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

完善xpath处理，待测试

Browse Source
This commit is contained in:
g1879 2020-10-27 17:36:44 +08:00
parent 04112d95e0
commit 7cca3f8d06
1 changed files with 11 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
DrissionPage/session_element.py
View File

@ -37,8 +37,11 @@ class SessionElement(DrissionElement):
return unescape(self._inner_ele.text).replace('\xa0', ' ') return unescape(self._inner_ele.text).replace('\xa0', ' ')
def texts(self, text_node_only: bool = False) -> List[str]: def texts(self, text_node_only: bool = False) -> List[str]:
# TODO: 待补充 nodes = self.eles('xpath:./*/node()')
return [] if text_node_only:
return [x for x in nodes if isinstance(x, str)]
else:
return [x if isinstance(x, str) else x.text for x in nodes]
@property @property
def html(self) -> str: def html(self) -> str:
@ -246,13 +249,17 @@ def execute_session_find(page_or_ele: BaseParser,
try: try:
ele = None ele = None
if loc_by == 'xpath': if loc_by == 'xpath':
if 'PyQuery' in str(type(page_or_ele.element)) or '()' in loc_str.split('[')[0]: if 'PyQuery' in str(type(page_or_ele.element)):
# 从页面查找。后面的条件是处理./node()、./text()等xpath语句时用的 # or '()' in loc_str.split('[')[0]\
# or loc_str.split('/')[-1].startswith('@'):
# 从页面查找。第二个条件处理./node()、./text()等xpath语句，第三个条件处理获取属性的语句
ele = page_or_ele.xpath(loc_str) ele = page_or_ele.xpath(loc_str)
elif 'HtmlElement' in str(type(page_or_ele.element)): elif 'HtmlElement' in str(type(page_or_ele.element)):
# 从元素查找。Q_Q忘记了为什么要这样区分 # 从元素查找。Q_Q忘记了为什么要这样区分
elements = page_or_ele.element.xpath(loc_str) elements = page_or_ele.element.xpath(loc_str)
ele = [Element(element=e, url=page_or_ele.url) for e in elements] ele = [Element(element=e, url=page_or_ele.url) for e in elements]
if not ele:
ele = page_or_ele.xpath(loc_str)
else: # 用css selector获取 else: # 用css selector获取
ele = page_or_ele.find(loc_str) ele = page_or_ele.find(loc_str)