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
|
# Copyright (c) 2018 crocoite contributors
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in
# all copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
# THE SOFTWARE.
"""
Misc tools
"""
import shutil, sys, os, logging, argparse, json
from io import BytesIO
from warcio.archiveiterator import ArchiveIterator
from warcio.warcwriter import WARCWriter
from .util import packageUrl, getSoftwareInfo
def mergeWarc (files, output):
unique = 0
revisit = 0
payloadMap = {}
writer = WARCWriter (output, gzip=True)
# Add an additional warcinfo record, describing the transformations. This
# is not ideal, since
# “A ‘warcinfo’ record describes the records that
# follow it […] until next ‘warcinfo’”
# -- https://iipc.github.io/warc-specifications/specifications/warc-format/warc-1.1/#warcinfo
# A warcinfo record is expected at the beginning of every file. But it
# might have written by a different software, so we don’t want to
# strip/replace that information, but supplement it.
warcinfo = {
'software': getSoftwareInfo (),
'tool': 'crocoite-merge', # not the name of the cli tool
'parameters': {'inputs': files},
}
payload = BytesIO (json.dumps (warcinfo, indent=2).encode ('utf-8'))
record = writer.create_warc_record (packageUrl ('warcinfo'), 'warcinfo',
payload=payload,
warc_headers_dict={'Content-Type': 'text/plain; encoding=utf-8'})
writer.write_record (record)
for l in files:
with open (l, 'rb') as fd:
for record in ArchiveIterator (fd):
if record.rec_type in {'resource', 'response'}:
headers = record.rec_headers
rid = headers.get_header('WARC-Record-ID')
csum = headers.get_header('WARC-Payload-Digest')
dup = payloadMap.get (csum, None)
if dup is None:
payloadMap[csum] = {'uri': headers.get_header('WARC-Target-URI'),
'id': rid, 'date': headers.get_header('WARC-Date')}
unique += 1
else:
logging.debug ('Record {} is duplicate of {}'.format (rid, dup['id']))
# Payload may be identical, but HTTP headers are
# (probably) not. Include them.
record = writer.create_revisit_record (
headers.get_header('WARC-Target-URI'), digest=csum,
refers_to_uri=dup['uri'], refers_to_date=dup['date'],
http_headers=record.http_headers)
record.rec_headers.add_header ('WARC-Truncated', 'length')
record.rec_headers.add_header ('WARC-Refers-To', dup['id'])
revisit += 1
else:
unique += 1
writer.write_record (record)
logging.info ('Wrote {} unique records, {} revisits'.format (unique, revisit))
def mergeWarcCli():
parser = argparse.ArgumentParser(description='Merge WARCs, reads filenames from stdin.')
parser.add_argument('--verbose', '-v', action='store_true')
parser.add_argument('output', type=argparse.FileType ('wb'), help='Output WARC')
args = parser.parse_args()
loglevel = logging.DEBUG if args.verbose else logging.INFO
logging.basicConfig (level=loglevel)
mergeWarc([l.strip() for l in sys.stdin], args.output)
def extractScreenshot ():
"""
Extract page screenshots from a WARC generated by crocoite into files
"""
parser = argparse.ArgumentParser(description='Extract screenshots.')
parser.add_argument('-f', '--force', action='store_true', help='Overwrite existing files')
parser.add_argument('input', type=argparse.FileType ('rb'), help='Input WARC')
parser.add_argument('prefix', help='Output file prefix')
args = parser.parse_args()
with args.input:
for record in ArchiveIterator (args.input):
headers = record.rec_headers
if record.rec_type != 'conversion' or \
headers['Content-Type'] != 'image/png' or \
'X-Crocoite-Screenshot-Y-Offset' not in headers:
continue
urlSanitized = headers.get_header('WARC-Target-URI').replace ('/', '_')
xoff = 0
yoff = int (headers.get_header ('X-Crocoite-Screenshot-Y-Offset'))
outpath = '{}-{}-{}-{}.png'.format (args.prefix, urlSanitized, xoff, yoff)
if args.force or not os.path.exists (outpath):
with open (outpath, 'wb') as out:
shutil.copyfileobj (record.raw_stream, out)
else:
print ('not overwriting {}'.format (outpath))
|
