docs: errors.md com 69 itens e comportamento de cada falha

Terceira rodada contra a origem recuperou 6 imagens de preservação (6433,
6520, 6656, 7529, 7939, 8396). Os 69 restantes estão classificados pelo que a
origem faz: 500 na sequência da preservação, travamento cortado em ~300 s ou
~30 s, ou falha de rede. A forma canônica por nome também devolve 500, e
Range não ajuda porque o servidor não envia nem os cabeçalhos.

Contagens atualizadas no README, MANIFEST e TODO: 12.991 itens com
preservação e 41.450 objetos no ledger.
This commit is contained in:
rodado
2026-09-13 21:59:58 +02:00
parent 711288405e
commit aeb8b3b179
10 changed files with 339 additions and 180 deletions
+26
View File
@@ -0,0 +1,26 @@
#!/bin/bash
# Baixa por curl, em serie e com timeout longo, os itens de errors.md.
# Descoberta de 13/09: a origem serve esses bitstreams a ~11 KB/s; o que
# parecia "erro de rede" no navegador era estouro de tempo. Alguns voltam 403
# (bloqueio Cloudflare a cliente sem sessao) -- esses ficam para a aba.
UA="Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/140.0.0.0 Safari/537.36"
B=https://brasilianafotografica.bn.gov.br/brasiliana/bitstream/20.500.12156.1
ok=0; b403=0; b500=0; outro=0
while IFS='|' read -r id seq arq; do
[ -z "$id" ] && continue
nome="BRAS__20.500.12156.1_${id}__$(python3 -c "import urllib.parse,sys;print(urllib.parse.unquote(sys.argv[1]))" "$arq")"
[ -f "$HOME/Downloads/$nome" ] && continue
code=$(curl -sL --max-time 600 -o "$HOME/Downloads/.parcial" -w "%{http_code}" \
-H "User-Agent: $UA" -H "Accept: image/*,*/*;q=0.8" \
-H "Referer: https://brasilianafotografica.bn.gov.br/" --compressed "$B/$id/$seq/$arq")
sz=$(stat -f %z "$HOME/Downloads/.parcial" 2>/dev/null || echo 0)
if [ "$code" = "200" ] && [ "$sz" -gt 1024 ]; then
mv "$HOME/Downloads/.parcial" "$HOME/Downloads/$nome"; ok=$((ok+1)); echo "ok $id $((sz/1024)) KB"
else
rm -f "$HOME/Downloads/.parcial"
case "$code" in 403) b403=$((b403+1));; 500) b500=$((b500+1));; *) outro=$((outro+1));; esac
echo "erro $id http=$code ${sz}B"
fi
sleep 2
done < faltantes-v3.compacto.curl
echo "FIM: ok=$ok 403=$b403 500=$b500 outros=$outro"
+61 -66
View File
@@ -1,74 +1,69 @@
20.500.12156.1/6545
20.500.12156.1/6555
20.500.12156.1/6568
20.500.12156.1/6570
20.500.12156.1/6669
20.500.12156.1/6670
20.500.12156.1/6674
20.500.12156.1/7034
20.500.12156.1/7317
20.500.12156.1/7326
20.500.12156.1/7344
20.500.12156.1/7353
20.500.12156.1/7355
20.500.12156.1/7358
20.500.12156.1/7379
20.500.12156.1/7386
20.500.12156.1/7393
20.500.12156.1/7438
20.500.12156.1/7440
20.500.12156.1/7457
20.500.12156.1/7461
20.500.12156.1/7463
20.500.12156.1/7475
20.500.12156.1/8785
20.500.12156.1/7515
20.500.12156.1/7516
20.500.12156.1/7517
20.500.12156.1/7523
20.500.12156.1/7743
20.500.12156.1/7744
20.500.12156.1/7766
20.500.12156.1/7802
20.500.12156.1/7814
20.500.12156.1/7817
20.500.12156.1/7848
20.500.12156.1/7852
20.500.12156.1/7861
20.500.12156.1/7875
20.500.12156.1/8075
20.500.12156.1/7817
20.500.12156.1/7326
20.500.12156.1/7386
20.500.12156.1/8912
20.500.12156.1/8262
20.500.12156.1/8128
20.500.12156.1/8133
20.500.12156.1/8141
20.500.12156.1/8145
20.500.12156.1/8161
20.500.12156.1/8182
20.500.12156.1/8187
20.500.12156.1/8249
20.500.12156.1/8254
20.500.12156.1/8262
20.500.12156.1/8267
20.500.12156.1/8268
20.500.12156.1/8271
20.500.12156.1/8275
20.500.12156.1/8277
20.500.12156.1/8286
20.500.12156.1/8313
20.500.12156.1/8316
20.500.12156.1/8374
20.500.12156.1/8739
20.500.12156.1/8761
20.500.12156.1/8762
20.500.12156.1/7457
20.500.12156.1/8804
20.500.12156.1/8774
20.500.12156.1/7516
20.500.12156.1/7379
20.500.12156.1/7344
20.500.12156.1/7743
20.500.12156.1/8313
20.500.12156.1/8374
20.500.12156.1/6545
20.500.12156.1/8187
20.500.12156.1/8133
20.500.12156.1/8277
20.500.12156.1/7355
20.500.12156.1/7848
20.500.12156.1/8267
20.500.12156.1/6520
20.500.12156.1/8275
20.500.12156.1/7529
20.500.12156.1/6570
20.500.12156.1/8182
20.500.12156.1/7034
20.500.12156.1/7744
20.500.12156.1/6568
20.500.12156.1/8872
20.500.12156.1/8396
20.500.12156.1/7317
20.500.12156.1/7517
20.500.12156.1/8268
20.500.12156.1/8141
20.500.12156.1/6433
20.500.12156.1/7438
20.500.12156.1/6670
20.500.12156.1/7440
20.500.12156.1/7939
20.500.12156.1/8825
20.500.12156.1/7353
20.500.12156.1/7393
20.500.12156.1/7515
20.500.12156.1/7814
20.500.12156.1/7358
20.500.12156.1/7463
20.500.12156.1/7852
20.500.12156.1/8796
20.500.12156.1/8145
20.500.12156.1/8254
20.500.12156.1/7766
20.500.12156.1/6674
20.500.12156.1/7461
20.500.12156.1/8128
20.500.12156.1/8316
20.500.12156.1/8249
20.500.12156.1/6555
20.500.12156.1/6669
20.500.12156.1/7802
20.500.12156.1/8739
20.500.12156.1/7861
20.500.12156.1/9148
20.500.12156.1/6656
20.500.12156.1/8781
20.500.12156.1/8271
20.500.12156.1/8286
20.500.12156.1/8785
20.500.12156.1/8796
20.500.12156.1/8804
20.500.12156.1/8825
20.500.12156.1/8872
20.500.12156.1/8912
20.500.12156.1/9148
+74
View File
@@ -0,0 +1,74 @@
6433|1|0072430cx006-05t.jpg
6520|1|007_IMG_1008t.jpg
6545|1|CC-05-01-015-3.jpg
6555|1|BR_RJANRIO_Q0_ADM_CPA_VFE_FOT_0009_m0003de0003.jpg
6568|1|BR_RJANRIO_Q0_ADM_CPA_VFE_FOT_0019_m0001de0001.jpg
6570|1|BR_RJANRIO_Q0_ADM_CPA_VFE_FOT_0024_m0001de0001.jpg
6656|2|imagem.jpg
6669|1|BP-06-TP-01-012.jpg
6670|1|BP-06-TP-01-015.jpg
6674|1|BP-06-TP-01-022.jpg
7034|1|007A6P3F08-004.jpg
7317|4|Alb%200294%20069ct.jpg
7326|4|Alb%200294%20037ct.jpg
7344|4|Alb%200294%20093ct.jpg
7353|4|Alb%200294%20097ct.jpg
7355|4|Alb%200259%20073%20ct.jpg
7358|1|BR_RJANRIO_OG_0_FOT_0001_021.jpg
7379|1|BR_RJANRIO_OG_0_FOT_0001_057.jpg
7386|1|BR_RJANRIO_OG_0_FOT_0001_067.jpg
7393|1|BR_RJANRIO_OG_0_FOT_0001_089.jpg
7438|1|BR_RJANRIO_OG_0_FOT_0001_085.jpg
7440|1|BR_RJANRIO_OG_0_FOT_0001_087.jpg
7457|4|Alb%200294%20127ct.jpg
7461|4|Alb%200259%20081ct.jpg
7463|4|Alb%200294%20106ct.jpg
7475|4|Alb%200259%20096ct.jpg
7515|4|Alb%200259%20145ct.jpg
7516|4|Alb%200259%20139ct.jpg
7517|3|Album%200035%20297%20CT.jpg
7529|5|Alb%200259%20130ct.jpg
7743|1|001ALA011011.jpg
7744|1|001ALA011012.jpg
7766|1|001ATK012010.jpg
7802|1|Alb%200036%20037%20CT%20ok.jpg
7814|1|Alb%200036%20081%20CT%20ok.jpg
7817|1|Alb%200036%20087%20CT%20ok.jpg
7848|1|Alb%200036%20013%20CT%20ok.jpg
7852|1|Album%200035%20105%20CT.jpg
7861|1|Album%200035%20088%20CT.jpg
7875|1|Album%200035%20078%20CT.jpg
7939|2|imagem.jpg
8075|1|Alb%200038%20009%20CT%20ok.jpg
8128|1|014AM006009.jpg
8133|1|014AM010003.jpg
8141|1|014AM010014.jpg
8145|1|014AM012006.jpg
8161|1|014AM012058.jpg
8182|1|014AM019007.jpg
8187|1|014AM019013.jpg
8249|1|014AM002012.jpg
8254|1|014AM002019.jpg
8262|1|014AM003015.jpg
8267|1|014AM004003.jpg
8268|1|014AM005003.jpg
8271|1|014AM005005.jpg
8275|1|014AM005014.jpg
8277|1|014AM005020.jpg
8286|1|014AM006002.jpg
8313|1|001AAN005123.jpg
8316|1|001ACL019004.jpg
8374|1|002080NUS0309.jpg
8396|2|imagem.jpg
8739|1|007ALA102.jpg
8761|1|007ALA015.jpg
8762|1|007ALA016.jpg
8774|1|007ALA027.jpg
8781|1|007ALA033.jpg
8785|1|007ALA037.jpg
8796|1|007ALA047.jpg
8804|1|007ALA054.jpg
8825|1|007ALA073.jpg
8872|1|A05F03P02.jpg
8912|1|pixinguinha04.jpg
9148|1|007ALA091.jpg
+1
View File
@@ -0,0 +1 @@
02613de5023060e3,05911dc2ecc6cc15,0caab216058ff6d2,0d55d8aed6f5c6ab,0f3c9e36634481a6,0fab79100a789e1e,156a2fb4dbf31022,19b7926881196d2c,1d79f6322473b2d6,1dd9eb1b3225e4f5,245c2235080f8741,2adcc082cc2803f6,2f5796cbebe1630f,3170f17d024f1ecb,39d71b3d5698ce40,39f5e743c8e7c82f,3c1ebc546fe9515a,3f2d83f3343edece,406d157fa4a0dece,4653cb23d05ca80a,4dd6179c4aa5c6ad,52d64de29697520d,55804fed0b889e20,592a055b12dde540,5dd72d2b95a8a360,63c554533a29f9c7,646a2ca5f0e27755,64eb90a0f19f5c92,68237f8e1b3320a2,6b3dc2e4fab10c17,6e5fb5d70b0a2188,78b1c7c97264eccc,7ed78268ecd643d3,805597161ea720ca,857f49a66ef4790a,8761a8854c2f2d94,88e7134f34a1c980,8c27317041265193,9027d49c43062815,9048c399cbd2c9ea,93ecf64dfbd9dadd,9988377423792689,9dcbda0f1b62059a,9e3d84d8f527852a,a11dc33508dc2f4f,a5daf0bb81dced94,aba0616fc5ababd5,ac85ebad711a1e4e,ae7974f4b7cf7c5b,ae7a8b07fcae91f2,ae8d4c76a7b7a11a,aec60e35ea0d63d6,b270eb4a505cb651,ba496d1ac80b3566,baac480015239d09,bc5afbc7c40ae40c,bd2d3f1c856e5f6a,be0f499b3a79a4f5,cb58995e649b0463,cf9282f500f4b123,cfdf15b521f5f74b,d1d9d4e2a42a4bda,d8749360ea01dc8b,dc485d5aa7327ef8,dd14376bddd21672,de1bbbf57c2cf42b,deef3f833f25f707,ea827ea65df1eb2e,f154da9ee174cf8c,f1862c0b01c18b00,f739113fc8912219,faa22557ced734f0,ff3501b9e831ae94
+1
View File
@@ -0,0 +1 @@
6545|1|CC-05-01-015-3.jpg;6555|1|BR_RJANRIO_Q0_ADM_CPA_VFE_FOT_0009_m0003de0003.jpg;6568|1|BR_RJANRIO_Q0_ADM_CPA_VFE_FOT_0019_m0001de0001.jpg;6570|1|BR_RJANRIO_Q0_ADM_CPA_VFE_FOT_0024_m0001de0001.jpg;6656|2|imagem.jpg;6669|1|BP-06-TP-01-012.jpg;6670|1|BP-06-TP-01-015.jpg;6674|1|BP-06-TP-01-022.jpg;7034|1|007A6P3F08-004.jpg;7317|4|Alb%200294%20069ct.jpg;7326|4|Alb%200294%20037ct.jpg;7344|4|Alb%200294%20093ct.jpg;7353|4|Alb%200294%20097ct.jpg;7355|4|Alb%200259%20073%20ct.jpg;7358|1|BR_RJANRIO_OG_0_FOT_0001_021.jpg;7379|1|BR_RJANRIO_OG_0_FOT_0001_057.jpg;7386|1|BR_RJANRIO_OG_0_FOT_0001_067.jpg;7393|1|BR_RJANRIO_OG_0_FOT_0001_089.jpg;7438|1|BR_RJANRIO_OG_0_FOT_0001_085.jpg;7440|1|BR_RJANRIO_OG_0_FOT_0001_087.jpg;7457|4|Alb%200294%20127ct.jpg;7461|4|Alb%200259%20081ct.jpg;7463|4|Alb%200294%20106ct.jpg;7475|4|Alb%200259%20096ct.jpg;7515|4|Alb%200259%20145ct.jpg;7516|4|Alb%200259%20139ct.jpg;7517|3|Album%200035%20297%20CT.jpg;7529|5|Alb%200259%20130ct.jpg;7743|1|001ALA011011.jpg;7744|1|001ALA011012.jpg;7766|1|001ATK012010.jpg;7802|1|Alb%200036%20037%20CT%20ok.jpg;7814|1|Alb%200036%20081%20CT%20ok.jpg;7817|1|Alb%200036%20087%20CT%20ok.jpg;7848|1|Alb%200036%20013%20CT%20ok.jpg;7852|1|Album%200035%20105%20CT.jpg;7861|1|Album%200035%20088%20CT.jpg;7875|1|Album%200035%20078%20CT.jpg;7939|2|imagem.jpg;8075|1|Alb%200038%20009%20CT%20ok.jpg;8128|1|014AM006009.jpg;8133|1|014AM010003.jpg;8141|1|014AM010014.jpg;8145|1|014AM012006.jpg;8161|1|014AM012058.jpg;8182|1|014AM019007.jpg;8187|1|014AM019013.jpg;8249|1|014AM002012.jpg;8254|1|014AM002019.jpg;8262|1|014AM003015.jpg;8267|1|014AM004003.jpg;8268|1|014AM005003.jpg;8271|1|014AM005005.jpg;8275|1|014AM005014.jpg;8277|1|014AM005020.jpg;8286|1|014AM006002.jpg;8313|1|001AAN005123.jpg;8316|1|001ACL019004.jpg;8374|1|002080NUS0309.jpg;8396|2|imagem.jpg;8739|1|007ALA102.jpg;8761|1|007ALA015.jpg;8762|1|007ALA016.jpg;8774|1|007ALA027.jpg;8781|1|007ALA033.jpg;8785|1|007ALA037.jpg;8796|1|007ALA047.jpg;8804|1|007ALA054.jpg;8825|1|007ALA073.jpg;8872|1|A05F03P02.jpg;8912|1|pixinguinha04.jpg;9148|1|007ALA091.jpg