Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
9c31a901b7 |
@ -1,147 +0,0 @@
|
||||
2022-04-20 02:33:03,517 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-20 02:34:22,952 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-20 02:34:41,682 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-20 02:37:03,708 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-20 02:38:32,080 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-20 02:47:05,419 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-20 02:47:20,616 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-20 02:50:20,425 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-20 02:58:18,494 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-20 03:06:07,345 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-20 03:07:45,102 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-20 03:08:46,162 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-20 03:11:05,040 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-20 03:11:21,977 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-20 03:12:18,315 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-20 03:15:53,501 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-20 03:18:48,477 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-20 03:20:00,913 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-20 03:23:14,356 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-20 03:36:00,708 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-20 03:37:24,758 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-20 03:37:24,758 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-20 03:37:42,260 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-20 03:42:16,880 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-20 03:42:23,013 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-20 03:45:40,958 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-20 03:49:54,245 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-20 03:50:02,043 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-20 03:59:18,104 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-20 04:00:14,031 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-20 04:01:31,386 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-20 04:02:16,043 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-20 18:08:59,911 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-22 12:31:49,310 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-22 12:32:31,178 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-22 12:32:35,094 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-22 12:33:25,233 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-22 12:33:42,393 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-22 12:36:07,413 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-22 12:37:56,413 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-22 12:38:45,000 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-22 12:39:14,157 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-22 12:39:50,638 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-22 12:39:56,516 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-22 12:41:07,005 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-22 12:46:01,865 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-22 12:46:16,984 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-22 12:49:37,689 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-22 12:53:43,854 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-22 12:54:45,134 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-22 12:56:48,517 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-22 12:57:19,541 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-22 13:02:40,174 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-22 13:07:26,611 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-22 17:25:16,739 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-22 17:27:01,372 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-22 17:28:24,395 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-22 17:33:03,228 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-22 17:33:14,391 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-22 17:34:11,862 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-22 17:35:05,121 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-22 17:36:23,994 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-22 17:36:31,564 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-22 17:38:41,035 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-22 17:39:43,493 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-22 17:43:12,698 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-22 17:46:27,304 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-22 17:52:23,826 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-22 17:52:38,658 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-22 17:59:19,523 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-22 18:00:51,039 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-22 18:01:45,112 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 00:46:46,850 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 00:49:09,876 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 00:53:26,894 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 00:53:54,532 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 01:40:16,310 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 01:41:34,284 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 01:43:18,453 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 01:46:32,822 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 01:47:34,475 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 01:48:29,467 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 01:48:56,671 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 01:50:51,864 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 01:53:07,556 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 01:53:56,693 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 01:54:34,028 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 01:55:03,124 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 01:56:20,721 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 01:59:29,951 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 01:59:57,446 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 02:02:46,431 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 02:05:59,557 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 16:26:02,713 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 16:26:15,186 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 16:26:45,445 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 16:27:24,255 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 16:31:59,791 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 16:32:26,864 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 16:35:18,046 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 16:37:12,709 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 16:37:48,356 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 16:38:16,370 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 16:38:22,050 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 16:38:50,914 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 16:39:41,890 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 16:41:44,405 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 16:43:16,946 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 16:44:33,013 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 16:44:54,848 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 16:46:31,871 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 16:51:57,008 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 16:52:42,659 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 16:54:20,296 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 16:57:49,247 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 16:59:12,978 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 17:00:10,268 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 17:00:41,805 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 17:01:46,542 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 17:03:07,751 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 17:04:06,325 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 17:06:00,643 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 17:06:09,928 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 17:06:50,980 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 17:07:03,781 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 17:07:48,403 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 17:08:32,837 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 17:10:06,168 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 17:10:56,162 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 17:12:04,126 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 17:13:56,449 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 17:14:32,348 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 17:15:10,188 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 17:15:18,099 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 17:15:28,945 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 17:23:44,222 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 17:24:20,095 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 17:24:58,182 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 17:25:29,482 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 17:25:43,095 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 17:58:37,549 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 17:58:48,116 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 20:19:11,395 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 20:33:31,301 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-23 22:13:18,206 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-24 10:06:50,608 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
2022-04-24 14:10:29,409 - FRONTIER - INFO - Found save file frontier.shelve, deleting it.
|
||||
File diff suppressed because it is too large
Load Diff
@ -1,14 +1,13 @@
|
||||
[IDENTIFICATION]
|
||||
# Set your user agent string here.
|
||||
USERAGENT = IR US22 19854690,44333574,95241547
|
||||
USERAGENT = IR US22 19854690,44333574
|
||||
|
||||
[CONNECTION]
|
||||
HOST = styx.ics.uci.edu
|
||||
PORT = 9000
|
||||
|
||||
[CRAWLER]
|
||||
SEEDURL = https://www.ics.uci.edu,https://www.cs.uci.edu,https://www.informatics.uci.edu,https://www.stat.uci.edu,https://www.eecs.uci.edu
|
||||
|
||||
SEEDURL = https://www.ics.uci.edu,https://www.cs.uci.edu,https://www.informatics.uci.edu,https://www.stat.uci.edu
|
||||
# In seconds
|
||||
POLITENESS = 0.5
|
||||
|
||||
@ -17,5 +16,5 @@ POLITENESS = 0.5
|
||||
SAVE = frontier.shelve
|
||||
|
||||
# IMPORTANT: DO NOT CHANGE IT IF YOU HAVE NOT IMPLEMENTED MULTITHREADING.
|
||||
THREADCOUNT = 5
|
||||
THREADCOUNT = 1
|
||||
|
||||
|
||||
@ -1,57 +1,17 @@
|
||||
import os
|
||||
import shelve
|
||||
|
||||
from threading import Thread, Lock,Semaphore
|
||||
from threading import Thread, RLock
|
||||
from queue import Queue, Empty
|
||||
|
||||
import time
|
||||
|
||||
from utils import get_logger, get_urlhash, normalize
|
||||
from scraper import is_valid
|
||||
from datacollection import *
|
||||
|
||||
|
||||
#*.ics.uci.edu/* 0
|
||||
#*.cs.uci.edu/* 1
|
||||
#*.informatics.uci.edu/* 2
|
||||
#*.stat.uci.edu/* 3
|
||||
#today.uci.edu/department/information_computer_sciences/* 4
|
||||
|
||||
|
||||
|
||||
class Frontier(object):
|
||||
def __init__(self, config, restart):
|
||||
self.logger = get_logger("FRONTIER")
|
||||
self.config = config
|
||||
|
||||
#Load balancer, list()
|
||||
self.to_be_downloaded = [set(),set(),set(),set(),set()]
|
||||
|
||||
self.balance_index = 0
|
||||
|
||||
|
||||
#Semaphore for each domain to keep each domain noice and tidy with politeness
|
||||
self.domain_semaphores = [Lock(),Lock(),Lock(),Lock(),Lock()]
|
||||
#Local data lock
|
||||
self.data_mutex = Lock()
|
||||
|
||||
#FIle locks for data to make sure everything is thread-safe
|
||||
self.file_1_mutex = Lock()
|
||||
self.file_2_mutex = Lock()
|
||||
self.file_3_mutex = Lock()
|
||||
self.file_4_mutex = Lock()
|
||||
|
||||
|
||||
# data collection is going to happen in the frontier
|
||||
# uniques encompass overall unique links
|
||||
self.uniques = set()
|
||||
# grand_dict encompasses all the words over the entire set of links
|
||||
self.grand_dict = dict()
|
||||
# ics dict contains all subdomains of ics
|
||||
self.ics = dict()
|
||||
# used to find the longest page
|
||||
self.max = -9999
|
||||
self.longest = None
|
||||
self.to_be_downloaded = list()
|
||||
|
||||
if not os.path.exists(self.config.save_file) and not restart:
|
||||
# Save file does not exist, but request to load save.
|
||||
@ -75,202 +35,38 @@ class Frontier(object):
|
||||
for url in self.config.seed_urls:
|
||||
self.add_url(url)
|
||||
|
||||
|
||||
def _parse_save_file(self):
|
||||
''' This function can be overridden for alternate saving techniques. '''
|
||||
total_count = len(self.save)
|
||||
tbd_count = 0
|
||||
for url, completed in self.save.values():
|
||||
if not completed and is_valid(url):
|
||||
self.to_be_downloaded[self.get_domain_index(url)].add(url)
|
||||
self.to_be_downloaded.append(url)
|
||||
tbd_count += 1
|
||||
self.logger.info(
|
||||
f"Found {tbd_count} urls to be downloaded from {total_count} "
|
||||
f"total urls discovered.")
|
||||
|
||||
def get_tbd_url(self):
|
||||
###CRITICAL SECTION
|
||||
self.data_mutex.acquire()
|
||||
try:
|
||||
#Load balancing
|
||||
loop = 10
|
||||
while not self.to_be_downloaded[self.balance_index] and loop != 0:
|
||||
self.balance_index = self.balance_index + 1
|
||||
if self.balance_index > 4:
|
||||
self.balance_index = 0
|
||||
loop = loop - 1
|
||||
if loop == 0:
|
||||
self.data_mutex.release()
|
||||
return None
|
||||
hold = self.to_be_downloaded[self.balance_index].pop()
|
||||
self.balance_index = self.balance_index + 1
|
||||
self.data_mutex.release()
|
||||
#print(hold)
|
||||
return hold
|
||||
|
||||
return self.to_be_downloaded.pop()
|
||||
except IndexError:
|
||||
print("POPPING RANDOM SHIT BRO")
|
||||
self.data_mutex.release()
|
||||
return None
|
||||
|
||||
def add_url(self, url):
|
||||
url = normalize(url)
|
||||
urlhash = get_urlhash(url)
|
||||
##CRITICAL SECTION
|
||||
if urlhash not in self.save:
|
||||
self.save[urlhash] = (url, False)
|
||||
self.save.sync()
|
||||
self.to_be_downloaded[self.get_domain_index(url)].add(url)
|
||||
###CRITICAL SECTION
|
||||
|
||||
self.to_be_downloaded.append(url)
|
||||
|
||||
def mark_url_complete(self, url):
|
||||
urlhash = get_urlhash(url)
|
||||
|
||||
##CRITICAL SECTION
|
||||
if urlhash not in self.save:
|
||||
# This should not happen.
|
||||
self.logger.error(
|
||||
f"Completed url {url}, but have not seen it before.")
|
||||
|
||||
self.save[urlhash] = (url, True)
|
||||
self.save.sync()
|
||||
##CRITICAL SECTION
|
||||
|
||||
|
||||
def get_domain_index(self,url):
|
||||
#yeah if you put ics.uci.edu in first it will add all informatics link into that instead
|
||||
if "informatics.uci.edu" in url:
|
||||
return 0
|
||||
elif "ics.uci.edu" in url:
|
||||
return 1
|
||||
elif "cs.uci.edu" in url:
|
||||
return 2
|
||||
elif "stat.uci.edu" in url:
|
||||
return 3
|
||||
elif "today.uci.edu/department/information_computer_sciences/" in url:
|
||||
return 4
|
||||
else:
|
||||
print(url)
|
||||
print("ERROR")
|
||||
|
||||
|
||||
|
||||
def acquire_polite(self,url):
|
||||
return self.domain_semaphores[self.get_domain_index(url)].acquire()
|
||||
|
||||
def release_polite(self,url):
|
||||
return self.domain_semaphores[self.get_domain_index(url)].release()
|
||||
|
||||
def acquire_data_mutex(self):
|
||||
return self.data_mutex.acquire()
|
||||
|
||||
def release_data_mutex(self):
|
||||
return self.data_mutex.release()
|
||||
|
||||
def acquire_234_mutex(self):
|
||||
return self.file_2_3_4_mutex.acquire()
|
||||
|
||||
def release_234_mutex(self):
|
||||
return self.file_2_3_4_mutex.release()
|
||||
|
||||
|
||||
def q1(self, url):
|
||||
# rakslice (8 May 2013) Stackoverflow. https://stackoverflow.com/questions/16430258/creating-a-python-file-in-a-local-directory
|
||||
# this saves to the local directory, so I can constantly access the right file and check if it exists or not
|
||||
path_to_script = os.path.dirname(os.path.abspath(__file__))
|
||||
my_filename = os.path.join(path_to_script, "q1.txt")
|
||||
|
||||
# Will create a file of all the unique links and you can read the file and do lines = f.readlines() then len(lines) to get the number of unique links
|
||||
#Locking and releasing each file
|
||||
self.file_1_mutex.acquire()
|
||||
if (os.path.exists(my_filename)):
|
||||
f = open(my_filename, 'a')
|
||||
f.write(str(removeFragment(url)) + "\n")
|
||||
f.close()
|
||||
else:
|
||||
f = open(my_filename, 'w')
|
||||
f.write(str(removeFragment(url)) + "\n")
|
||||
f.close()
|
||||
self.file_1_mutex.release()
|
||||
|
||||
def q234(self, url, resp):
|
||||
# rakslice (8 May 2013) Stackoverflow. https://stackoverflow.com/questions/16430258/creating-a-python-file-in-a-local-directory
|
||||
# this saves to the local directory, so I can constantly access the right file and check if it exists or not
|
||||
|
||||
if resp.status != 200:
|
||||
return
|
||||
|
||||
tic = time.perf_counter()
|
||||
path_to_script = os.path.dirname(os.path.abspath(__file__))
|
||||
my_filename = os.path.join(path_to_script, "q2.txt")
|
||||
|
||||
try:
|
||||
tempTok = tokenize(resp)
|
||||
self.file_2_mutex.acquire()
|
||||
if len(tempTok) > self.max:
|
||||
self.max = len(tempTok)
|
||||
self.longest = url
|
||||
f = open(my_filename, 'w')
|
||||
f.write("Longest Page: {url}, length: {length}".format(url = self.longest, length = self.max))
|
||||
f.close()
|
||||
except:
|
||||
print("resp dying for some reason ?")
|
||||
|
||||
self.file_2_mutex.release()
|
||||
|
||||
toc = time.perf_counter()
|
||||
#print(f"Took {toc - tic:0.4f} seconds to save file 2 !")
|
||||
|
||||
tic = time.perf_counter()
|
||||
tempTok = removeStopWords(tempTok)
|
||||
self.file_3_mutex.acquire()
|
||||
computeFrequencies(tempTok, self.grand_dict)
|
||||
# rakslice (8 May 2013) Stackoverflow. https://stackoverflow.com/questions/16430258/creating-a-python-file-in-a-local-directory
|
||||
# this saves to the local directory, so I can constantly access the right file and check if it exists or not
|
||||
path_to_script = os.path.dirname(os.path.abspath(__file__))
|
||||
my_filename = os.path.join(path_to_script, "q3.txt")
|
||||
|
||||
|
||||
f = open(my_filename, "w")
|
||||
sortedGrandDict = {k: v for k, v in sorted(self.grand_dict.items(), key=lambda item: item[1], reverse = True)}
|
||||
i = 0
|
||||
for k, v in sortedGrandDict.items():
|
||||
if i == 50:
|
||||
break
|
||||
else:
|
||||
f.write("{}: {}\n".format(k, v))
|
||||
i += 1
|
||||
f.close()
|
||||
self.file_3_mutex.release()
|
||||
|
||||
toc = time.perf_counter()
|
||||
#print(f"Took {toc - tic:0.4f} seconds to save file 3 !")
|
||||
|
||||
tic = time.perf_counter()
|
||||
|
||||
fragless = removeFragment(url)
|
||||
domain = findDomains(fragless.netloc)
|
||||
self.file_4_mutex.acquire()
|
||||
if domain[1] == 'ics':
|
||||
if domain[0] not in self.ics:
|
||||
self.ics[domain[0]] = urlData(url, domain[0], domain[1])
|
||||
else:
|
||||
if fragless not in self.ics[domain[0]].getUniques():
|
||||
self.ics[domain[0]].appendUnique(fragless)
|
||||
|
||||
# rakslice (8 May 2013) Stackoverflow. https://stackoverflow.com/questions/16430258/creating-a-python-file-in-a-local-directory
|
||||
# this saves to the local directory, so I can constantly access the right file and check if it exists or not
|
||||
path_to_script = os.path.dirname(os.path.abspath(__file__))
|
||||
my_filename = os.path.join(path_to_script, "q4.txt")
|
||||
|
||||
# creating text file for question 4
|
||||
sortedDictKeys = sorted(self.ics.keys())
|
||||
f = open(my_filename, "w")
|
||||
for i in sortedDictKeys:
|
||||
f.write("{url}, {num} + \n".format(url = self.ics[i].getNiceLink(), num = len(self.ics[i].getUniques())))
|
||||
f.close()
|
||||
self.file_4_mutex.release()
|
||||
|
||||
toc = time.perf_counter()
|
||||
#print(f"Took {toc - tic:0.4f} seconds to save file 4 !")
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@ -1 +0,0 @@
|
||||
Longest Page: http://www.ics.uci.edu/~cs224, length: 83259
|
||||
@ -1,50 +0,0 @@
|
||||
research: 71407
|
||||
computer: 44358
|
||||
science: 35764
|
||||
ics: 31878
|
||||
students: 31271
|
||||
uci: 30946
|
||||
events: 28911
|
||||
news: 28680
|
||||
student: 28244
|
||||
information: 28159
|
||||
informatics: 27680
|
||||
graduate: 27322
|
||||
0: 26001
|
||||
school: 25154
|
||||
2021: 24609
|
||||
bren: 24296
|
||||
data: 23332
|
||||
us: 22961
|
||||
undergraduate: 22912
|
||||
faculty: 22357
|
||||
2020: 22133
|
||||
software: 22105
|
||||
learning: 21218
|
||||
policies: 20976
|
||||
1: 19559
|
||||
contact: 18653
|
||||
2018: 17102
|
||||
alumni: 17032
|
||||
2: 16758
|
||||
donald: 16690
|
||||
projects: 16319
|
||||
2019: 15778
|
||||
computing: 15414
|
||||
people: 15237
|
||||
irvine: 15146
|
||||
academic: 15127
|
||||
support: 14680
|
||||
2017: 14599
|
||||
view: 14582
|
||||
2016: 14330
|
||||
ramesh: 14140
|
||||
engineering: 13971
|
||||
university: 13744
|
||||
may: 13308
|
||||
sciences: 13175
|
||||
systems: 13164
|
||||
course: 12868
|
||||
statistics: 12582
|
||||
media: 12577
|
||||
new: 12501
|
||||
@ -1,86 +0,0 @@
|
||||
http://Transformativeplay.ics.uci.edu, 1 +
|
||||
http://accessibility.ics.uci.edu, 1 +
|
||||
http://acoi.ics.uci.edu, 52 +
|
||||
http://aiclub.ics.uci.edu, 1 +
|
||||
http://archive.ics.uci.edu, 6 +
|
||||
http://asterix.ics.uci.edu, 7 +
|
||||
http://cbcl.ics.uci.edu, 23 +
|
||||
http://cert.ics.uci.edu, 5 +
|
||||
http://checkmate.ics.uci.edu, 1 +
|
||||
http://chenli.ics.uci.edu, 9 +
|
||||
http://cloudberry.ics.uci.edu, 45 +
|
||||
http://cml.ics.uci.edu, 172 +
|
||||
http://code.ics.uci.edu, 12 +
|
||||
http://computableplant.ics.uci.edu, 33 +
|
||||
http://cradl.ics.uci.edu, 20 +
|
||||
http://create.ics.uci.edu, 6 +
|
||||
http://cwicsocal18.ics.uci.edu, 12 +
|
||||
http://cyberclub.ics.uci.edu, 14 +
|
||||
http://dgillen.ics.uci.edu, 19 +
|
||||
http://duttgroup.ics.uci.edu, 85 +
|
||||
http://elms.ics.uci.edu, 1 +
|
||||
http://emj.ics.uci.edu, 45 +
|
||||
http://evoke.ics.uci.edu, 62 +
|
||||
http://flamingo.ics.uci.edu, 11 +
|
||||
http://fr.ics.uci.edu, 3 +
|
||||
http://frost.ics.uci.edu, 1 +
|
||||
http://futurehealth.ics.uci.edu, 72 +
|
||||
http://graphics.ics.uci.edu, 4 +
|
||||
http://hack.ics.uci.edu, 1 +
|
||||
http://hai.ics.uci.edu, 3 +
|
||||
http://helpdesk.ics.uci.edu, 3 +
|
||||
http://hobbes.ics.uci.edu, 1 +
|
||||
http://i-sensorium.ics.uci.edu, 1 +
|
||||
http://iasl.ics.uci.edu, 17 +
|
||||
http://industryshowcase.ics.uci.edu, 23 +
|
||||
http://www.informatics.ics.uci.edu, 1 +
|
||||
http://intranet.ics.uci.edu, 2 +
|
||||
http://ipf.ics.uci.edu, 2 +
|
||||
http://ipubmed.ics.uci.edu, 1 +
|
||||
http://isg.ics.uci.edu, 104 +
|
||||
http://jgarcia.ics.uci.edu, 23 +
|
||||
http://luci.ics.uci.edu, 4 +
|
||||
http://malek.ics.uci.edu, 1 +
|
||||
http://mcs.ics.uci.edu, 31 +
|
||||
http://mdogucu.ics.uci.edu, 1 +
|
||||
http://mds.ics.uci.edu, 11 +
|
||||
http://mhcid.ics.uci.edu, 16 +
|
||||
http://mondego.ics.uci.edu, 3 +
|
||||
http://motifmap.ics.uci.edu, 2 +
|
||||
http://mse.ics.uci.edu, 2 +
|
||||
http://mswe.ics.uci.edu, 16 +
|
||||
http://mt-live.ics.uci.edu, 1634 +
|
||||
http://nalini.ics.uci.edu, 7 +
|
||||
http://ngs.ics.uci.edu, 2000 +
|
||||
http://perennialpolycultures.ics.uci.edu, 1 +
|
||||
http://plrg.ics.uci.edu, 14 +
|
||||
http://psearch.ics.uci.edu, 1 +
|
||||
http://radicle.ics.uci.edu, 1 +
|
||||
http://redmiles.ics.uci.edu, 4 +
|
||||
http://riscit.ics.uci.edu, 1 +
|
||||
http://sconce.ics.uci.edu, 2 +
|
||||
http://sdcl.ics.uci.edu, 205 +
|
||||
http://seal.ics.uci.edu, 6 +
|
||||
http://sherlock.ics.uci.edu, 7 +
|
||||
http://sli.ics.uci.edu, 338 +
|
||||
http://sourcerer.ics.uci.edu, 1 +
|
||||
http://sprout.ics.uci.edu, 2 +
|
||||
http://stairs.ics.uci.edu, 4 +
|
||||
http://statconsulting.ics.uci.edu, 5 +
|
||||
http://student-council.ics.uci.edu, 1 +
|
||||
http://studentcouncil.ics.uci.edu, 3 +
|
||||
http://support.ics.uci.edu, 4 +
|
||||
http://swiki.ics.uci.edu, 42 +
|
||||
http://tad.ics.uci.edu, 3 +
|
||||
http://tastier.ics.uci.edu, 1 +
|
||||
http://tippers.ics.uci.edu, 1 +
|
||||
http://tippersweb.ics.uci.edu, 5 +
|
||||
http://transformativeplay.ics.uci.edu, 58 +
|
||||
http://tutors.ics.uci.edu, 44 +
|
||||
http://ugradforms.ics.uci.edu, 3 +
|
||||
http://unite.ics.uci.edu, 10 +
|
||||
http://vision.ics.uci.edu, 200 +
|
||||
http://wearablegames.ics.uci.edu, 11 +
|
||||
http://wics.ics.uci.edu, 970 +
|
||||
http://www-db.ics.uci.edu, 10 +
|
||||
http://xtune.ics.uci.edu, 6 +
|
||||
@ -18,53 +18,16 @@ class Worker(Thread):
|
||||
|
||||
def run(self):
|
||||
while True:
|
||||
tic = time.perf_counter()
|
||||
tbd_url = self.frontier.get_tbd_url()
|
||||
toc = time.perf_counter()
|
||||
#print(f"Took {toc - tic:0.4f} seconds to get_tbd_url")
|
||||
if not tbd_url:
|
||||
self.logger.info("Frontier is empty. Stopping Crawler.")
|
||||
break
|
||||
self.frontier.acquire_polite(tbd_url)
|
||||
tic = time.perf_counter()
|
||||
resp = download(tbd_url, self.config, self.logger)
|
||||
start = time.perf_counter()
|
||||
toc = time.perf_counter()
|
||||
#print(f"Took {toc - tic:0.4f} seconds to do download url")
|
||||
|
||||
self.logger.info(
|
||||
f"Downloaded {tbd_url}, status <{resp.status}>, "
|
||||
f"using cache {self.config.cache_server}.")
|
||||
|
||||
tic = time.perf_counter()
|
||||
scraped_urls = scraper.scraper(tbd_url, resp)
|
||||
toc = time.perf_counter()
|
||||
#print(f"Took {toc - tic:0.4f} seconds to do scrape url")
|
||||
|
||||
tic = time.perf_counter()
|
||||
self.frontier.acquire_data_mutex()
|
||||
for scraped_url in scraped_urls:
|
||||
self.frontier.add_url(scraped_url)
|
||||
self.frontier.mark_url_complete(tbd_url)
|
||||
self.frontier.release_data_mutex()
|
||||
toc = time.perf_counter()
|
||||
#print(f"Took {toc - tic:0.4f} seconds to do add_url stuffs")
|
||||
|
||||
tic = time.perf_counter()
|
||||
self.frontier.q1(tbd_url)
|
||||
toc = time.perf_counter()
|
||||
#print(f"Took {toc - tic:0.4f} seconds to do log q1 url")
|
||||
|
||||
tic = time.perf_counter()
|
||||
self.frontier.q234(tbd_url, resp)
|
||||
toc = time.perf_counter()
|
||||
#print(f"Took {toc - tic:0.4f} seconds to do log q234 url")
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
while start + self.config.time_delay > time.perf_counter():
|
||||
#print("Sleeping")
|
||||
time.sleep(self.config.time_delay/5)
|
||||
self.frontier.release_polite(tbd_url)
|
||||
time.sleep(self.config.time_delay)
|
||||
|
||||
@ -1,123 +0,0 @@
|
||||
import re
|
||||
import os
|
||||
import urllib.request
|
||||
from urllib.parse import urlparse
|
||||
from urllib.parse import urljoin
|
||||
from bs4 import BeautifulSoup
|
||||
from nltk.tokenize import word_tokenize
|
||||
from nltk.corpus import stopwords
|
||||
from nltk.corpus import words
|
||||
import re
|
||||
import html2text
|
||||
import nltk
|
||||
nltk.download('stopwords')
|
||||
nltk.download('words')
|
||||
nltk.download('punkt')
|
||||
|
||||
english_words = words.words()
|
||||
english_stop_words = stopwords.words('english')
|
||||
|
||||
# there is another nltk.download() requirement but I removed it so i forgot what it was
|
||||
# it'll show in the console/terminal if you run the code i believe
|
||||
# it showed in mine
|
||||
|
||||
# To explain this class I have to start by explaining the container I decided on using to keep track of subdomains of ics.uci.edu
|
||||
# I decided to use a dict. Long story short, I was trying to figure out what to make my key so it would uniquely identify what I needed it to do.
|
||||
# I was going to use the parsed.netloc; however, we're taking into account that a link that looks like https://somename.vision.ics.uci.edu
|
||||
# is a unique link of the subdomain vision.
|
||||
# And so I made the key the subdomain that is before ics.uci.edu in the link, and the value of the dict is this class
|
||||
# It's a very simple class, so I'm not going to commenting what it does
|
||||
class urlData:
|
||||
def __init__(self, url, subdomain, domain):
|
||||
self.url = url
|
||||
self.nicelink = "http://" + removeFragment(url).netloc
|
||||
self.domain = domain
|
||||
self.subdomain = subdomain
|
||||
self.uniques = set()
|
||||
self.uniques.add(removeFragment(url))
|
||||
|
||||
def getDomain(self):
|
||||
return self.domain
|
||||
|
||||
def getURL(self):
|
||||
return self.url
|
||||
|
||||
def getNiceLink(self):
|
||||
return self.nicelink
|
||||
|
||||
def getSub(self):
|
||||
return self.subdomain
|
||||
|
||||
def getUniques(self):
|
||||
return self.uniques
|
||||
|
||||
def appendUnique(self, parse):
|
||||
self.uniques.add(parse)
|
||||
|
||||
# Tried to find a libary that would do this for me, but couldn't
|
||||
# It parses the url and uses the netloc to separat for domain and subdomain
|
||||
def findDomains(url):
|
||||
urlsplit = url.split('.')
|
||||
if urlsplit[0].lower() == 'www':
|
||||
urlsplit.remove('www')
|
||||
for i in range(len(urlsplit)):
|
||||
if urlsplit[i] == 'ics':
|
||||
if i == 0:
|
||||
return 0, 0
|
||||
elif i == 1:
|
||||
return urlsplit[0], urlsplit[1]
|
||||
else:
|
||||
return urlsplit[i-1], urlsplit[i] #something like random.vision.ics.uci.edu will be consider a unique page of vision
|
||||
return None, None
|
||||
else:
|
||||
for i in range(len(urlsplit)):
|
||||
if urlsplit[i] == 'ics':
|
||||
if i == 0:
|
||||
return 0, 0
|
||||
elif i == 1:
|
||||
return urlsplit[0], urlsplit[1]
|
||||
else:
|
||||
return urlsplit[i-1], urlsplit[i] #something like random.vision.ics.uci.edu will be consider a unique page of vision
|
||||
return None, None
|
||||
|
||||
def tokenize(resp):
|
||||
# getting connection from url
|
||||
valid = re.compile(r'[^a-zA-Z0-9]+')
|
||||
# named it tSoup for merge convience
|
||||
# need the 'lxml' parser for this.
|
||||
# When extract_next_links is called it returns a list full of links with no resp, and I had to find a way to get text from just link.
|
||||
# Therefore, I decided to get the plain text this way.
|
||||
tSoup = BeautifulSoup(resp.raw_response.content, 'lxml')
|
||||
|
||||
# Floyd (1 March 2021) Stackoverflow. https://stackoverflow.com/questions/328356/extracting-text-from-html-file-using-python
|
||||
# compared this with tSoup.get_text() and clean_text just provided content easier to tokenize and more inline with my intentions
|
||||
clean_text = ' '.join(tSoup.stripped_strings)
|
||||
token = word_tokenize(clean_text)
|
||||
|
||||
clean_token = list()
|
||||
# This used the nltk.corpus and just removes the tokens that aren't words
|
||||
#token = [i for i in token if i.lower() in english_words]
|
||||
|
||||
for word in token:
|
||||
if not valid.match(word):
|
||||
clean_token.append(word.lower())
|
||||
|
||||
return clean_token
|
||||
|
||||
#added this so the scraper code is not too redundant
|
||||
def computeFrequencies(tokens, d):
|
||||
for t in tokens:
|
||||
if t not in d:
|
||||
d[t] = 1
|
||||
else:
|
||||
d[t] += 1
|
||||
|
||||
def removeStopWords(toks):
|
||||
return [t for t in toks if t.lower() if not t.lower() in english_stop_words]
|
||||
|
||||
def removeFragment(u):
|
||||
# turn into a urlparse object
|
||||
# removed fragment in order to have "unique" links
|
||||
removefrag = urlparse(u)
|
||||
removefrag = removefrag._replace(fragment = '')
|
||||
return removefrag
|
||||
Binary file not shown.
File diff suppressed because it is too large
Load Diff
@ -1,5 +1,6 @@
|
||||
import re
|
||||
from urllib import robotparser
|
||||
from urllib.parse import urlparse
|
||||
from bs4 import BeautifulSoup
|
||||
from collections import defaultdict
|
||||
import requests
|
||||
@ -9,6 +10,7 @@ import requests
|
||||
# https://docs.python.org/3/library/urllib.robotparser.html#urllib.robotparser.RobotFileParser
|
||||
# http://pymotw.com/2/robotparser/
|
||||
# https://stackoverflow.com/questions/43085744/parsing-robots-txt-in-python
|
||||
'''This is ver 1.0
|
||||
robots_seen = dict() # all robots go here (global so we can store over all site)
|
||||
def robots_ok(parsed)->bool:
|
||||
global robots_seen # global dict for files
|
||||
@ -32,4 +34,30 @@ def robots_are_ok(parsed):
|
||||
return robots_ok(parsed)
|
||||
else:
|
||||
return robots_seen[parsed.netloc] # if it has been read return its value
|
||||
'''
|
||||
# Ver 1.1 maybe if I am understanding this correctly
|
||||
robots_seen = dict() # dict of all seen robot files and store not allowed
|
||||
def robots_ok(url)->bool:
|
||||
try:
|
||||
parsed = urlparse(url) # parse url
|
||||
except:
|
||||
print("Error in parse for: " + url)
|
||||
|
||||
robotstxt = "" # string for location of file
|
||||
try:
|
||||
robottxts = parsed.scheme + "://" + parsed.hostname + "/robots.txt" # location of file
|
||||
except:
|
||||
print("Error in parse for robots.txt: " + parsed)
|
||||
|
||||
if robotstxt not in robots_seen: # if url not in dict add to dict
|
||||
robots_seen[robotstxt] = robotparser.RobotFileParser(robotstxt)
|
||||
try:
|
||||
robots_seen[robotstxt] = robotparser.RobotFileParser.read(robotstxt)
|
||||
except:
|
||||
del robots_seen[robotstxt]
|
||||
return True
|
||||
try:
|
||||
return robots_seen[robotstxt].can_fetch('*', url)
|
||||
except:
|
||||
print("There was an error with: " + url)
|
||||
return True
|
||||
|
||||
@ -1,37 +1,23 @@
|
||||
from distutils.filelist import findall
|
||||
from operator import truediv
|
||||
import re
|
||||
import time
|
||||
import urllib.request
|
||||
from urllib import robotparser
|
||||
from urllib.parse import urlparse
|
||||
from urllib.parse import urljoin
|
||||
from bs4 import BeautifulSoup
|
||||
from robotsokay import *
|
||||
|
||||
def scraper(url, resp):
|
||||
|
||||
links = extract_next_links(url, resp)
|
||||
|
||||
|
||||
links_valid = set()
|
||||
links_valid = list()
|
||||
valid_links = open("valid_links.txt",'a')
|
||||
invalid_links = open("invalid_links.txt",'a')
|
||||
|
||||
tic = time.perf_counter()
|
||||
|
||||
for link in links:
|
||||
if is_valid(link):
|
||||
links_valid.add(link)
|
||||
links_valid.append(link)
|
||||
valid_links.write(link + "\n")
|
||||
else:
|
||||
invalid_links.write("From: " + url + "\n")
|
||||
invalid_links.write(link + "\n")
|
||||
pass
|
||||
|
||||
toc = time.perf_counter()
|
||||
#print(f"Took {toc - tic:0.4f} seconds to validate !!!")
|
||||
|
||||
return links_valid
|
||||
|
||||
def extract_next_links(url, resp):
|
||||
@ -44,11 +30,11 @@ def extract_next_links(url, resp):
|
||||
# resp.raw_response.url: the url, again
|
||||
# resp.raw_response.content: the content of the page!
|
||||
# Return a list with the hyperlinks (as strings) scrapped from resp.raw_response.content
|
||||
pages = set()
|
||||
pages = list()
|
||||
if resp.status == 200:
|
||||
#do stuff
|
||||
soup = BeautifulSoup(resp.raw_response.content,'lxml')
|
||||
#tempFile = open("test.txt", 'a')
|
||||
soup = BeautifulSoup(resp.raw_response.content)
|
||||
tempFile = open("test6.txt", 'a')
|
||||
#Getting all the links, href = true means at least theres a href value, dont know what it is yet
|
||||
for link in soup.find_all('a', href=True):
|
||||
#There is a lot of relative paths stuff here gotta add them
|
||||
@ -64,30 +50,13 @@ def extract_next_links(url, resp):
|
||||
if(href_link.startswith("/")):
|
||||
href_link = urljoin(url,href_link)
|
||||
|
||||
if(href_link.startswith("www.")):
|
||||
href_link = "https://" + href_link
|
||||
|
||||
#skipping query with specific actions which mutate the websites and cause a trap
|
||||
if "do=" in href_link:
|
||||
continue
|
||||
|
||||
# don't know if this is too expensive, otherwise idk
|
||||
# takes parsed url and if not ok on robots goes next, else we can write file
|
||||
|
||||
"""
|
||||
#For now robot checking too time expensive and incorrectly implemented
|
||||
parsed = urlparse(href_link)
|
||||
tic = time.perf_counter()
|
||||
print(parsed)
|
||||
if not robots_are_ok(parsed):
|
||||
continue
|
||||
toc = time.perf_counter()
|
||||
print(f"Took {toc - tic:0.4f} seconds to robots_are_ok !!!")
|
||||
"""
|
||||
|
||||
#tempFile.write(href_link + "\n")
|
||||
tempFile.write(href_link + "\n")
|
||||
#Adding to the boi wonder pages
|
||||
pages.add(href_link)
|
||||
pages.append(href_link)
|
||||
else:
|
||||
print("Page error !")
|
||||
return pages
|
||||
@ -106,6 +75,7 @@ def is_valid(url):
|
||||
# There are already some conditions that return False.
|
||||
|
||||
try:
|
||||
#Gotta check if they are in the domain
|
||||
parsed = urlparse(url)
|
||||
url_parsed_path = parsed.path.lower() # this may help speed things up a little bit (less calls to parsed.path)
|
||||
if parsed.scheme not in set(["http", "https"]):
|
||||
@ -118,72 +88,36 @@ def is_valid(url):
|
||||
+ r"|data|dat|exe|bz2|tar|msi|bin|7z|psd|dmg|iso"
|
||||
+ r"|epub|dll|cnf|tgz|sha1"
|
||||
+ r"|thmx|mso|arff|rtf|jar|csv"
|
||||
+ r"|rm|smil|wmv|swf|wma|zip|rar|gz)$",parsed.path.lower()):
|
||||
return False
|
||||
elif re.match(
|
||||
#turns out some query also try to download files, which filled stuff with random stuff thats uncessary
|
||||
r".*\.(css|js|bmp|gif|jpe?g|ico"
|
||||
+ r"|png|tiff?|mid|mp2|mp3|mp4"
|
||||
+ r"|wav|avi|mov|mpeg|ram|m4v|mkv|ogg|ogv|pdf"
|
||||
+ r"|ps|eps|tex|ppt|pptx|doc|docx|xls|xlsx|names"
|
||||
+ r"|data|dat|exe|bz2|tar|msi|bin|7z|psd|dmg|iso"
|
||||
+ r"|epub|dll|cnf|tgz|sha1"
|
||||
+ r"|thmx|mso|arff|rtf|jar|csv"
|
||||
+ r"|rm|smil|wmv|swf|wma|zip|rar|gz)$",parsed.query.lower()):
|
||||
+ r"|rm|smil|wmv|swf|wma|zip|rar|gz)$",url_parsed_path):
|
||||
return False
|
||||
elif not re.match(
|
||||
#Making sure domains are respected
|
||||
r".*[./]ics.uci.edu/.*"
|
||||
+ r"|.*[./]cs.uci.edu/.*"
|
||||
+ r"|.*[./]informatics.uci.edu/.*"
|
||||
+ r"|.*[./]stat.uci.edu/.*"
|
||||
r".*ics.uci.edu/.*"
|
||||
+ r"|.*cs.uci.edu/.*"
|
||||
+ r"|.*informatics.uci.edu/.*"
|
||||
+ r"|.*stat.uci.edu/.*"
|
||||
+ r"|today.uci.edu/department/information_computer_sciences/.*",url):
|
||||
return False
|
||||
|
||||
#Querying dates return usually bad information
|
||||
#anything that ends with a date also usually returns junk also returns nothing useful most of the time
|
||||
#/events/caterogy/ all gives random pages of no information
|
||||
elif re.match(
|
||||
r".*\d{4}-\d{2}-\d{2}",url):
|
||||
return False
|
||||
elif re.match(
|
||||
r".*\d{4}-\d{2}-\d{2}/",url):
|
||||
return False
|
||||
elif re.match(
|
||||
r".*\d{4}-\d{2}-\d{2}",parsed.query):
|
||||
return False
|
||||
elif re.match(
|
||||
r".*\/events/category/.*",url):
|
||||
return False
|
||||
elif parsed.fragment:
|
||||
return False
|
||||
|
||||
# https://support.archive-it.org/hc/en-us/articles/208332963-Modify-crawl-scope-with-a-Regular-Expression
|
||||
# length check for looping filters and queries (could add hash check for similarity or regex, but don't know if we want to as this works well enought)
|
||||
# we can adjust it based on what the cralwer does as well
|
||||
if len(url) > 250:
|
||||
if len(url) > 169:
|
||||
return False
|
||||
# this fixes any search box that keeps going page to page, currenty allow a depth of 0 filters
|
||||
# any filter just give you uncesssary information since the original page already has all information for all poeple
|
||||
if re.match(r".*(&filter%.*){1,}",url):
|
||||
if robots_ok(url) == False: # if robots returns false than no go
|
||||
return False
|
||||
if re.match(r".*(&filter%.*){3,}" # this fixes any search box that keeps going page to page, currenty allow a depth of 2 filters
|
||||
+ r"|^.*?(/.+?/).*?\1.*$|^.*?/(.+?/)\2.*$" # looping directory check
|
||||
+ r"|^.*(/misc|/sites|/all|/themes|/modules|/profiles|/css|/field|/node|/theme){3}.*$" # extra directories check (we can add as we find)
|
||||
+ r"|^.*calendar.*$",url_parsed_path): # calendar checks plus adding or downloading calendar (ical)
|
||||
return False
|
||||
# this is for urls which when opened, download a file (do we want to download these files and tokenize them)
|
||||
# elif re.match(r"^.*\&format=(\D{3,4})\Z$",url_parsed_path):
|
||||
# return False
|
||||
# another looping directory check but more advanced than the one contained in is_a_trap
|
||||
if re.match(r"^.*?(/.+?/).*?\1.*$|^.*?/(.+?/)\2.*$",url):
|
||||
return False
|
||||
# extra directories check (we can add as we find)
|
||||
if re.match(r"^.*(/misc|/sites|/all|/themes|/modules|/profiles|/css|/field|/node|/theme){3}.*$", url):
|
||||
return False
|
||||
# calendar checks plus adding or downloading calendar (ical)
|
||||
if re.match(r"^.*calendar.*$",url):
|
||||
return False
|
||||
if parsed.query.find('ical') != -1:
|
||||
return False
|
||||
else:
|
||||
return True
|
||||
|
||||
except TypeError:
|
||||
print ("TypeError for ", parsed)
|
||||
raise
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
Loading…
Reference in New Issue
Block a user