Repository navigation
Expand file tree
/
Copy pathcrawler.py
More file actions
318 lines (252 loc) · 8.2 KB
/
Copy pathcrawler.py
File metadata and controls
318 lines (252 loc) · 8.2 KB
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
import config
import logging
from urllib.parse import urljoin
import re
from urllib.parse import urlparse
from urllib.request import urlopen, Request
from urllib.robotparser import RobotFileParser
from datetime import datetime
import mimetypes
import os
class Crawler():
# Variables
parserobots = False
output = None
report = False
config = None
domain = ""
exclude = []
skipext = []
drop = []
debug = False
tocrawl = set([])
crawled = set([])
excluded = set([])
marked = {}
not_parseable_ressources = (".avi", ".mkv", ".mp4", ".jpg", ".jpeg", ".png", ".gif" ,".pdf", ".iso", ".rar", ".tar", ".tgz", ".zip", ".dmg", ".exe")
# TODO also search for window.location={.*?}
linkregex = re.compile(b'<a [^>]*href=[\'|"](.*?)[\'"][^>]*?>')
imageregex = re.compile (b'<img [^>]*src=[\'|"](.*?)[\'"].*?>')
rp = None
response_code={}
nb_url=1 # Number of url.
nb_rp=0 # Number of url blocked by the robots.txt
nb_exclude=0 # Number of url excluded by extension or word
output_file = None
target_domain = ""
def __init__(self, parserobots=False, output=None, report=False ,domain="",
exclude=[], skipext=[], drop=[], debug=False, verbose=False, images=False):
self.parserobots = parserobots
self.output = output
self.report = report
self.domain = domain
self.exclude = exclude
self.skipext = skipext
self.drop = drop
self.debug = debug
self.verbose = verbose
self.images = images
if self.debug:
log_level = logging.DEBUG
elif self.verbose:
log_level = logging.INFO
else:
log_level = logging.ERROR
logging.basicConfig(level=log_level)
self.tocrawl = set([domain])
try:
self.target_domain = urlparse(domain)[1]
except:
logging.error("Invalide domain")
raise ("Invalid domain")
if self.output:
try:
self.output_file = open(self.output, 'w')
except:
logging.error ("Output file not available.")
exit(255)
def run(self):
print(config.xml_header, file=self.output_file)
if self.parserobots:
self.check_robots()
logging.info("Start the crawling process")
while len(self.tocrawl) != 0:
self.__crawling()
logging.info("Crawling has reached end of all found links")
print (config.xml_footer, file=self.output_file)
def __crawling(self):
crawling = self.tocrawl.pop()
url = urlparse(crawling)
self.crawled.add(crawling)
logging.info("Crawling #{}: {}".format(len(self.crawled), url.geturl()))
request = Request(crawling, headers={"User-Agent":config.crawler_user_agent})
# Ignore ressources listed in the not_parseable_ressources
# Its avoid dowloading file like pdf… etc
if not url.path.endswith(self.not_parseable_ressources):
try:
response = urlopen(request)
except Exception as e:
if hasattr(e,'code'):
if e.code in self.response_code:
self.response_code[e.code]+=1
else:
self.response_code[e.code]=1
# Gestion des urls marked pour le reporting
if self.report:
if e.code in self.marked:
self.marked[e.code].append(crawling)
else:
self.marked[e.code] = [crawling]
logging.debug ("{1} ==> {0}".format(e, crawling))
return self.__continue_crawling()
else:
logging.debug("Ignore {0} content might be not parseable.".format(crawling))
response = None
# Read the response
if response is not None:
try:
msg = response.read()
if response.getcode() in self.response_code:
self.response_code[response.getcode()]+=1
else:
self.response_code[response.getcode()]=1
response.close()
# Get the last modify date
if 'last-modified' in response.headers:
date = response.headers['Last-Modified']
else:
date = response.headers['Date']
date = datetime.strptime(date, '%a, %d %b %Y %H:%M:%S %Z')
except Exception as e:
logging.debug ("{1} ===> {0}".format(e, crawling))
return None
else:
# Response is None, content not downloaded, just continu and add
# the link to the sitemap
msg = "".encode( )
date = None
# Image sitemap enabled ?
image_list = "";
if self.images:
# Search for images in the current page.
images = self.imageregex.findall(msg)
for image_link in list(set(images)):
image_link = image_link.decode("utf-8")
# Append domain if not present
if not image_link.startswith(("http", "https")):
image_link = "{0}{1}".format(self.domain.strip("/"), image_link.replace("./", "/"))
# Test if images as been already seen and not present in the
# robot file
if self.can_fetch(image_link):
logging.debug("Found image : {0}".format(image_link))
image_list = "{0}<image:image><image:loc>{1}</image:loc></image:image>".format(image_list, self.htmlspecialchars(image_link))
# Last mod fetched ?
lastmod = ""
if date:
lastmod = "<lastmod>"+date.strftime('%Y-%m-%dT%H:%M:%S+00:00')+"</lastmod>"
print ("<url><loc>"+self.htmlspecialchars(url.geturl())+"</loc>" + lastmod + image_list + "</url>", file=self.output_file)
if self.output_file:
self.output_file.flush()
# Found links
links = self.linkregex.findall(msg)
for link in links:
link = link.decode("utf-8")
logging.debug("Found : {0}".format(link))
if link.startswith('/'):
link = url.scheme + '://' + url[1] + link
elif link.startswith('#'):
link = url.scheme + '://' + url[1] + url[2] + link
elif not link.startswith(('http', "https")):
link = url.scheme + '://' + url[1] + '/' + link
# Remove the anchor part if needed
if "#" in link:
link = link[:link.index('#')]
# Drop attributes if needed
for toDrop in self.drop:
link=re.sub(toDrop,'',link)
# Parse the url to get domain and file extension
parsed_link = urlparse(link)
domain_link = parsed_link.netloc
target_extension = os.path.splitext(parsed_link.path)[1][1:]
if link in self.crawled:
continue
if link in self.tocrawl:
continue
if link in self.excluded:
continue
if domain_link != self.target_domain:
continue
if "javascript" in link:
continue
if self.is_image(parsed_link.path):
continue
if parsed_link.path.startswith("data:"):
continue
# Count one more URL
self.nb_url+=1
# Check if the navigation is allowed by the robots.txt
if not self.can_fetch(link):
self.exclude_link(link)
self.nb_rp+=1
continue
# Check if the current file extension is allowed or not.
if (target_extension in self.skipext):
self.exclude_link(link)
self.nb_exclude+=1
continue
# Check if the current url doesn't contain an excluded word
if (not self.exclude_url(link)):
self.exclude_link(link)
self.nb_exclude+=1
continue
self.tocrawl.add(link)
return None
def is_image(self, path):
mt,me = mimetypes.guess_type(path)
return mt is not None and mt.startswith("image/")
def __continue_crawling(self):
if self.tocrawl:
self.__crawling()
def exclude_link(self,link):
if link not in self.excluded:
self.excluded.add(link)
def check_robots(self):
robots_url = urljoin(self.domain, "robots.txt")
self.rp = RobotFileParser()
self.rp.set_url(robots_url)
self.rp.read()
def can_fetch(self, link):
try:
if self.parserobots:
if self.rp.can_fetch("*", link):
return True
else:
logging.debug ("Crawling of {0} disabled by robots.txt".format(link))
return False
if not self.parserobots:
return True
return True
except:
# On error continue!
logging.debug ("Error during parsing robots.txt")
return True
def exclude_url(self, link):
for ex in self.exclude:
if ex in link:
return False
return True
def htmlspecialchars(self, text):
return text.replace("&", "&").replace('"', """).replace("<", "<").replace(">", ">")
def make_report(self):
print ("Number of found URL : {0}".format(self.nb_url))
print ("Number of link crawled : {0}".format(len(self.crawled)))
if self.parserobots:
print ("Number of link block by robots.txt : {0}".format(self.nb_rp))
if self.skipext or self.exclude:
print ("Number of link exclude : {0}".format(self.nb_exclude))
for code in self.response_code:
print ("Nb Code HTTP {0} : {1}".format(code, self.response_code[code]))
for code in self.marked:
print ("Link with status {0}:".format(code))
for uri in self.marked[code]:
print ("\t- {0}".format(uri))