抓取天天基金网上的基金净值
fund1.py
# -*- coding: utf-8 -*-
import os, sys
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support.ui import Select
from selenium.common.exceptions import NoSuchElementException
from selenium.common.exceptions import NoAlertPresentException
import unittest, time, re
class ParametrizedTestCase(unittest.TestCase):
""" TestCase classes that want to be parametrized should
inherit from this class.
"""
def __init__(self, methodName='runTest', param=None):
super(ParametrizedTestCase, self).__init__(methodName)
self.param = param
@staticmethod
def parametrize(testcase_klass, param=None):
""" Create a suite containing all tests taken from the given
subclass, passing them the parameter 'param'.
"""
testloader = unittest.TestLoader()
testnames = testloader.getTestCaseNames(testcase_klass)
suite = unittest.TestSuite()
for name in testnames:
suite.addTest(testcase_klass(name, param=param))
return suite
class Fund(ParametrizedTestCase):
def setUp(self):
ch_driver = os.path.abspath(r"D:\selenium\chromedriver.exe")
os.environ["webdriver.chrome.driver"]= ch_driver
self.driver = webdriver.Chrome()
self.driver.implicitly_wait(30)
self.base_url = "http://fund.eastmoney.com"
self.verificationErrors = []
self.accept_next_alert = True
print self.param
self.fp = open(self.param+'.txt','w')
def test_fund(self):
f1 = self.param
fp = self.fp
driver = self.driver
driver.get(self.base_url + "/f10/jjjz_%s.html" % (f1))
assert f1 in driver.title
try:
div = driver.find_element_by_id("jztable")
table = div.find_elements_by_tag_name("table")
tbody = table[0].find_elements_by_tag_name("tbody")
t_rows = tbody[0].find_elements_by_tag_name('tr')
for row in t_rows:
fp.write(f1+' ')
tds = row.find_elements_by_tag_name('td')
for td in tds[0:4]:
fp.write(td.text +' ')
fp.write('\n')
except Exception as msg:
print msg
#
def is_element_present(self, how, what):
try: self.driver.find_element(by=how, value=what)
except NoSuchElementException as e: return False
return True
def is_alert_present(self):
try: self.driver.switch_to_alert()
except NoAlertPresentException as e: return False
return True
def close_alert_and_get_its_text(self):
try:
alert = self.driver.switch_to_alert()
alert_text = alert.text
if self.accept_next_alert:
alert.accept()
else:
alert.dismiss()
return alert_text
finally: self.accept_next_alert = True
def tearDown(self):
self.fp.close()
self.driver.quit()
self.assertEqual([], self.verificationErrors)
if len(sys.argv) ==2:
f1 = sys.argv[1]
if len(f1) !=6:
sys.exit(2)
## unittest 单元测试框架 改传参数
suite = unittest.TestSuite()
suite.addTest(ParametrizedTestCase.parametrize(Fund, param=f1))
unittest.TextTestRunner(verbosity=2).run(suite)
else:
print ' usage: fund1.py fundcode '
sys.exit(1)
例如:python fund1.py 150103

本教程通过Python Selenium实现从天天基金网上自动抓取特定基金的历史净值数据,并保存到本地文件中。该程序首先打开指定基金的网页,定位到净值表格,然后逐行读取并记录数据。

被折叠的 条评论
为什么被折叠?



