Created
July 17, 2015 09:12
-
-
Save oldsharp/ce62c36717e0b1151963 to your computer and use it in GitHub Desktop.
yet another stupid web crawler
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/python2 | |
# -*- coding: utf-8 -*- | |
import re | |
import time | |
from bs4 import BeautifulSoup | |
from selenium import webdriver | |
URL = "http://dianying.taobao.com/cinemaDetail.htm?spm=a1z21.6646277.w2.303.cccQvy&cinemaId=13553&n_s=new" | |
RAW = ur".*7月18日(周六).*" | |
def main(): | |
try: | |
browser = webdriver.Firefox() | |
browser.get(URL) | |
while True: | |
soup = BeautifulSoup(browser.page_source, "html.parser") | |
pretty_page_src = soup.prettify() | |
if match(pretty_page_src): | |
# Put notify logic here | |
print "Gotcha" | |
break | |
else: | |
print "Pity, refreshing..." | |
time.sleep(5) | |
browser.refresh() | |
except KeyboardInterrupt: | |
pass | |
finally: | |
browser.quit() | |
def match(text): | |
pattern = re.compile(RAW) | |
for line in text.splitlines(): | |
if pattern.search(line): | |
return True | |
return False | |
if __name__ == "__main__": | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment