def get_html_data(self, html_name):
try:
with codecs.open(os.path.join(self.html_Path, html_name), "r",
"utf-8") as f:
content = f.read()
# 获取html树，通过xpath获取指定内容
tree = etree.HTML(content)
node = tree.xpath("//div[@class='content']")[0]
node.text.encoding('gbk')
# 通过正则表达式 获取<tr></tr>之间指定的内容
res_tr = r'<tr>(.*?)</tr>'
m_tr = re.findall(res_tr, content, re.S | re.M)
for line in m_tr:
print(line)
#获取表格第一列th 属性
res_th = r'<th>(.*?)</th>'
m_th = re.findall(res_th, line, re.S | re.M)
for mm in m_th:
print(unicode(mm, 'utf-8')) #unicode防止乱
# #获取表格第二列td 属性值
res_td = r'<td>(.*?)</td>'
m_td = re.findall(res_td, line, re.S | re.M)
for nn in m_td:
print(unicode(nn, 'utf-8'))
except Exception as e:
print(e)
def test_stylenames():
class my:
class body(html.body):
style = html.Style(font_size="12pt")
u = unicode(my.body())
assert u == '<body style="font-size: 12pt"></body>'
def test_tag_with_subclassed_attr_simple():
class my(ns.hello):
class Attr(ns.hello.Attr):
hello="world"
x = my()
assert x.attr.hello == 'world'
assert unicode(x) == '<my hello="world"/>'
def test_tag_with_subclassed_attr_simple():
class my(ns.hello):
class Attr(ns.hello.Attr):
hello = "world"
x = my()
assert x.attr.hello == 'world'
assert unicode(x) == '<my hello="world"/>'
def test_alternating_style():
alternating = (
html.Style(background="white"),
html.Style(background="grey"),
)
class my(html):
class li(html.li):
def style(self):
i = self.parent.index(self)
return alternating[i % 2]
style = property(style)
x = my.ul(my.li("hello"), my.li("world"), my.li("42"))
u = unicode(x)
assert u == ('<ul><li style="background: white">hello</li>'
'<li style="background: grey">world</li>'
'<li style="background: white">42</li>'
'</ul>')
def test_alternating_style():
alternating = (
html.Style(background="white"),
html.Style(background="grey"),
)
class my(html):
class li(html.li):
def style(self):
i = self.parent.index(self)
return alternating[i%2]
style = property(style)
x = my.ul(
my.li("hello"),
my.li("world"),
my.li("42"))
u = unicode(x)
assert u == ('<ul><li style="background: white">hello</li>'
'<li style="background: grey">world</li>'
'<li style="background: white">42</li>'
'</ul>')
def test_html_name_stickyness():
class my(html.p):
pass
x = my("hello")
assert unicode(x) == '<p>hello</p>'
def test_raw():
x = ns.some(py.xml.raw("<p>literal</p>"))
u = unicode(x)
assert u == "<some><p>literal</p></some>"
def test_class_None():
t = html.body(class_=None)
u = unicode(t)
assert u == '<body></body>'
def test_tag_with_text_and_attributes():
x = ns.some(name="hello", value="world")
assert x.attr.name == 'hello'
assert x.attr.value == 'world'
u = unicode(x)
assert u == '<some name="hello" value="world"/>'
def test_tag_with_text_and_attributes():
x = ns.some(name="hello", value="world")
assert x.attr.name == 'hello'
assert x.attr.value == 'world'
u = unicode(x)
assert u == '<some name="hello" value="world"/>'
def test_singleton():
h = html.head(html.link(href="foo"))
assert unicode(h) == '<head><link href="foo"/></head>'
h = html.head(html.script(src="foo"))
assert unicode(h) == '<head><script src="foo"></script></head>'
def test_tag_with_text_entity():
x = ns.hello('world & rest')
u = unicode(x)
assert u == "<hello>world & rest</hello>"
def test_tag_xmlname():
class my(ns.hello):
xmlname = 'world'
u = unicode(my())
assert u == '<world/>'
def test_list_nested():
x = ns.hello([ns.world()]) #pass in a list here
u = unicode(x)
assert u == '<hello><world/></hello>'
def test_tag_nested():
x = ns.hello(ns.world())
unicode(x) # triggers parentifying
assert x[0].parent is x
u = unicode(x)
assert u == '<hello><world/></hello>'
def test_tag_with_raw_attr():
x = html.object(data=raw('&'))
assert unicode(x) == '<object data="&"></object>'
def test_singleton():
h = html.head(html.link(href="foo"))
assert unicode(h) == '<head><link href="foo"/></head>'
h = html.head(html.script(src="foo"))
assert unicode(h) == '<head><script src="foo"></script></head>'
def test_class_None():
t = html.body(class_=None)
u = unicode(t)
assert u == '<body></body>'
def test_tag_with_raw_attr():
x = html.object(data=raw('&'))
assert unicode(x) == '<object data="&"></object>'
def test_list_nested():
x = ns.hello([ns.world()]) #pass in a list here
u = unicode(x)
assert u == '<hello><world/></hello>'
def test_tag_with_text():
x = ns.hello("world")
u = unicode(x)
assert u == "<hello>world</hello>"
def test_tag_with_text_entity():
x = ns.hello('world & rest')
u = unicode(x)
assert u == "<hello>world & rest</hello>"
def test_tag_with_text_and_attributes_entity():
x = ns.some(name="hello & world")
assert x.attr.name == "hello & world"
u = unicode(x)
assert u == '<some name="hello & world"/>'
def test_tag_with_text():
x = ns.hello("world")
u = unicode(x)
assert u == "<hello>world</hello>"
def test_tag_nested():
x = ns.hello(ns.world())
unicode(x) # triggers parentifying
assert x[0].parent is x
u = unicode(x)
assert u == '<hello><world/></hello>'
def test_raw():
x = ns.some(py.xml.raw("<p>literal</p>"))
u = unicode(x)
assert u == "<some><p>literal</p></some>"
def test_tag_xmlname():
class my(ns.hello):
xmlname = 'world'
u = unicode(my())
assert u == '<world/>'
def test_html_name_stickyness():
class my(html.p):
pass
x = my("hello")
assert unicode(x) == '<p>hello</p>'
def test_tag_with_text_and_attributes_entity():
x = ns.some(name="hello & world")
assert x.attr.name == "hello & world"
u = unicode(x)
assert u == '<some name="hello & world"/>'
def test_stylenames():
class my:
class body(html.body):
style = html.Style(font_size = "12pt")
u = unicode(my.body())
assert u == '<body style="font-size: 12pt"></body>'