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

支持异域iframe内元素截图，基本完成

Browse Source
This commit is contained in:
g1879 2023-03-05 22:59:41 +08:00
parent 6dda0886bc
commit 1550e8d673
5 changed files with 145 additions and 67 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

123
DrissionPage/chromium_base.py
View File

@ -631,60 +631,8 @@ class ChromiumBase(BasePage):
:param right_bottom: 截取范围右下角角坐标
:return: 图片完整路径或字节文本
"""
if as_bytes:
if as_bytes is True:
pic_type = 'png'
else:
if as_bytes not in ('jpg', 'jpeg', 'png', 'webp'):
raise ValueError("只能接收 'jpg', 'jpeg', 'png', 'webp' 四种格式。")
pic_type = 'jpeg' if as_bytes == 'jpg' else as_bytes
elif as_base64:
if as_base64 is True:
pic_type = 'png'
else:
if as_base64 not in ('jpg', 'jpeg', 'png', 'webp'):
raise ValueError("只能接收 'jpg', 'jpeg', 'png', 'webp' 四种格式。")
pic_type = 'jpeg' if as_base64 == 'jpg' else as_base64
else:
if not path:
path = f'{self.title}.jpg'
path = get_usable_path(path)
pic_type = path.suffix.lower()
if pic_type not in ('.jpg', '.jpeg', '.png', '.webp'):
raise TypeError(f'不支持的文件格式：{pic_type}。')
pic_type = 'jpeg' if pic_type == '.jpg' else pic_type[1:]
width, height = self.size
if full_page:
vp = {'x': 0, 'y': 0, 'width': width, 'height': height, 'scale': 1}
png = self.run_cdp_loaded('Page.captureScreenshot', format=pic_type,
captureBeyondViewport=True, clip=vp)['data']
else:
if left_top and right_bottom:
x, y = left_top
w = right_bottom[0] - x
h = right_bottom[1] - y
vp = {'x': x, 'y': y, 'width': w, 'height': h, 'scale': 1}
png = self.run_cdp_loaded('Page.captureScreenshot', format=pic_type,
captureBeyondViewport=False, clip=vp)['data']
else:
png = self.run_cdp_loaded('Page.captureScreenshot', format=pic_type)['data']
if as_base64:
return png
from base64 import b64decode
png = b64decode(png)
if as_bytes:
return png
path.parent.mkdir(parents=True, exist_ok=True)
with open(path, 'wb') as f:
f.write(png)
return str(path.absolute())
return self._get_screenshot(path=path, as_bytes=as_bytes, as_base64=as_base64,
full_page=full_page, left_top=left_top, right_bottom=right_bottom)
def clear_cache(self, session_storage=True, local_storage=True, cache=True, cookies=True):
"""清除缓存，可选要清除的项
@ -749,6 +697,73 @@ class ChromiumBase(BasePage):
return True
def _get_screenshot(self, path=None, as_bytes=None, as_base64=None,
full_page=False, left_top=None, right_bottom=None, ele=None):
"""对页面进行截图，可对整个网页、可见网页、指定范围截图。对可视范围外截图需要90以上版本浏览器支持
:param path: 完整路径，后缀可选 'jpg','jpeg','png','webp'
:param as_bytes: 是否以字节形式返回图片，可选 'jpg','jpeg','png','webp'，生效时path参数和as_base64参数无效
:param as_base64: 是否以base64字符串形式返回图片，可选 'jpg','jpeg','png','webp'，生效时path参数无效
:param full_page: 是否整页截图，为True截取整个网页，为False截取可视窗口
:param left_top: 截取范围左上角坐标
:param right_bottom: 截取范围右下角角坐标
:param ele: 为异域iframe内元素截图设置
:return: 图片完整路径或字节文本
"""
if as_bytes:
if as_bytes is True:
pic_type = 'png'
else:
if as_bytes not in ('jpg', 'jpeg', 'png', 'webp'):
raise ValueError("只能接收 'jpg', 'jpeg', 'png', 'webp' 四种格式。")
pic_type = 'jpeg' if as_bytes == 'jpg' else as_bytes
elif as_base64:
if as_base64 is True:
pic_type = 'png'
else:
if as_base64 not in ('jpg', 'jpeg', 'png', 'webp'):
raise ValueError("只能接收 'jpg', 'jpeg', 'png', 'webp' 四种格式。")
pic_type = 'jpeg' if as_base64 == 'jpg' else as_base64
else:
if not path:
path = f'{self.title}.jpg'
path = get_usable_path(path)
pic_type = path.suffix.lower()
if pic_type not in ('.jpg', '.jpeg', '.png', '.webp'):
raise TypeError(f'不支持的文件格式：{pic_type}。')
pic_type = 'jpeg' if pic_type == '.jpg' else pic_type[1:]
width, height = self.size
if full_page:
vp = {'x': 0, 'y': 0, 'width': width, 'height': height, 'scale': 1}
png = self.run_cdp_loaded('Page.captureScreenshot', format=pic_type,
captureBeyondViewport=True, clip=vp)['data']
else:
if left_top and right_bottom:
x, y = left_top
w = right_bottom[0] - x
h = right_bottom[1] - y
vp = {'x': x, 'y': y, 'width': w, 'height': h, 'scale': 1}
png = self.run_cdp_loaded('Page.captureScreenshot', format=pic_type,
captureBeyondViewport=False, clip=vp)['data']
else:
png = self.run_cdp_loaded('Page.captureScreenshot', format=pic_type)['data']
if as_base64:
return png
from base64 import b64decode
png = b64decode(png)
if as_bytes:
return png
path.parent.mkdir(parents=True, exist_ok=True)
with open(path, 'wb') as f:
f.write(png)
return str(path.absolute())
# ------------------准备废弃----------------------
def wait_loading(self, timeout=None):
"""阻塞程序，等待页面进入加载状态

7
DrissionPage/chromium_base.pyi
View File

@ -183,6 +183,13 @@ class ChromiumBase(BasePage):
left_top: Tuple[int, int] = None,
right_bottom: Tuple[int, int] = None) -> Union[str, bytes]: ...
def _get_screenshot(self, path: [str, Path] = None,
as_bytes: [bool, str] = None, as_base64: [bool, str] = None,
full_page: bool = False,
left_top: Tuple[int, int] = None,
right_bottom: Tuple[int, int] = None,
ele: ChromiumElement = None) -> Union[str, bytes]: ...
def clear_cache(self,
session_storage: bool = True,
local_storage: bool = True,

4
DrissionPage/chromium_element.py
View File

@ -485,8 +485,8 @@ class ChromiumElement(DrissionElement):
right_bottom = (left + width, top + height)
if not path:
path = f'{self.tag}.jpg'
return self.page.get_screenshot(path, as_bytes=as_bytes, as_base64=as_base64, full_page=False,
left_top=left_top, right_bottom=right_bottom)
return self.page._get_screenshot(path, as_bytes=as_bytes, as_base64=as_base64, full_page=False,
left_top=left_top, right_bottom=right_bottom, ele=self)
def input(self, vals, clear=True):
"""输入文本或组合键，也可用于输入文件路径到input元素（路径间用\n间隔）

65
DrissionPage/chromium_frame.py
View File

@ -7,6 +7,7 @@ from re import search
from time import sleep, perf_counter
from warnings import warn
from .commons.tools import get_usable_path
from .chromium_base import ChromiumBase, ChromiumPageScroll, ChromiumBaseSetter
from .chromium_element import ChromiumElement
@ -402,23 +403,73 @@ class ChromiumFrame(ChromiumBase):
self._check_ok()
return self.frame_ele.afters(filter_loc, timeout)
def get_screenshot(self, path=None, as_bytes=None, as_base64=None,
full_page=False, left_top=None, right_bottom=None):
def get_screenshot(self, path=None, as_bytes=None, as_base64=None):
"""对页面进行截图，可对整个网页、可见网页、指定范围截图。对可视范围外截图需要90以上版本浏览器支持
:param path: 完整路径，后缀可选 'jpg','jpeg','png','webp'
:param as_bytes: 是否以字节形式返回图片，可选 'jpg','jpeg','png','webp'，生效时path参数和as_base64参数无效
:param as_base64: 是否以base64字符串形式返回图片，可选 'jpg','jpeg','png','webp'，生效时path参数无效
:return: 图片完整路径或字节文本
"""
return self.frame_ele.get_screenshot(path=path, as_bytes=as_bytes, as_base64=as_base64)
def _get_screenshot(self, path=None, as_bytes: [bool, str] = None, as_base64: [bool, str] = None,
full_page=False, left_top=None, right_bottom=None, ele=None):
"""实现对元素截图
:param path: 完整路径，后缀可选 'jpg','jpeg','png','webp'
:param as_bytes: 是否以字节形式返回图片，可选 'jpg','jpeg','png','webp'，生效时path参数和as_base64参数无效
:param as_base64: 是否以base64字符串形式返回图片，可选 'jpg','jpeg','png','webp'，生效时path参数无效
:param full_page: 是否整页截图，为True截取整个网页，为False截取可视窗口
:param left_top: 截取范围左上角坐标
:param right_bottom: 截取范围右下角角坐标
:param ele: 为异域iframe内元素截图设置
:return: 图片完整路径或字节文本
"""
if full_page:
raise RuntimeError('暂未实现对iframe全页截图功能。')
if left_top is None and right_bottom is None:
return self.frame_ele.get_screenshot(path=path, as_bytes=as_bytes, as_base64=as_base64)
if not self._is_diff_domain:
return super().get_screenshot(path=path, as_bytes=as_bytes, as_base64=as_base64,
full_page=full_page, left_top=left_top, right_bottom=right_bottom)
else:
raise RuntimeError('暂未实现对异域iframe内元素截图功能。')
if as_bytes:
if as_bytes is True:
pic_type = 'png'
else:
if as_bytes not in ('jpg', 'jpeg', 'png', 'webp'):
raise ValueError("只能接收 'jpg', 'jpeg', 'png', 'webp' 四种格式。")
pic_type = 'jpeg' if as_bytes == 'jpg' else as_bytes
elif as_base64:
if as_base64 is True:
pic_type = 'png'
else:
if as_base64 not in ('jpg', 'jpeg', 'png', 'webp'):
raise ValueError("只能接收 'jpg', 'jpeg', 'png', 'webp' 四种格式。")
pic_type = 'jpeg' if as_base64 == 'jpg' else as_base64
else:
if not path:
path = f'{self.title}.jpg'
path = get_usable_path(path)
pic_type = path.suffix.lower()
if pic_type not in ('.jpg', '.jpeg', '.png', '.webp'):
raise TypeError(f'不支持的文件格式：{pic_type}。')
pic_type = 'jpeg' if pic_type == '.jpg' else pic_type[1:]
self.scroll.to_see(ele)
cx, cy = ele.locations.viewport_location
w, h = ele.size
img_data = f'data:image/{pic_type};base64,{self.frame_ele.get_screenshot(as_base64=True)}'
body = self.page('t:body')
first_child = body('c::first-child')
js = f'''
haskell = document.createElement('img');
haskell.src = "{img_data}";
arguments[0].insertBefore(haskell, this);
return haskell;'''
new_ele = first_child.run_js(js, body)
r = self.page.get_screenshot(path=path, as_bytes=as_bytes, as_base64=as_base64,
left_top=(cx, cy), right_bottom=(cx + w, cy + h))
self.page.remove_ele(new_ele)
return r
def _find_elements(self, loc_or_ele, timeout=None, single=True, relative=False, raise_err=None):
"""在frame内查找单个元素

13
DrissionPage/chromium_frame.pyi
View File

@ -152,10 +152,15 @@ class ChromiumFrame(ChromiumBase):
timeout: float = ...) -> List[Union[ChromiumElement, ChromiumFrame, str]]: ...
def get_screenshot(self, path: [str, Path] = None,
as_bytes: [bool, str] = None, as_base64: [bool, str] = None,
full_page: bool = False,
left_top: Tuple[int, int] = None,
right_bottom: Tuple[int, int] = None) -> Union[str, bytes]: ...
as_bytes: [bool, str] = None,
as_base64: [bool, str] = None) -> Union[str, bytes]: ...
def _get_screenshot(self, path: [str, Path] = None,
as_bytes: [bool, str] = None, as_base64: [bool, str] = None,
full_page: bool = False,
left_top: Tuple[int, int] = None,
right_bottom: Tuple[int, int] = None,
ele: ChromiumElement = None) -> Union[str, bytes]: ...
def _find_elements(self, loc_or_ele: Union[Tuple[str, str], str, ChromiumElement, ChromiumFrame],
timeout: float = None, single: bool = True, relative: bool = False, raise_err: bool = None) \