forked from ArchiveTeam/NewsGrabber-Warrior
/
pipeline.py
328 lines (281 loc) · 10.9 KB
/
pipeline.py
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
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
# encoding=utf8
from distutils.version import StrictVersion
import datetime
import hashlib
import os
import random
import shutil
import socket
import subprocess
import sys
import time
import re
import urllib
from subprocess import call
sys.path.insert(0, os.getcwd())
import warcio
from warcio.archiveiterator import ArchiveIterator
from warcio.warcwriter import WARCWriter
assert hasattr(warcio, 'ATWARCIO'), 'warcio was not imported correctly. Location: ' + warcio.__file__
try:
import requests
except ImportError:
print('Please install or update the requests module.')
sys.exit(1)
import seesaw
from seesaw.config import realize, NumberConfigValue
from seesaw.externalprocess import WgetDownload, ExternalProcess
from seesaw.item import ItemInterpolation, ItemValue
from seesaw.pipeline import Pipeline
from seesaw.project import Project
from seesaw.task import SimpleTask, SetItemKey, LimitConcurrent
from seesaw.tracker import PrepareStatsForTracker, GetItemFromTracker, \
UploadWithTracker, SendDoneToTracker
from seesaw.util import find_executable
# check the seesaw version
if StrictVersion(seesaw.__version__) < StrictVersion("0.8.5"):
raise Exception("This pipeline needs seesaw version 0.8.5 or higher.")
###########################################################################
# Find a useful Wpull executable.
#
# WPULL_EXE will be set to the first path that
# 1. does not crash with --version, and
# 2. prints the required version string
WPULL_EXE = find_executable(
"Wpull",
re.compile(r"\b1\.2\.3\b"),
[
"./wpull",
"/usr/local/bin/wpull",
os.path.expanduser("~/.local/share/wpull-1.2.3/wpull"),
os.path.expanduser("~/.local/bin/wpull"),
"/usr/bin/wpull",
"/usr/local/lib/python3.7/site-packages/wpull",
"./wpull_bootstrap",
]
)
YOUTUBE_DL_EXE = find_executable(
"youtube-dl",
None, # No version requirements
[
"./youtube-dl",
"/usr/local/bin/youtube-dl",
"/usr/bin/youtube-dl",
"youtube-dl",
],
'--version',
)
PYTHON3_EXE = find_executable(
"Python",
re.compile(r"^Python 3\."),
[
"python",
"python3",
]
)
if not WPULL_EXE:
raise Exception("No usable Wpull found.")
if not YOUTUBE_DL_EXE:
raise Exception("No usable youtube-dl found.")
###########################################################################
# The version number of this pipeline definition.
#
# Update this each time you make a non-cosmetic change.
# It will be added to the WARC files and reported to the tracker.
VERSION = "20190702.01"
TRACKER_ID = 'newsgrabber'
TRACKER_HOST = 'tracker.archiveteam.org'
###########################################################################
# This section defines project-specific tasks.
#
# Simple tasks (tasks that do not need any concurrency) are based on the
# SimpleTask class and have a process(item) method that is called for
# each item.
class CheckIP(SimpleTask):
def __init__(self):
SimpleTask.__init__(self, "CheckIP")
self._counter = 0
def process(self, item):
# NEW for 2014! Check if we are behind firewall/proxy
if self._counter <= 0:
item.log_output('Checking IP address.')
ip_set = set()
ip_set.add(socket.gethostbyname('twitter.com'))
ip_set.add(socket.gethostbyname('facebook.com'))
ip_set.add(socket.gethostbyname('youtube.com'))
ip_set.add(socket.gethostbyname('microsoft.com'))
ip_set.add(socket.gethostbyname('icanhas.cheezburger.com'))
ip_set.add(socket.gethostbyname('archiveteam.org'))
if len(ip_set) != 6:
item.log_output('Got IP addresses: {0}'.format(ip_set))
item.log_output(
'Are you behind a firewall/proxy? That is a big no-no!')
raise Exception(
'Are you behind a firewall/proxy? That is a big no-no!')
# Check only occasionally
if self._counter <= 0:
self._counter = 10
else:
self._counter -= 1
class PrepareDirectories(SimpleTask):
def __init__(self, warc_prefix):
SimpleTask.__init__(self, "PrepareDirectories")
self.warc_prefix = warc_prefix
def process(self, item):
item_name = item["item_name"]
escaped_item_name = item_name.replace(':', '_').replace('/', '_').replace('~', '_')
dirname = "/".join((item["data_dir"], escaped_item_name))
if os.path.isdir(dirname):
shutil.rmtree(dirname)
os.makedirs(dirname)
item["item_dir"] = dirname
item["warc_file_base"] = "%s-%s-%s" % (self.warc_prefix, escaped_item_name,
time.strftime("%Y%m%d-%H%M%S"))
open("%(item_dir)s/%(warc_file_base)s.warc.gz" % item, "w").close()
class MoveFiles(SimpleTask):
def __init__(self):
SimpleTask.__init__(self, "MoveFiles")
def process(self, item):
os.rename("%(item_dir)s/%(warc_file_base)s-deduplicated.warc.gz" % item,
"%(data_dir)s/%(warc_file_base)s-deduplicated.warc.gz" % item)
shutil.rmtree("%(item_dir)s" % item)
class DeduplicateWarcExtProc(SimpleTask):
def __init__(self):
SimpleTask.__init__(self, "DeduplicateWarcExtProc")
def process(self, item):
sourcewarc = "%(item_dir)s/%(warc_file_base)s.warc.gz" % item
destwarc = "%(item_dir)s/%(warc_file_base)s-deduplicated.warc.gz" % item
call(["python", "-u", "dedupe.py", sourcewarc, destwarc])
def get_hash(filename):
with open(filename, 'rb') as in_file:
return hashlib.sha256(in_file.read()).hexdigest()
CWD = os.getcwd()
PIPELINE_SHA256 = get_hash(os.path.join(CWD, 'pipeline.py'))
WARRIOR_INSTALL_SHA256 = get_hash(os.path.join(CWD, 'warrior-install.sh'))
WPULL_BOOTSTRAP_SHA256 = get_hash(os.path.join(CWD, 'wpull_bootstrap'))
def stats_id_function(item):
d = {
'pipeline_hash': PIPELINE_SHA256,
'warrior_install_hash': WARRIOR_INSTALL_SHA256,
'wpull_bootstrap_hash': WPULL_BOOTSTRAP_SHA256,
'python_version': sys.version,
}
return d
class WgetArgs(object):
def realize(self, item):
item_name = item['item_name']
item_type, item_value = item_name.split(':', 1)
item['item_type'] = item_type
item['item_value'] = item_value
wpull_args = [
WPULL_EXE,
'-nv',
'-U', 'ArchiveTeam; Googlebot/2.1',
'--no-check-certificate',
'--no-robots',
'--dns-timeout', '20',
'--connect-timeout', '20',
'--read-timeout', '900',
'--session-timeout', '1800',
'--tries', '5',
'--waitretry', '5',
'--max-redirect', '20',
'--output-file', ItemInterpolation("%(item_dir)s/wpull.log"),
'--database', ItemInterpolation("%(item_dir)s/wpull.db"),
'--delete-after',
'--page-requisites',
'--no-parent',
'--concurrent', '5',
'--warc-file', ItemInterpolation("%(item_dir)s/%(warc_file_base)s"),
'--level', '0',
'--page-requisites-level', '5',
'--span-hosts-allow', 'page-requisites',
'--warc-header', 'pipeline-py-sha256: ' + PIPELINE_SHA256,
'--warc-header', 'warrior-install-sh-sha256: ' + WARRIOR_INSTALL_SHA256,
'--warc-header', 'operator: Archive Team',
'--warc-header', 'newsgrabber-dld-script-version: ' + VERSION,
'--warc-header', ItemInterpolation('ftp-item: %(item_name)s'),
'--reject-regex', r'(^https?://launcher\.spot\.im/spot/(www\.spot\.im/launcher/|launcher\.spot\.im/|modules/launcher/){3,}bundle\.js)|(https?://static\.xx\.fbcdn\.net/rsrc\.php/)',
'--proxy-server-address', '127.0.0.1'
]
if '-videos' in item_value:
wpull_args.append('--youtube-dl')
wpull_args.append('--youtube-dl-exe')
wpull_args.append(YOUTUBE_DL_EXE)
list_url = 'http://master.newsbuddy.net/' + item_value
list_data = requests.get(list_url)
#wpull_args.append(list_url)
if list_data.status_code == 200:
for url in list_data.text.splitlines():
url = url.strip()
wpull_args.append(url)
if 'bind_address' in globals():
wpull_args.extend(['--bind-address', globals()['bind_address']])
print('')
print('*** Wpull will bind address at {0} ***'.format(
globals()['bind_address']))
print('')
return realize(wpull_args, item)
###########################################################################
# Initialize the project.
#
# This will be shown in the warrior management panel. The logo should not
# be too big. The deadline is optional.
project = Project(
title="newsgrabber",
project_html="""
<img class="project-logo" alt="Project logo" src="http://archiveteam.org/images/thumb/f/f3/Archive_team.png/235px-Archive_team.png" height="50px" title=""/>
<h2>archiveteam.org <span class="links"><a href="http://archiveteam.org/">Website</a> · <a href="http://tracker.archiveteam.org/newsgrabber/">Leaderboard</a></span></h2>
<p>Archiving all the news!</p>
"""
)
pipeline = Pipeline(
CheckIP(),
GetItemFromTracker("http://%s/%s" % (TRACKER_HOST, TRACKER_ID), downloader,
VERSION),
PrepareDirectories(warc_prefix="newsgrabber"),
WgetDownload(
WgetArgs(),
max_tries=2,
accept_on_exit_code=[0, 4, 8]
),
LimitConcurrent(
NumberConfigValue(min=1, max=20, default="1",
name="shared:dedupe_threads", title="Deduplicate threads",
description="The maximum number of concurrent dedupes."),
DeduplicateWarcExtProc(),
),
PrepareStatsForTracker(
defaults={"downloader": downloader, "version": VERSION},
file_groups={
"data": [
ItemInterpolation("%(item_dir)s/%(warc_file_base)s-deduplicated.warc.gz")
]
},
id_function=stats_id_function,
),
MoveFiles(),
LimitConcurrent(
NumberConfigValue(min=1, max=4, default="1",
name="shared:rsync_threads", title="Rsync threads",
description="The maximum number of concurrent uploads."),
UploadWithTracker(
"http://%s/%s" % (TRACKER_HOST, TRACKER_ID),
downloader=downloader,
version=VERSION,
files=[
ItemInterpolation("%(data_dir)s/%(warc_file_base)s-deduplicated.warc.gz")
],
rsync_target_source_path=ItemInterpolation("%(data_dir)s/"),
rsync_extra_args=[
"--recursive",
"--partial",
"--partial-dir", ".rsync-tmp",
]
),
),
SendDoneToTracker(
tracker_url="http://%s/%s" % (TRACKER_HOST, TRACKER_ID),
stats=ItemValue("stats")
)
)