, 不写库 / 不删文件")
|
|
parser.add_argument("--limit", type=int, default=0,
|
|
help="最多处理多少条 (0=不限)")
|
|
parser.add_argument("--delete-file", action="store_true",
|
|
help="同时删除预览页文件(坏文件无论该开关都会删)")
|
|
|
|
def handle(self, *args, **opts):
|
|
dry = opts["dry_run"]
|
|
limit = opts["limit"]
|
|
del_preview = opts["delete_file"]
|
|
|
|
qs = Paper.objects.filter(
|
|
has_fulltext_pdf=True, doi__startswith="10.1016"
|
|
).order_by("id")
|
|
total = qs.count()
|
|
self.stdout.write(
|
|
f"候选(has_fulltext_pdf=True 且 DOI 以 10.1016 开头): {total}")
|
|
|
|
checked = preview = broken = only_pdf = deleted = 0
|
|
missing = unknown = 0
|
|
for paper in qs.iterator():
|
|
if limit and checked >= limit:
|
|
break
|
|
checked += 1
|
|
|
|
path = paper.init_paper_path("pdf")
|
|
if not os.path.exists(path):
|
|
missing += 1
|
|
continue
|
|
try:
|
|
with open(path, "rb") as f:
|
|
content = f.read()
|
|
except OSError:
|
|
unknown += 1
|
|
continue
|
|
|
|
kind, pages = _inspect_pdf(content)
|
|
if kind == "ok":
|
|
continue
|
|
if kind == "unknown":
|
|
unknown += 1
|
|
continue
|
|
|
|
# kind in ('preview', 'broken'): 都要纠正标记
|
|
do_delete = (kind == "broken") or del_preview
|
|
only_pdf_case = not paper.has_fulltext_xml
|
|
if kind == "preview":
|
|
preview += 1
|
|
tag = f"preview {pages}p"
|
|
else:
|
|
broken += 1
|
|
tag = "broken"
|
|
if only_pdf_case:
|
|
only_pdf += 1
|
|
self.stdout.write(
|
|
f"[{tag}]{' (only-pdf)' if only_pdf_case else ''}"
|
|
f"{' +rm' if do_delete else ''} {paper.doi} {path}")
|
|
if dry:
|
|
continue
|
|
|
|
paper.has_fulltext_pdf = False
|
|
update_fields = ["has_fulltext_pdf", "update_time"]
|
|
# 没有 XML 全文时, has_fulltext 之前只是被这张假/坏 PDF 置上的, 一并回退
|
|
if only_pdf_case:
|
|
paper.has_fulltext = False
|
|
update_fields.insert(0, "has_fulltext")
|
|
paper.save(update_fields=update_fields)
|
|
reason = "elsevier_pdf_preview_only" if kind == "preview" else "pdf_broken"
|
|
if reason not in (paper.fail_reason or ""):
|
|
paper.save_fail_reason(reason)
|
|
if do_delete:
|
|
try:
|
|
os.remove(path)
|
|
deleted += 1
|
|
except OSError:
|
|
pass
|
|
|
|
self.stdout.write(self.style.SUCCESS(
|
|
f"检查={checked} 预览页={preview} 坏文件={broken} "
|
|
f"(无XML全文一并回退has_fulltext={only_pdf}) 删除文件={deleted} "
|
|
f"文件缺失={missing} 未知/跳过={unknown}"
|
|
+ (" (dry-run, 未写库)" if dry else "")
|
|
))
|