-
Notifications
You must be signed in to change notification settings - Fork 1
/
tornado_spider.py
231 lines (193 loc) · 9.4 KB
/
tornado_spider.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
import argparse
import logging
import sys
import time
from lxml import objectify
from tornado.gen import coroutine
from tornado.httpclient import HTTPClient
from tornado.ioloop import IOLoop
from toro import JoinableQueue, BoundedSemaphore, Lock
from config import DOMAINS_TO_BE_SKIPPED, START_URL, \
IMPLEMENTATION_CLIENT, MAX_CONCURRENT_REQUESTS_PER_SERVER
from resource_issue_detector import detect_js_and_resource_issues
from tornado_client_page import TornadoClientPage
from util import print_pages_with_errors, print_pages_with_hardcoded_links, print_pages_to_file, extract_domain, \
extract_base_site, decode_to_unicode
from web_page import WebPage
logger = logging.getLogger(__name__)
logger.setLevel(logging.DEBUG)
logger.addHandler(logging.FileHandler('spider.log', mode='w'))
RESOURCES_STATE = dict()
universal_messages = []
def _get_client_page(*args):
if IMPLEMENTATION_CLIENT == 'tornado':
return TornadoClientPage(*args)
else:
return WebPage(args)
class TornadoSpider:
def __init__(self, start_url, sitemap_url=None, max_concurrent_connections=MAX_CONCURRENT_REQUESTS_PER_SERVER):
self.visited_urls = set()
self.intermediate_urls = set()
self.base_domain = extract_domain(start_url)
self.base_site = extract_base_site(start_url)
self.base_page = _get_client_page(start_url, None, start_url, self.base_domain, DOMAINS_TO_BE_SKIPPED)
self.non_visited_urls = {self.base_page}
self.added_count = 1
self.idle_ping = 0
self.start_idle_counter = False
self.sitemap_url = u'{}/sitemap.xml'.format(self.base_site) if not sitemap_url else sitemap_url
self.max_concurrent_connections = max_concurrent_connections
self.page_queue = JoinableQueue()
self.semaphore = BoundedSemaphore(self.max_concurrent_connections)
self.start = time.time()
self.skip_count = 0
@coroutine
def initiate_crawl(self):
self.non_visited_urls.add(self.base_page)
self.add_sitemap_urls(self.base_page)
self.page_queue.put(self.base_page)
self._crawl_web_page()
yield self.page_queue.join()
@coroutine
def _crawl_web_page(self):
while True:
if len(self.intermediate_urls) < 5 and self.start_idle_counter:
print("Unprocessed urls : ")
for page in self.intermediate_urls:
print(u'>>>>>> %s ' % page.encoded_url)
# print("Available Semaphore %s" % self.semaphore.counter)
yield self.semaphore.acquire()
# print("0.Issued Semaphore %s " % (self.semaphore.counter+1))
self._fetch_page(self.semaphore.counter + 1)
if len(self.intermediate_urls) < 5 and self.start_idle_counter:
print("Unprocessed urls : ")
for page in self.intermediate_urls:
print(u'>> %s ' % page.encoded_url)
self.wrap_up()
@coroutine
def _fetch_page(self, semaphore_count):
try:
page = yield self.page_queue.get()
if page in self.visited_urls or page in self.intermediate_urls:
return
if page.skip_page():
self.skip_count += 1
logger.debug("Skipped {} " % page.url)
return
logger.debug(
u"1.Sempahore in use> %s int.count %s for %s" % (semaphore_count, len(self.intermediate_urls),
page.encoded_url))
self.intermediate_urls.add(page)
page.process(self)
response = yield page.make_head_request()
get_response = yield page._process_head_response(response)
if get_response:
page.process_get_response(get_response)
print(
u"Total urls added : {} , Total urls visited : {} , Total urls in process : {} Skipped : {},"
u" semaphore used : {} " \
.format(self.added_count, len(self.visited_urls), len(self.intermediate_urls), self.skip_count,
semaphore_count))
logger.debug(
u"Total urls added : {} , Total urls visited : {} , Total urls in process : {} Skipped : {}, "
u"semaphore {}"
.format(self.added_count, len(self.visited_urls), len(self.intermediate_urls), self.skip_count,
self.semaphore.counter))
except Exception as ex:
logger.debug(ex)
finally:
self.page_queue.task_done()
self.semaphore.release()
logger.debug(
u"2.Sempahore returned>> %s available %s after %s" % (semaphore_count, self.semaphore.counter,
page.encoded_url))
def _filter_visited_links(self, page):
return page not in self.visited_urls and page not in self.intermediate_urls and page not in self.non_visited_urls
def add_sitemap_urls(self, parent_page):
logger.debug("Adding sitemap urls as well for processing")
http_client = HTTPClient()
try:
response = http_client.fetch(self.sitemap_url)
val = bytes(response.body)
root = objectify.fromstring(val)
for url_element in root.url:
page = _get_client_page(decode_to_unicode(url_element.loc.text), parent_page, self.base_site,
self.base_domain, DOMAINS_TO_BE_SKIPPED)
if page not in self.visited_urls and page not in self.non_visited_urls \
and page not in self.intermediate_urls:
print(u"Added {}".format(url_element.loc))
self.non_visited_urls.add(page)
self.added_count += 1
self.page_queue.put(page)
except Exception as e:
logger.error(u"Error adding sitemap urls from %s " % self.sitemap_url)
finally:
http_client.close()
def _get_unique_non_visited_links(self, page):
l = Lock()
l.acquire()
filtered_links = set(filter(self._filter_visited_links, page.links))
l.release()
return filtered_links
def process_web_page(self, web_page):
logger.debug(u"Called {} for {}".format('process_web_page', unicode(web_page.url).encode("utf-8")))
logger.debug(u"Removing %s " % web_page.url)
self.visited_urls.add(web_page)
self.non_visited_urls.discard(web_page)
self.intermediate_urls.discard(web_page)
unique_pages = self._get_unique_non_visited_links(web_page)
for page in unique_pages:
if page not in self.non_visited_urls:
self.non_visited_urls.add(page)
self.page_queue.put(page)
self.added_count += 1
logger.debug("Added link-url %s " % page.encoded_url)
self.start_idle_counter = True
def wrap_up(self):
self.print_stats()
IOLoop.instance().stop()
print('Done crawling in %d seconds, fetched %s URLs.' % (time.time() - self.start, len(self.visited_urls)))
def print_stats(self):
print_pages_with_errors(True, self.visited_urls, "broken_external_links.txt")
print_pages_with_errors(False, self.visited_urls, "broken_internal_links.txt")
print_pages_with_hardcoded_links(self.visited_urls, "hardcoded_url_links.txt")
print("\nTotal pages visited : {}\n".format(len(self.visited_urls)))
print_pages_to_file("all_internal_pages.txt", False, self.visited_urls)
print_pages_to_file("all_external_pages.txt", True, self.visited_urls)
def process_parameters():
parser = argparse.ArgumentParser(description='A Simple website scrapper')
parser.add_argument("--url", help="the start url , defaults to the config.ini url", default=START_URL)
parser.add_argument("--sitemap-url", dest="sitemap_url", help="the sitemap url ")
parser.add_argument("--url-file", dest="url_file", help="File containing list of urls ", action="store")
parser.add_argument('--jserrors', dest='testjs', action='store_true')
parser.add_argument('--no-jserrors', dest='testjs', action='store_false')
parser.add_argument('--process-exisitng-urls', dest='process_file', action='store')
parser.set_defaults(testjs=False)
return parser.parse_args()
if __name__ == "__main__":
# url ='http://appdynamics.com/blog/2010/09/01/application-virtualization-survey'
#
# link_info = extract(url)
# parsed_link = u"{}.{}.{}".format(link_info.subdomain, link_info.domain, link_info.suffix)
#
# for skipped_domain in DOMAINS_TO_BE_SKIPPED:
# if parsed_link == skipped_domain:
# pass
# pass
args = process_parameters()
base_url = decode_to_unicode(args.url)
sitemap_url = decode_to_unicode(args.sitemap_url)
enable_js_tests = args.testjs
process_existing_urls = args.process_file
url_list_file = decode_to_unicode(args.url_file)
if process_existing_urls:
if not url_list_file:
print("Missing file containing url list, please provide one with --url-file parameter")
sys.exit(1)
detect_js_and_resource_issues(url_list_file)
sys.exit(0)
scrapper = TornadoSpider(base_url, sitemap_url)
future = scrapper.initiate_crawl()
IOLoop.instance().start()
if enable_js_tests:
detect_js_and_resource_issues("all_internal_pages.txt")