blackteay/DrissionPage
1
0
Fork 0
mirror of https://gitee.com/g1879/DrissionPage.git synced 2024-12-10 04:00:23 +08:00
Code Issues Projects Releases Wiki Activity

优化s模式html和text，去除空格和回车，未完成

Browse Source
This commit is contained in:
g1879 2020-12-31 00:33:59 +08:00
parent 1badd08827
commit 5187a6b5b1
2 changed files with 28 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
DrissionPage/common.py
View File

@ -201,9 +201,12 @@ def _make_search_str(search_str: str) -> str:
return search_str return search_str
def format_html(text: str) -> str: def format_html(text: str, replace_space: bool = True) -> str:
"""处理html编码字符""" """处理html编码字符"""
return unescape(text).replace('\xa0', ' ') if text else text if text:
return unescape(text).replace('\xa0', ' ') if replace_space else unescape(text)
else:
return text
def translate_loc(loc: tuple) -> tuple: def translate_loc(loc: tuple) -> tuple:

31
DrissionPage/session_element.py
View File

@ -37,8 +37,15 @@ class SessionElement(DrissionElement):
def html(self) -> str: def html(self) -> str:
"""返回元素outerHTML文本""" """返回元素outerHTML文本"""
# tostring()会把跟紧元素的文本节点也带上，因此要去掉 # tostring()会把跟紧元素的文本节点也带上，因此要去掉
# print(tostring(self._inner_ele, method="html").decode())
html = format_html(tostring(self._inner_ele, method="html").decode()) html = format_html(tostring(self._inner_ele, method="html").decode())
# print(html)
return html[:html.rfind('>') + 1] return html[:html.rfind('>') + 1]
# return format_html(html[:html.rfind('>') + 1],False)
# def _html(self) -> str:
# html = tostring(self._inner_ele, method="html").decode()
# return html[:html.rfind('>') + 1]
@property @property
def inner_html(self) -> str: def inner_html(self) -> str:
@ -59,7 +66,19 @@ class SessionElement(DrissionElement):
@property @property
def text(self) -> str: def text(self) -> str:
"""返回元素内所有文本""" """返回元素内所有文本"""
return str(self._inner_ele.text_content()) html = format_html(tostring(self._inner_ele, method="html").decode(), False)
html = html[:html.rfind('>') + 1]
txt = re.sub(r'<.*?>', '', html).replace('\n', ' ')
txt = re.sub(r' {2,}', ' ', txt).strip()
# return format_html(txt)
return txt
# return t
# return str(self._inner_ele.text_content())
# return self._inner_ele.text_content()
# txt = str(self._inner_ele.text_content()).replace('\n', ' ')
@property @property
def link(self) -> str: def link(self) -> str:
@ -284,12 +303,6 @@ class SessionElement(DrissionElement):
ele = self ele = self
while ele: while ele:
# ele_id = ele.attr('id')
# if ele_id:
# return f'#{ele_id}{path_str}' if mode == 'css' else f'//{ele.tag}[@id="{ele_id}"]{path_str}'
# else:
if mode == 'css': if mode == 'css':
brothers = len(ele.eles(f'xpath:./preceding-sibling::*')) brothers = len(ele.eles(f'xpath:./preceding-sibling::*'))
path_str = f'>:nth-child({brothers + 1}){path_str}' path_str = f'>:nth-child({brothers + 1}){path_str}'
@ -357,7 +370,8 @@ def execute_session_find(page_or_ele,
page_or_ele = page_or_ele.inner_ele page_or_ele = page_or_ele.inner_ele
else: # 传入的是SessionPage对象 else: # 传入的是SessionPage对象
page = page_or_ele page = page_or_ele
page_or_ele = fromstring(page_or_ele.html) # page_or_ele = fromstring(page_or_ele.html)
page_or_ele = fromstring(page_or_ele.response.text, False)
try: try:
# 用lxml内置方法获取lxml的元素对象列表 # 用lxml内置方法获取lxml的元素对象列表
@ -368,6 +382,7 @@ def execute_session_find(page_or_ele,
else: else:
ele = page_or_ele.cssselect(loc[1]) ele = page_or_ele.cssselect(loc[1])
# 结果不是列表，如数字
if not isinstance(ele, list): if not isinstance(ele, list):
return ele return ele