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
|
#!/usr/bin/env python
# -*- coding: utf-8 -*-
# Copyright (c) 2016 Samsung Electronics Co., Ltd All Rights Reserved
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
##
# @author Pawel Wieczorek <p.wieczorek2@samsung.com>
import os
import urllib2
import time
import argparse
import bs4
discovered_urls = 'modified_urls'
dispatched_urls = 'dispatched_urls'
def crawl(url):
visited = set()
visited.add(url)
h = urllib2.build_opener()
h.addheaders = [('User-agent', 'Prerelease Crawler')]
try:
resp = h.open(url)
except urllib2.HTTPError as e:
print 'Failed to access {url}: {code} - {reason}'\
.format(url=url, code=e.code, reason=e.reason)
html = str(resp.read())
soup = bs4.BeautifulSoup(html, 'lxml')
links = soup('a')
discovered = set()
for link in links:
if link not in discovered and link not in visited:
if link.string.startswith('tizen-common'):
discovered.add(url + link['href'])
return discovered
def get_modified_paths(discovered, timestamp):
ret = set()
str_time = time.strftime('%a, %d %b %Y %H:%M:%S GMT', time.gmtime(time.time()))
if os.path.exists(dispatched_urls):
with open(timestamp, 'r') as f:
stamp = f.read();
else:
return discovered
with open(timestamp, 'w') as f:
f.write(str_time)
for url in discovered:
for md5sums_url in [url + 'images/arm-wayland/common-wayland-3parts-armv7l-odroidu3/MD5SUMS',\
url + 'images/x86_64-wayland/common-wayland-efi-x86_64/MD5SUMS',\
url + 'images/ia32-wayland/common-wayland-efi-i586/MD5SUMS']:
try:
u = urllib2.urlopen(urllib2.Request(md5sums_url, headers={"If-Modified-Since": stamp}))
except urllib2.HTTPError as e:
pass
else:
ret.add(url)
break
return ret
def parse_arguments():
"""parse_arguments() -> args
Parse any command-line options given returning both
the parsed options and arguments.
"""
parser = argparse.ArgumentParser(description="Crawler for download.tizen.org")
parser.add_argument("url", type=str,
help='URL of prerelease or snapshot to crawl.')
args = parser.parse_args()
return args
if '__main__' == __name__:
args = parse_arguments()
snapshots = crawl(args.url)
timestamp_file = 'timestamp'
if "snapshots" in args.url:
timestamp_file = 'timestamp_snapshot'
discovered = snapshots
else:
discovered = set()
for snapshot in snapshots:
discovered |= crawl(snapshot)
if os.path.exists(dispatched_urls):
with open(dispatched_urls, 'r') as f:
dispatched = set([url.rstrip() for url in f.readlines()])
# save discovered URLs for dispatching download requests
modified = get_modified_paths(discovered, timestamp_file)
with open(discovered_urls, 'w') as f:
f.write('\n'.join(modified))
# save all URLs for storing download history
dispatched |= modified
with open(dispatched_urls, 'w') as f:
f.write('\n'.join(dispatched))
|