class Data(object):
def __init__(self, folder_path):
self.folder_path = folder_path
self.page_parse = PageParse()
self.content = None
def define_content(self, data_format):
self.content = data_format
def parsePage(self, pages):
self.page_parse.add_page(pages)
content = self.page_parse.parse()
return content
def parsePage(self, page):
reg = 'src="(.+?\.jpg)"'
imgre = re.compile(reg)
img_list = re.findall(imgre, page)
reg = 'href="(.+?\.html)"'
htmlre = re.compile(reg)
html_list = re.findall(htmlre, page)
return img_list, html_list
def download(self, file_list):
print("Contains images: {} ".format(len(file_list)))
for i in range(len(file_list)):
image_url = file_list[i]
image_name = image_url.split('/')[-1]
request.urlretrieve(image_url, self.folder_path+image_name)
def setup_class(cls):
page_xml = ''
with open('testdata/pageSource/pageSource.xml', 'r',
encoding='utf-8') as f:
for line in f.readlines():
page_xml += line
page = PageParse(page_xml)
cls.root = page.current_page_root
def get_page_info(self):
'''
Returns:
page: PageParse class instance.
current_activity: string
'''
current_page_source = self.get_page_source()
if not current_page_source:
self.driver.click_device_back()
# test: if after click back, still timeout, relaunch app.
try:
self.__get_page_source()
except FunctionTimedOut:
self.driver.launch_app()
log.warning('Get page source timeout, relaunch app.')
except WebDriverException:
log.warning('refresh appium driver')
self.init_appium()
finally:
return self.get_page_info()
else:
current_activity = self.driver.get_current_activity()
page = PageParse(current_page_source, current_activity)
return page
def test_page_parse_equal_str_error(self, path):
with pytest.raises(expected_exception=XMLSyntaxError):
page_xml_1 = self.get_page_xml(path)
page_xml_2 = "test"
page1 = PageParse(page_xml_1)
assert page1 != page_xml_2
def test_page_parse_not_equal_str(self, path):
page_xml_1 = self.get_page_xml(path[0])
page_xml_2 = self.get_page_xml(path[1])
page1 = PageParse(page_xml_1)
assert page1 != page_xml_2
def test_page_parse_equal_str(self, path):
page_xml = self.get_page_xml(path)
page1 = PageParse(page_xml)
assert page1 == page_xml
def test_page_parse_init(self):
page_xml = self.get_page_xml('testdata/pageSource/pageSource.xml')
page = PageParse(page_xml)
print(page)
def __init__(self, folder_path):
self.folder_path = folder_path
self.page_parse = PageParse()
self.content = None