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
|
import base64
import magic
import hashlib
import datetime
from typing import Optional
import requests
from requests.adapters import HTTPAdapter
from requests.packages.urllib3.util.retry import Retry # pylint: disable=import-error
import urlcanon
def clean_url(s: str) -> str:
s = s.strip()
parsed = urlcanon.parse_url(s)
if not parsed.port and parsed.colon_before_port:
parsed.colon_before_port = b''
return str(urlcanon.whatwg(parsed))
def gen_file_metadata(blob: bytes) -> dict:
"""
Takes a file blob (bytestream) and returns hashes and other metadata.
Returns a dict: size_bytes, md5hex, sha1hex, sha256hex, mimetype
"""
assert blob
mimetype = magic.Magic(mime=True).from_buffer(blob)
hashes = [
hashlib.sha1(),
hashlib.sha256(),
hashlib.md5(),
]
for h in hashes:
h.update(blob)
return dict(
size_bytes=len(blob),
sha1hex=hashes[0].hexdigest(),
sha256hex=hashes[1].hexdigest(),
md5hex=hashes[2].hexdigest(),
mimetype=mimetype,
)
def b32_hex(s: str) -> str:
"""
Converts a base32-encoded SHA-1 checksum into hex-encoded
base32 checksums are used by, eg, heritrix and in wayback CDX files
"""
s = s.strip().split()[0].lower()
if s.startswith("sha1:"):
s = s[5:]
if len(s) != 32:
if len(s) == 40:
return s
raise ValueError("not a base-32 encoded SHA-1 hash: {}".format(s))
return base64.b16encode(base64.b32decode(s.upper())).lower().decode('utf-8')
NORMAL_MIME = (
'application/pdf',
'application/postscript',
'text/html',
'text/xml',
'application/octet-stream',
)
def normalize_mime(raw: str) -> Optional[str]:
raw = raw.lower().strip()
for norm in NORMAL_MIME:
if raw.startswith(norm):
return norm
# Special cases
if raw.startswith('application/xml'):
return 'text/xml'
if raw.startswith('application/x-pdf'):
return 'application/pdf'
if raw in (
'.pdf',
):
return 'application/pdf'
if raw in (
'application/download',
'binary/octet-stream',
'unk',
'application/x-download',
'application/octetstream',
'application/force-download',
'application/unknown',
):
return 'application/octet-stream'
return None
def test_normalize_mime():
assert normalize_mime("asdf") is None
assert normalize_mime("application/pdf") == "application/pdf"
assert normalize_mime("application/pdf+journal") == "application/pdf"
assert normalize_mime("Application/PDF") == "application/pdf"
assert normalize_mime("application/p") is None
assert normalize_mime("application/xml+stuff") == "text/xml"
assert normalize_mime("application/x-pdf") == "application/pdf"
assert normalize_mime("application/x-html") is None
assert normalize_mime("unk") == "application/octet-stream"
assert normalize_mime("binary/octet-stream") == "application/octet-stream"
def parse_cdx_line(raw_cdx: str, normalize=True) -> Optional[dict]:
"""
This method always filters a few things out:
- non-HTTP requests, based on lack of status code (eg, whois)
"""
cdx = raw_cdx.split()
if len(cdx) < 11:
return None
surt = cdx[0]
dt = cdx[1]
url = cdx[2]
mime = normalize_mime(cdx[3])
http_status = cdx[4]
sha1b32 = cdx[5]
c_size = cdx[8]
offset = cdx[9]
warc = cdx[10]
if not (sha1b32.isalnum() and c_size.isdigit() and offset.isdigit()
and len(sha1b32) == 32 and dt.isdigit()):
return None
if '-' in (surt, dt, url, http_status, sha1b32, c_size, offset, warc):
return None
if mime is None or mime == '-':
mime = "application/octet-stream"
if normalize:
mime = normalize_mime(mime)
sha1hex = b32_hex(sha1b32)
return dict(
surt=surt,
url=url,
datetime=dt,
mimetype=mime,
http_status=int(http_status),
sha1b32=sha1b32,
sha1hex=sha1hex,
warc_csize=int(c_size),
warc_offset=int(offset),
warc_path=warc,
)
def parse_cdx_datetime(dt_str: str) -> Optional[datetime.datetime]:
if not dt_str:
return None
try:
return datetime.datetime.strptime(dt_str, "%Y%m%d%H%M%S")
except Exception:
return None
def test_parse_cdx_datetime() -> None:
assert parse_cdx_datetime("") == None
assert parse_cdx_datetime("asdf") == None
assert parse_cdx_datetime("19930203123045") != None
assert parse_cdx_datetime("20201028235103") == datetime.datetime(year=2020, month=10, day=28, hour=23, minute=51, second=3)
def datetime_to_cdx(dt: datetime.datetime) -> str:
return '%04d%02d%02d%02d%02d%02d' % (
dt.year, dt.month, dt.day,
dt.hour, dt.minute, dt.second,
)
def test_datetime_to_cdx() -> None:
assert "20201028235103" == datetime_to_cdx(datetime.datetime(year=2020, month=10, day=28, hour=23, minute=51, second=3))
def requests_retry_session(retries=10, backoff_factor=3,
status_forcelist=(500, 502, 504), session=None) -> requests.Session:
"""
From: https://www.peterbe.com/plog/best-practice-with-retries-with-requests
"""
session = session or requests.Session()
retry = Retry(
total=retries,
read=retries,
connect=retries,
backoff_factor=backoff_factor,
status_forcelist=status_forcelist,
)
adapter = HTTPAdapter(max_retries=retry)
session.mount('http://', adapter)
session.mount('https://', adapter)
return session
|
