blob: ec4e536b954e58e5428f11702d6aeec66a44cd25 (
plain)
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
|
Goal: re-bulk-ingest some older existing crawls which hung on errors like
`cdx-error` or `wayback-error`, indicating that ingest might actually succeed
on retry.
Sources:
- unpaywall (again)
- doi (ingest, changelog, etc)
- mag
- oai
## DOI
SELECT ingest_file_result.status, COUNT(*)
FROM ingest_request
LEFT JOIN ingest_file_result
ON ingest_file_result.ingest_type = ingest_request.ingest_type
AND ingest_file_result.base_url = ingest_request.base_url
WHERE
ingest_request.ingest_type = 'pdf'
AND ingest_request.link_source = 'doi'
GROUP BY status
ORDER BY COUNT DESC
LIMIT 25;
status | count
-------------------------------------+---------
no-pdf-link | 8304582
success | 3461708
no-capture | 1881269
redirect-loop | 1851541
gateway-timeout | 355820
cdx-error | 341848
terminal-bad-status | 328650
skip-url-blocklist | 220474
spn2-cdx-lookup-failure | 125521
link-loop | 109352
wayback-error | 101525
null-body | 73539
wrong-mimetype | 53151
spn-error | 13579
spn2-error | 6848
spn2-error:job-failed | 4381
spn-remote-error | 4180
other-mimetype | 2305
petabox-error | 904
timeout | 710
spn2-error:soft-time-limit-exceeded | 557
spn2-error:proxy-error | 437
spn2-error:browser-running-error | 273
invalid-host-resolution | 233
pending | 116
(25 rows)
Bulk:
COPY (
SELECT row_to_json(ingest_request.*)
FROM ingest_request
LEFT JOIN ingest_file_result
ON ingest_file_result.ingest_type = ingest_request.ingest_type
AND ingest_file_result.base_url = ingest_request.base_url
WHERE
ingest_request.ingest_type = 'pdf'
AND ingest_request.link_source = 'doi'
AND (
ingest_file_result.status = 'cdx-error' OR
ingest_file_result.status = 'wayback-error'
)
) TO '/grande/snapshots/ingest_doi_errors_2020-09-03.rows.json';
=> 443421
./scripts/ingestrequest_row2json.py /grande/snapshots/ingest_doi_errors_2020-09-03.rows.json | pv -l | shuf > /grande/snapshots/ingest_doi_errors_2020-09-03.requests.json
cat /grande/snapshots/ingest_doi_errors_2020-09-03.requests.json | rg -v "\\\\" | jq . -c | kafkacat -P -b wbgrp-svc263.us.archive.org -t sandcrawler-prod.ingest-file-requests-bulk -p -1
=> done
Additional 27,779 success status? Hard to tell because lots of other ingest
running in parallel.
Live:
COPY (
SELECT row_to_json(ingest_request.*)
FROM ingest_request
LEFT JOIN ingest_file_result
ON ingest_file_result.ingest_type = ingest_request.ingest_type
AND ingest_file_result.base_url = ingest_request.base_url
WHERE
ingest_request.ingest_type = 'pdf'
AND ingest_request.link_source = 'doi'
AND (
ingest_file_result.status = 'spn-error' OR
ingest_file_result.status = 'spn2-cdx-lookup-failure' OR
ingest_file_result.status = 'spn2-error:job-failed' OR
ingest_file_result.status = 'spn2-error:proxy-error'
)
) TO '/grande/snapshots/ingest_doi_spn_errors_2020-09-03.rows.json';
=> 143984
./scripts/ingestrequest_row2json.py /grande/snapshots/ingest_doi_spn_errors_2020-09-03.rows.json | pv -l | shuf > /grande/snapshots/ingest_doi_errors_2020-09-03.requests.json
cat /grande/snapshots/ingest_doi_spn_errors_2020-09-03.requests.json | rg -v "\\\\" | jq . -c | kafkacat -P -b wbgrp-svc263.us.archive.org -t sandcrawler-prod.ingest-file-requests -p -1
## Unpaywall (again)
Bulk:
COPY (
SELECT row_to_json(ingest_request.*)
FROM ingest_request
LEFT JOIN ingest_file_result
ON ingest_file_result.ingest_type = ingest_request.ingest_type
AND ingest_file_result.base_url = ingest_request.base_url
WHERE
ingest_request.ingest_type = 'pdf'
AND ingest_request.link_source = 'unpaywall'
AND (
ingest_file_result.status = 'cdx-error' OR
ingest_file_result.status = 'wayback-error'
)
) TO '/grande/snapshots/ingest_unpaywall_errors_2020-09-03.rows.json';
=> 43912
./scripts/ingestrequest_row2json.py /grande/snapshots/ingest_unpaywall_errors_2020-09-03.rows.json | pv -l | shuf > /grande/snapshots/ingest_unpaywall_errors_2020-09-03.requests.json
cat /grande/snapshots/ingest_unpaywall_errors_2020-09-03.requests.json | rg -v "\\\\" | jq . -c | kafkacat -P -b wbgrp-svc263.us.archive.org -t sandcrawler-prod.ingest-file-requests-bulk -p -1
=> done
## MAG
COPY (
SELECT row_to_json(ingest_request.*)
FROM ingest_request
LEFT JOIN ingest_file_result
ON ingest_file_result.ingest_type = ingest_request.ingest_type
AND ingest_file_result.base_url = ingest_request.base_url
WHERE
ingest_request.ingest_type = 'pdf'
AND ingest_request.link_source = 'mag'
AND (
ingest_file_result.status = 'cdx-error' OR
ingest_file_result.status = 'wayback-error'
)
) TO '/grande/snapshots/ingest_mag_errors_2020-09-03.rows.json';
=> 188175
./scripts/ingestrequest_row2json.py /grande/snapshots/ingest_mag_errors_2020-09-03.rows.json | pv -l | shuf > /grande/snapshots/ingest_mag_errors_2020-09-03.requests.json
cat /grande/snapshots/ingest_mag_errors_2020-09-03.requests.json | rg -v "\\\\" | jq . -c | kafkacat -P -b wbgrp-svc263.us.archive.org -t sandcrawler-prod.ingest-file-requests-bulk -p -1
=> done
## OAI-PMH
COPY (
SELECT row_to_json(ingest_request.*)
FROM ingest_request
LEFT JOIN ingest_file_result
ON ingest_file_result.ingest_type = ingest_request.ingest_type
AND ingest_file_result.base_url = ingest_request.base_url
WHERE
ingest_request.ingest_type = 'pdf'
AND ingest_request.link_source = 'oai'
AND (
ingest_file_result.status = 'cdx-error' OR
ingest_file_result.status = 'wayback-error'
)
) TO '/grande/snapshots/ingest_oai_errors_2020-09-03.rows.json';
=> 851056
./scripts/ingestrequest_row2json.py /grande/snapshots/ingest_oai_errors_2020-09-03.rows.json | pv -l | shuf > /grande/snapshots/ingest_oai_errors_2020-09-03.requests.json
cat /grande/snapshots/ingest_oai_errors_2020-09-03.requests.json | rg -v "\\\\" | jq . -c | kafkacat -P -b wbgrp-svc263.us.archive.org -t sandcrawler-prod.ingest-file-requests-bulk -p -1
=> done
---------
COPY (
SELECT row_to_json(ingest_request.*)
FROM ingest_request
LEFT JOIN ingest_file_result
ON ingest_file_result.ingest_type = ingest_request.ingest_type
AND ingest_file_result.base_url = ingest_request.base_url
WHERE
ingest_request.ingest_type = 'pdf'
AND ingest_request.link_source = 'unpaywall'
AND date(ingest_request.created) > '2020-04-01'
AND ingest_file_result.status = 'no-capture'
AND ingest_request.base_url NOT LIKE '%journals.sagepub.com%'
AND ingest_request.base_url NOT LIKE '%pubs.acs.org%'
AND ingest_request.base_url NOT LIKE '%ahajournals.org%'
AND ingest_request.base_url NOT LIKE '%www.journal.csj.jp%'
AND ingest_request.base_url NOT LIKE '%aip.scitation.org%'
AND ingest_request.base_url NOT LIKE '%academic.oup.com%'
AND ingest_request.base_url NOT LIKE '%tandfonline.com%'
) TO '/grande/snapshots/unpaywall_nocapture_2020-05-04.rows.json';
|
