webcrawler/spacetime-crawler4py-master/config.ini

21 lines
464 B
INI

[IDENTIFICATION]
# Set your user agent string here.
USERAGENT = IR US22 19854690,44333574,95241547
[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
# In seconds
POLITENESS = 0.5
[LOCAL PROPERTIES]
# Save file for progress
SAVE = frontier.shelve
# IMPORTANT: DO NOT CHANGE IT IF YOU HAVE NOT IMPLEMENTED MULTITHREADING.
THREADCOUNT = 1