test/DrissionPage
1
0
Fork 0
mirror of https://gitee.com/g1879/DrissionPage.git synced 2024-11-29 18:47:34 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

增加了search()和search_all()

Browse Source
This commit is contained in:
g1879 2020-04-27 15:52:36 +08:00
parent cc272ed14a
commit 315cf6085a
9 changed files with 304 additions and 273 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
DrissionPage/config.py
View File

@ -10,17 +10,17 @@ Path(global_tmp_path).mkdir(parents=True, exist_ok=True)
global_driver_options = {
# ---------------已打开的浏览器---------------
# 'debuggerAddress': '127.0.0.1:9222',
'debuggerAddress': '127.0.0.1:9222',
# ---------------chromedriver路径---------------
'chromedriver_path': r'D:\python\Google Chrome\Chrome\chromedriver.exe',
# ---------------手动指定使用的浏览器位置---------------
# 'binary_location': r'C:\Program Files (x86)\Google\Chrome\Application\chrome.exe',
# ---------------启动参数---------------
'arguments': [
'--headless', # 隐藏浏览器窗口
# '--headless', # 隐藏浏览器窗口
'--mute-audio', # 静音
'--no-sandbox',
'--blink-settings=imagesEnabled=false', # 不加载图片
# '--blink-settings=imagesEnabled=false', # 不加载图片
# r'--user-data-dir="E:\tmp\chrome_tmp"', # 指定用户文件夹路径
# '-–disk-cache-dir=""', # 指定缓存路径
'zh_CN.UTF-8', # 编码格式

2
DrissionPage/drission.py
View File

@ -12,7 +12,7 @@ from selenium import webdriver
from selenium.common.exceptions import WebDriverException
from selenium.webdriver.chrome.options import Options
from DrissionPage.config import global_driver_options, global_session_options
from .config import global_driver_options, global_session_options
def _get_chrome_options(options: dict) -> Options:

20
DrissionPage/driver_page.py
View File

@ -95,7 +95,6 @@ class DriverPage(object):
elif mode == 'visible':
msg = '元素不可见或不存在'
ele = wait.until(EC.visibility_of_element_located(loc))
# print(loc,ele)
return ele
except:
if show_errmsg:
@ -105,6 +104,25 @@ class DriverPage(object):
"""查找符合条件的所有元素"""
return self.find(loc, mode='all', timeout=timeout, show_errmsg=show_errmsg)
def search(self, value: str, mode: str = None, timeout: float = 10):
mode = mode if mode else 'single'
if mode not in ['single', 'all']:
raise ValueError("mode须在'single', 'all'中选择")
ele = []
try:
loc = 'xpath', f'//*[contains(text(),"{value}")]'
wait = WebDriverWait(self.driver, timeout=timeout)
if mode == 'single':
ele = wait.until(EC.presence_of_element_located(loc))
elif mode == 'all':
ele = wait.until(EC.presence_of_all_elements_located(loc))
return ele
except:
return ele
def search_all(self, value: str, timeout: float = 10):
return self.search(value, mode='all', timeout=timeout)
def get_attr(self, loc_or_ele: Union[WebElement, tuple], attr: str) -> str:
"""获取元素属性"""
ele = self._get_ele(loc_or_ele)

224
DrissionPage/mix_element.py Normal file
View File

@ -0,0 +1,224 @@
#!/usr/bin/env python
# -*- coding:utf-8 -*-
import re
from html import unescape
from time import sleep
from typing import Union
from requests_html import Element
from selenium.webdriver.remote.webelement import WebElement
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.wait import WebDriverWait
from .config import global_tmp_path
from .session_page import _translate_loc
class MixElement(object):
def __init__(self, ele: Union[WebElement, Element]):
self._ele = ele
@property
def ele(self):
return self._ele
@property
def text(self):
if isinstance(self._ele, Element):
return unescape(self._ele.text).replace('\xa0', ' ')
else:
return unescape(self.attr('innerText')).replace('\xa0', ' ')
@property
def html(self):
if isinstance(self._ele, Element):
html = unescape(self._ele.html).replace('\xa0', ' ')
r = re.match(r'<.*?>(.*)</.*?>', html, flags=re.DOTALL)
return r.group(1)
else:
return unescape(self.attr('innerHTML')).replace('\xa0', ' ')
@property
def tag_name(self):
if isinstance(self._ele, Element):
html = unescape(self._ele.html).replace('\xa0', ' ')
r = re.match(r'^<(.*?)\s+', html, flags=re.DOTALL)
return r.group(1)
else:
return self._ele.tag_name
def attr(self, attr):
if isinstance(self._ele, Element):
try:
if attr == 'href':
# 如直接获取attr只能获取相对地址
for link in self._ele.absolute_links:
return link
elif attr == 'class':
class_str = ''
for key, i in enumerate(self._ele.attrs['class']):
class_str += ' ' if key > 0 else ''
class_str += i
return class_str
else:
return self._ele.attrs[attr]
except:
return ''
else:
return self._ele.get_attribute(attr)
def find(self, loc: tuple, mode: str = None, show_errmsg: bool = True):
"""根据loc获取元素"""
if isinstance(self._ele, Element):
mode = mode if mode else 'single'
if mode not in ['single', 'all']:
raise ValueError("mode须在'single', 'all'中选择")
loc_by, loc_str = _translate_loc(loc)
msg = first = None
try:
if mode == 'single':
msg = '未找到元素'
first = True
elif mode == 'all':
msg = '未找到元素s'
first = False
if loc_by == 'xpath':
ele = self.ele.xpath(loc_str, first=first, _encoding='utf-8')
else:
ele = self.ele.find(loc_str, first=first, _encoding='utf-8')
return MixElement(ele)
except:
if show_errmsg:
print(msg, loc)
raise
else: # d模式
mode = mode if mode else 'single'
if mode not in ['single', 'all', 'visible']:
raise ValueError("mode须在'single', 'all', 'visible'中选择")
msg = ele = None
try:
wait = WebDriverWait(self.ele.parent, timeout=10)
if mode == 'single':
msg = '未找到元素'
ele = wait.until(EC.presence_of_element_located(loc))
elif mode == 'all':
msg = '未找到元素s'
ele = wait.until(EC.presence_of_all_elements_located(loc))
elif mode == 'visible':
msg = '元素不可见或不存在'
ele = wait.until(EC.visibility_of_element_located(loc))
return MixElement(ele)
except:
if show_errmsg:
print(msg, loc)
def find_all(self, loc: tuple, show_errmsg: bool = True):
return self.find(loc, mode='all', show_errmsg=show_errmsg)
def search(self, value: str, mode: str = None):
"""根据内容获取元素"""
mode = mode if mode else 'single'
if mode not in ['single', 'all']:
raise ValueError("mode须在'single', 'all'中选择")
if isinstance(self._ele, Element):
try:
if mode == 'single':
ele = self.ele.xpath(f'.//*[contains(text(),"{value}")]', first=True)
return MixElement(ele)
elif mode == 'all':
eles = self.ele.xpath(f'.//*[contains(text(),"{value}")]')
return [MixElement(ele) for ele in eles]
except:
return None
else: # d模式
try:
loc = 'xpath', f'.//*[contains(text(),"{value}")]'
wait = WebDriverWait(self.ele.parent, timeout=10)
if mode == 'single':
ele = wait.until(EC.presence_of_element_located(loc))
return MixElement(ele)
elif mode == 'all':
eles = wait.until(EC.presence_of_all_elements_located(loc))
return [MixElement(ele) for ele in eles]
except:
return None
def search_all(self, value: str):
return self.search(value, mode='all')
# -----------------以下为d模式独占-------------------
def click(self):
"""点击"""
for _ in range(10):
try:
self.ele.click()
return True
except Exception as e:
print(e)
sleep(0.2)
# 若点击失败，用js方式点击
print('用js点击')
try:
self.run_script('arguments[0].click()')
return True
except:
raise
def input(self, value, clear: bool = True):
try:
if clear:
self.run_script("arguments[0].value=''")
self.ele.send_keys(value)
return True
except:
raise
def run_script(self, script: str):
self.ele.parent.execute_script(script, self.ele)
def submit(self):
self.ele.submit()
def clear(self):
self.ele.clear()
def is_selected(self):
return self.ele.is_selected()
def is_enabled(self):
return self.ele.is_enabled()
def is_displayed(self):
return self.ele.is_displayed()
@property
def size(self):
return self.ele.size
@property
def location(self):
return self.ele.location
def screenshot(self, path: str = None, filename: str = None):
path = path if path else global_tmp_path
name = filename if filename else self.tag_name
# 等待元素加载完成
if self.tag_name == 'img':
js = 'return arguments[0].complete && typeof arguments[0].naturalWidth ' \
'!= "undefined" && arguments[0].naturalWidth > 0'
while not self.run_script(js):
pass
img_path = f'{path}\\{name}.png'
self.ele.screenshot(img_path)
return img_path
def select(self, value: str):
pass
def set_attr(self, attr, value):
"""设置元素属性"""
try:
self.run_script(f"arguments[0].{attr} = '{value}';")
return True
except:
raise

18
DrissionPage/mix_page.py
View File

@ -12,9 +12,9 @@ from requests_html import Element, HTMLSession
from selenium.webdriver.chrome.webdriver import WebDriver
from selenium.webdriver.remote.webelement import WebElement
from DrissionPage.drission import Drission
from DrissionPage.driver_page import DriverPage
from DrissionPage.session_page import SessionPage
from .drission import Drission
from .driver_page import DriverPage
from .session_page import SessionPage
class Null(object):
@ -183,6 +183,18 @@ class MixPage(Null, SessionPage, DriverPage):
elif self._mode == 'd':
return super(SessionPage, self).find_all(loc, timeout=timeout, show_errmsg=show_errmsg)
def search(self, value: str, mode: str = None, timeout: float = 10):
if self._mode == 's':
return super().search(value, mode=mode)
elif self._mode == 'd':
return super(SessionPage, self).search(value, mode=mode, timeout=timeout)
def search_all(self, value: str, timeout: float = 10):
if self._mode == 's':
return super().search_all(value)
elif self._mode == 'd':
return super(SessionPage, self).search_all(value, timeout=timeout)
def get_attr(self, loc_or_ele: Union[WebElement, Element, tuple], attr: str) -> str:
"""获取元素属性值"""
if self._mode == 's':

232
DrissionPage/mix_page_old.py
View File

@ -1,232 +0,0 @@
#!/usr/bin/env python
# -*- coding:utf-8 -*-
"""
旧版MixPage，已弃用
在MixPage类中使用DriverPage和SessionPage对象，使用时根据模式调用相应对象的函数
问题是须要在MixPage类中为这两个类中的函数写一一对应的调用函数
新版中直接继承这两个类，只须要为这两个类共有的函数写调用函数即可
"""
from abc import abstractmethod
from typing import Union
from urllib import parse
from requests_html import Element
from selenium.webdriver.remote.webelement import WebElement
from DrissionPage.drission import Drission
from DrissionPage.driver_page import DriverPage
from DrissionPage.session_page import SessionPage
class MixPage:
def __init__(self, drission: Drission, locs=None, mode='d'):
self._drission = drission
self._session = None
self._driver = None
self._session_page = None
self._driver_page = None
self._url = None
self._session_url = None
self._locs = locs
self._mode = mode
if mode == 's':
self._session_page = self.s_page
else:
self._driver_page = self.d_page
self._open_self_url()
@abstractmethod
def _open_self_url(self):
pass
@property
def mode(self):
return self._mode
@mode.setter
def mode(self, value):
self._mode = value
def change_mode(self, mode=None):
if mode == self.mode:
return
self.mode = 's' if self.mode == 'd' else 'd'
@property
def drission(self):
return self._drission
@property
def response(self):
return self.s_page.response
@property
def session(self):
if self._session is None:
self._session = self._drission.session
return self._session
@property
def driver(self):
if self._driver is None:
self._driver = self._drission.driver
return self._driver
@property
def d_page(self):
if self._driver_page is None:
self._driver_page = DriverPage(self.driver)
if self._url:
self._init_page()
return self._driver_page
@property
def s_page(self):
if self._session_page is None:
self._session_page = SessionPage(self.session)
if self._url:
self._init_page()
self.refresh_url() # 每次调用session页面时，使url和driver页面保持一致
return self._session_page
@property
def url(self):
if self.mode == 'd':
return self.d_page.url
else:
return self._url
def _init_page(self):
if self._session_page:
self.cookies_to_driver(self._url)
self.d_page.get(self._url)
elif self._driver_page:
self.cookies_to_session()
self.s_page.get(self._url)
def goto(self, url: str, url_data: dict = None):
"""跳转到一个url"""
to_url = f'{url}?{parse.urlencode(url_data)}' if url_data else url
if self._url == to_url:
return
now_url = self._url
self._url = to_url
if self._driver_page:
if self._session_page:
self.cookies_to_driver(now_url)
self._driver_page.get(to_url, url_data)
if not self._session_page:
return self.check_driver_url()
if self._session_page:
self._session_url = to_url
if self._session_page:
self.cookies_to_session()
return self.s_page.goto(to_url, url_data)
def check_driver_url(self) -> bool:
"""由子类依据不同的页面自行实现"""
return True
def refresh_url(self):
"""使session的url与driver当前保持一致，并复制cookies到session"""
if self._driver and (self._url != self._driver.current_url or self._session_url != self._driver.current_url):
self._url = self._driver.current_url
self._session_url = self._driver.current_url
self.cookies_to_session()
self._session_page.get(self._url)
def cookies_to_session(self):
self._drission.cookies_to_session()
def cookies_to_driver(self, url=None):
u = url if url else self._url
self._drission.cookies_to_driver(u)
# ----------------以下为共用函数-----------------------
def find(self, loc, timeout=10, show_errmsg=True) -> Union[WebElement, Element]:
if self._mode == 's':
return self.s_page.find(loc, show_errmsg)
elif self._mode == 'd':
return self.d_page.find(loc, timeout, show_errmsg)
def find_all(self, loc, timeout=10, show_errmsg=True) -> list:
if self._mode == 's':
return self.s_page.find_all(loc, show_errmsg)
elif self._mode == 'd':
return self.d_page.find_all(loc, timeout, show_errmsg)
def get_attr(self, loc_or_ele, attr) -> str:
if self._mode == 's':
return self.s_page.get_attr(loc_or_ele, attr)
elif self._mode == 'd':
return self.d_page.get_attr(loc_or_ele, attr)
def get_html(self, loc_or_ele) -> str:
if self._mode == 's':
return self.s_page.get_html(loc_or_ele)
elif self._mode == 'd':
return self.d_page.get_html(loc_or_ele)
def get_text(self, loc_or_ele) -> str:
if self._mode == 's':
return self.s_page.get_text(loc_or_ele)
elif self._mode == 'd':
return self.d_page.get_text(loc_or_ele)
def get_source(self):
if self._mode == 's':
return self.s_page.get_html()
elif self._mode == 'd':
return self.d_page.get_html()
def get_cookies(self):
if self._mode == 's':
return self.s_page.cookies
elif self._mode == 'd':
return self.d_page.cookies
# ----------------以下为driver page专用函数-----------------
def input(self, loc_or_ele, value: str, clear=True) -> bool:
return self.d_page.input(loc_or_ele, value, clear)
def click(self, loc_or_ele) -> bool:
return self.d_page.click(loc_or_ele)
def set_attr(self, loc_or_ele, attribute: str, value: str) -> bool:
return self.d_page.set_attr(loc_or_ele, attribute, value)
def run_script(self, loc_or_ele, script: str):
return self.d_page.run_script(loc_or_ele, script)
def get_tabs_sum(self) -> int:
return self.d_page.get_tabs_sum()
def get_tab_num(self) -> int:
return self.d_page.get_tab_num()
def to_tab(self, index: int = 0):
return self.d_page.to_tab(index)
def close_current_tab(self):
return self.d_page.close_current_tab()
def close_other_tabs(self, tab_index: int = None):
return self.d_page.close_other_tabs(tab_index)
def to_iframe(self, loc_or_ele):
return self.d_page.to_iframe(loc_or_ele)
def get_screen(self, loc_or_ele, path: str, file_name: str = None) -> str:
return self.d_page.get_screen(loc_or_ele, path, file_name)
def choose_select_list(self, loc_or_ele, text):
return self.d_page.choose_select_list(loc_or_ele, text)
def refresh(self):
return self.d_page.refresh()
def back(self):
return self.d_page.back()
def set_window_size(self, x: int = None, y: int = None):
return self.d_page.set_window_size(x, y)

19
DrissionPage/session_page.py
View File

@ -11,7 +11,7 @@ from urllib import parse
from requests_html import Element, HTMLSession, HTMLResponse
from DrissionPage.config import global_session_options
from .config import global_session_options
def _translate_loc(loc):
@ -115,6 +115,23 @@ class SessionPage(object):
"""查找符合条件的所有元素"""
return self.find(loc, mode='all', show_errmsg=True)
def search(self, value: str, mode: str = None):
mode = mode if mode else 'single'
if mode not in ['single', 'all']:
raise ValueError("mode须在'single', 'all'中选择")
try:
if mode == 'single':
ele = self.response.html.xpath(f'.//*[contains(text(),"{value}")]', first=True)
return ele
elif mode == 'all':
eles = self.response.html.xpath(f'.//*[contains(text(),"{value}")]')
return eles
except:
return None
def search_all(self, value: str):
return self.search(value, mode='all')
def _get_ele(self, loc_or_ele: Union[Element, tuple]) -> Element:
"""获取loc或元素实例，返回元素实例"""
# ======================================

32
README.md
View File

@ -2,36 +2,6 @@
#### 介绍
一个整合了selenium和requests_html的模块，封装了常用页面操作，可实现两种模式的无缝切换。兼顾selenium的易用性和requests的高性能，也可直接用于PO模式。
#### 软件架构
软件架构说明
适用于网页自动化，有效减少代码量。
#### 安装教程
1. xxxx
2. xxxx
3. xxxx
#### 使用说明
1. xxxx
2. xxxx
3. xxxx
#### 参与贡献
1. Fork 本仓库
2. 新建 Feat_xxx 分支
3. 提交代码
4. 新建 Pull Request
#### 码云特技
1. 使用 Readme\_XXX.md 来支持不同的语言，例如 Readme\_en.md, Readme\_zh.md
2. 码云官方博客 [blog.gitee.com](https://blog.gitee.com)
3. 你可以 [https://gitee.com/explore](https://gitee.com/explore) 这个地址来了解码云上的优秀开源项目
4. [GVP](https://gitee.com/gvp) 全称是码云最有价值开源项目，是码云综合评定出的优秀开源项目
5. 码云官方提供的使用手册 [https://gitee.com/help](https://gitee.com/help)
6. 码云封面人物是一档用来展示码云会员风采的栏目 [https://gitee.com/gitee-stars/](https://gitee.com/gitee-stars/)

22
setup.py Normal file
View File

@ -0,0 +1,22 @@
#!/usr/bin/env python
# -*- coding:utf-8 -*-
from setuptools import setup, find_packages
setup(
name="DrissionPage",
version="1.0.0 Alpha",
author="g1879",
author_email="g1879@qq.com",
description="page contains selenium and requests.",
license="BSD",
keywords="DrissionPage",
url="https://gitee.com/g1879/DrissionPage",
packages=find_packages(),
long_description="Long descrition is actually short...",
classifiers=[
"Development Status :: 1 - Alpha",
"Topic :: Utilities",
"License :: OSI Approved :: BSD License",
],
)