Created
January 22, 2017 14:42
-
-
Save anonymous/581b16a5d07746cc39cd4e46ad0a950f to your computer and use it in GitHub Desktop.
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/python | |
# -*- coding: utf-8 -*- | |
import re | |
import urllib2 | |
import csv | |
import pandas as pd | |
def GetHtmlcode(ID): | |
# Get the webpage's source html code | |
source = 'http://goodinfo.tw/StockInfo/StockDetail.asp?STOCK_ID=' | |
url = source + ID | |
print url | |
# Header | |
headers = { 'User-Agent' : 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/31.0.1650.63 Safari/537.36', | |
'Accept' : 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8', | |
'Accept-Charset' : 'Big5,utf-8;q=0.7,*;q=0.3', | |
#'Accept-Encoding' : 'gzip,deflate,sdch', | |
'Accept-Language' : 'zh-TW,zh;q=0.8,en-US;q=0.6,en;q=0.4,ja;q=0.2' , | |
'Cache-Control' : 'max-age=0', | |
'Connection' : 'keep-alive', | |
'Cookie' : '427 bytes were stripped', | |
'Host' : 'www.goodinfo.tw', | |
'Referer' : url } | |
req= urllib2.Request(url,"",headers) | |
response = urllib2.urlopen(req) | |
result = response.read().decode('utf-8') | |
return result | |
def main(): | |
page = GetHtmlcode('2103') | |
df=pd.read_html(page) | |
df2=pd.DataFrame(df[41]) | |
print df2 | |
print "\n\n" | |
df2 = df2[2:] ## 只要第二列之後 | |
print df2 | |
print df2.info() | |
print "\n\n" | |
df2.columns = df2.iloc[0] # 把第一列當作 columns 名稱 | |
print df2 | |
print "\n\n" | |
print df2.info() | |
if __name__ == "__main__": | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment