[Web] re:exchange rate crawler

呃...就是網頁的 css 改掉了 class name 也跟著改，所以原本 grep decimal 不管用了...要重寫

於是用前幾篇的 python url庫重練，這次感覺抓得沒有之前那麼針對性，比較通用，應該可以撐得更久一點bar ?!

 

	#!/usr/bin/env python2.7
	import urllib2 , io
	from HTMLParser import HTMLParser
	####################### SETTING ########################
	bank_url = "http://rate.bot.com.tw/xrt?Lang=zh-TW"
	####################### PAESER IMPLEMENT ###############
	class rateParser(HTMLParser):
	def __init__(self):
	HTMLParser.__init__(self)
	self.getData = False
	self.getCurrencyName = True
	self.countRate = 0
	self.lastTag = ""
	def handle_starttag(self , tag , attrs):
	self.lastTag = tag
	if tag == "td":
	self.getData = True;
	def handle_data(self , data):
	if self.getData == True:
	if self.lastTag == 'td' and self.countRate < 4:
	if data.strip() != "":
	print '%-7s\t' %data.strip() , " " ,
	self.countRate += 1
	if self.lastTag == 'div' and self.getCurrencyName == True:
	if data.strip() != "":
	print data.strip() , "\t" ,
	self.getCurrencyName = False
	def handle_endtag(self , tag):
	if tag == 'td' and self.getData == True:
	self.getData = False
	if tag == 'tr':
	if self.getCurrencyName == False:
	print ""
	self.getCurrencyName = True
	self.countRate = 0
	####################### MAIN ######################
	if __name__ == '__main__':
	req = urllib2.Request(bank_url)#declear a http request
	req.add_header("User-Agent" , 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)')#pretend firefox
	response = urllib2.urlopen(req)#download html file
	web_page = response.read()#read html file
	rateParser().feed(web_page)#analysis html file

view raw ExchangeRateCrawlerForPy2.py hosted with ❤ by GitHub

	#!/usr/bin/env python3
	import io , urllib
	from urllib.request import urlopen
	from html.parser import HTMLParser
	####################### SETTING ########################
	bank_url = "http://rate.bot.com.tw/xrt?Lang=zh-TW"
	####################### PAESER IMPLEMENT ###############
	class rateParser(HTMLParser):
	def __init__(self):
	HTMLParser.__init__(self)
	self.getData = False
	self.getCurrencyName = True
	self.countRate = 0
	self.lastTag = ""
	def handle_starttag(self , tag , attrs):
	self.lastTag = tag
	if tag == "td":
	self.getData = True;
	def handle_data(self , data):
	if self.getData == True:
	if self.lastTag == 'td' and self.countRate < 4:
	if data.strip() != "":
	print('{:7}\t '.format(data.strip()) , end='')
	self.countRate += 1
	if self.lastTag == 'div' and self.getCurrencyName == True:
	if data.strip() != "":
	print('{} \t '.format(data.strip()), end='')
	self.getCurrencyName = False
	def handle_endtag(self , tag):
	if tag == 'td' and self.getData == True:
	self.getData = False
	if tag == 'tr':
	if self.getCurrencyName == False:
	print("")
	self.getCurrencyName = True
	self.countRate = 0
	####################### MAIN ######################
	if __name__ == '__main__':
	response = urlopen(bank_url)#download html file
	rateParser().feed((response.read().decode('utf-8')))

view raw ExchangeRateCrawlerForPy3.py hosted with ❤ by GitHub