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

DriverElement和SessionElement增加link属性

Browse Source
This commit is contained in:
g1879 2020-11-13 00:09:01 +08:00
parent eb866ba29e
commit 70cc8da88d
4 changed files with 279 additions and 228 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
DrissionPage/driver_element.py
View File

@ -32,6 +32,13 @@ class DriverElement(DrissionElement):
loc_or_str: Union[Tuple[str, str], str], loc_or_str: Union[Tuple[str, str], str],
mode: str = 'single', mode: str = 'single',
timeout: float = None): timeout: float = None):
"""实现查找元素的简化写法 \n
例：ele2 = ele1('@id=ele_id') \n
:param loc_or_str: 元素的定位信息，可以是loc元组，或查询字符串
:param mode: 'single' 或 'all'，对应查找一个或全部
:param timeout: 超时时间
:return: DriverElement对象
"""
return self.ele(loc_or_str, mode, timeout or self.timeout) return self.ele(loc_or_str, mode, timeout or self.timeout)
# -----------------共有属性------------------- # -----------------共有属性-------------------
@ -74,6 +81,11 @@ class DriverElement(DrissionElement):
"""返回元素内所有文本""" """返回元素内所有文本"""
return self.attr('innerText') return self.attr('innerText')
@property
def link(self) -> str:
"""返回href或src绝对url"""
return self.attr('href') or self.attr('src')
@property @property
def css_path(self) -> str: def css_path(self) -> str:
"""返回当前元素的css路径""" """返回当前元素的css路径"""
@ -212,15 +224,6 @@ class DriverElement(DrissionElement):
raise ValueError('Argument loc_or_str can only be tuple or str.') raise ValueError('Argument loc_or_str can only be tuple or str.')
loc_str = loc_or_str[1] loc_str = loc_or_str[1]
# if loc_or_str[0] == 'xpath':
# # 处理语句最前面的(
# brackets = len(re.match(r'\(*', loc_or_str[1]).group(0))
# bracket, loc_str = '(' * brackets, loc_or_str[1][brackets:]
#
# # 确保查询语句最前面是.
# loc_str = loc_str if loc_str.startswith(('.', '/')) else f'.//{loc_str}'
# loc_str = loc_str if loc_str.startswith('.') else f'.{loc_str}'
# loc_str = f'{bracket}{loc_str}'
if loc_or_str[0] == 'xpath' and loc_or_str[1].lstrip().startswith('/'): if loc_or_str[0] == 'xpath' and loc_or_str[1].lstrip().startswith('/'):
loc_str = f'.{loc_str}' loc_str = f'.{loc_str}'

38
DrissionPage/session_element.py
View File

@ -26,6 +26,12 @@ class SessionElement(DrissionElement):
return f'<SessionElement {self.tag} {" ".join(attrs)}>' return f'<SessionElement {self.tag} {" ".join(attrs)}>'
def __call__(self, loc_or_str: Union[Tuple[str, str], str], mode: str = 'single'): def __call__(self, loc_or_str: Union[Tuple[str, str], str], mode: str = 'single'):
"""实现查找元素的简化写法 \n
例：ele2 = ele1('@id=ele_id') \n
:param loc_or_str: 元素的定位信息，可以是loc元组，或查询字符串
:param mode: 'single' 或 'all'，对应查找一个或全部
:return: SessionElement对象
"""
return self.ele(loc_or_str, mode) return self.ele(loc_or_str, mode)
@property @property
@ -53,7 +59,12 @@ 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 self._inner_ele.text_content() return str(self._inner_ele.text_content())
@property
def link(self) -> str:
"""返回href或src绝对url"""
return self.attr('href') or self.attr('src')
@property @property
def css_path(self) -> str: def css_path(self) -> str:
@ -133,8 +144,8 @@ class SessionElement(DrissionElement):
if attr == 'href': if attr == 'href':
link = self.inner_ele.get('href') link = self.inner_ele.get('href')
# 若链接为js或邮件，直接返回 # 若为链接为None、js或邮件，直接返回
if link.lower().startswith(('javascript:', 'mailto:')): if not link or link.lower().startswith(('javascript:', 'mailto:')):
return link return link
# 其它情况直接返回绝对url # 其它情况直接返回绝对url
@ -193,12 +204,6 @@ class SessionElement(DrissionElement):
element = self element = self
loc_str = loc_or_str[1] loc_str = loc_or_str[1]
# if loc_or_str[0] == 'xpath':
# brackets = len(re.match(r'\(*', loc_or_str[1]).group(0))
# bracket, loc_str = '(' * brackets, loc_or_str[1][brackets:]
# loc_str = loc_str if loc_str.startswith(('.', '/')) else f'.//{loc_str}'
# loc_str = loc_str if loc_str.startswith('.') else f'.{loc_str}'
# loc_str = f'{bracket}{loc_str}'
if loc_or_str[0] == 'xpath' and loc_or_str[1].lstrip().startswith('/'): if loc_or_str[0] == 'xpath' and loc_or_str[1].lstrip().startswith('/'):
loc_str = f'.{loc_str}' loc_str = f'.{loc_str}'
@ -239,8 +244,14 @@ class SessionElement(DrissionElement):
return self.ele(loc_or_str, mode='all') return self.ele(loc_or_str, mode='all')
# -----------------私有函数------------------- # -----------------私有函数-------------------
def _make_absolute(self, link): def _make_absolute(self, link) -> str:
"""生成绝对url""" """获取绝对url
:param link: 超链接
:return: 绝对链接
"""
if not link:
return link
parsed = urlparse(link)._asdict() parsed = urlparse(link)._asdict()
# 相对路径，与页面url拼接并返回 # 相对路径，与页面url拼接并返回
@ -257,7 +268,10 @@ class SessionElement(DrissionElement):
return link return link
def _get_ele_path(self, mode) -> str: def _get_ele_path(self, mode) -> str:
"""获取css路径或xpath路径""" """获取css路径或xpath路径
:param mode: 'css' 或 'xpath'
:return: css路径或xpath路径
"""
path_str = '' path_str = ''
ele = self ele = self

397
README.en.md
View File

@ -215,7 +215,7 @@ with open(f'{save_path}\\img.png','wb') as fd:
fd.write(chunk) fd.write(chunk)
# Use DrissionPage: # Use DrissionPage:
page.download(url, save_path,'img') # Support renaming and handle file name conflicts page.download(url, save_path,'img') # Support renaming and handle file name conflicts
``` ```
@ -225,14 +225,14 @@ page.download(url, save_path,'img') # Support renaming and handle file name conf
Log in to the website with selenium, and then switch to requests to read the web page. Both will share login information. Log in to the website with selenium, and then switch to requests to read the web page. Both will share login information.
```python ```python
page = MixPage() # Create page object, default driver mode page = MixPage() # Create page object, default driver mode
page.get('https://gitee.com/profile') # Visit the personal center page (not logged in, redirect to the login page) page.get('https://gitee.com/profile') # Visit the personal center page (not logged in, redirect to the login page)
page.ele('@id:user_login').input('your_user_name') # Use selenium to enter the account password to log in page.ele('@id:user_login').input('your_user_name') # Use selenium to enter the account password to log in
page.ele('@id:user_password').input('your_password\n') page.ele('@id:user_password').input('your_password\n')
page.change_mode() # Switch to session mode page.change_mode() # Switch to session mode
print('Title after login:', page.title,'\n') # session mode output after login print('Title after login:', page.title,'\n') # session mode output after login
``` ```
Output: Output:
@ -247,11 +247,11 @@ Title after login: Personal Information- Code Cloud Gitee.com
```python ```python
# Connect the previous code # Connect the previous code
foot = page.ele('@id:footer- left') # find element by id foot = page.ele('@id:footer- left') # find element by id
first_col = foot.ele('css:>div') # Use the css selector to find the element in the lower level of the element (the first one) first_col = foot.ele('css:>div') # Use the css selector to find the element in the lower level of the element (the first one)
lnk = first_col.ele('text: Command Learning') # Use text content to find elements lnk = first_col.ele('text: Command Learning') # Use text content to find elements
text = lnk.text # Get element text text = lnk.text # Get element text
href = lnk.attr('href') # Get element attribute value href = lnk.attr('href') # Get element attribute value
print(text, href,'\n') print(text, href,'\n')
@ -318,8 +318,8 @@ If you choose the third method, please run these lines of code before using this
```python ```python
from DrissionPage.easy_set import set_paths from DrissionPage.easy_set import set_paths
driver_path ='D:\\chrome\\chromedriver.exe' # Your chromedriver.exe path, optional driver_path ='D:\\chrome\\chromedriver.exe' # Your chromedriver.exe path, optional
chrome_path ='D:\\chrome\\chrome.exe' # Your chrome.exe path, optional chrome_path ='D:\\chrome\\chrome.exe' # Your chrome.exe path, optional
set_paths(driver_path, chrome_path) set_paths(driver_path, chrome_path)
``` ```
@ -341,11 +341,11 @@ After passing the check, you can use the driver mode normally.
In addition to the above two paths, this method can also set the following paths: In addition to the above two paths, this method can also set the following paths:
```python ```python
debugger_address # Debug browser address, such as: 127.0.0.1:9222 debugger_address # Debug browser address, such as: 127.0.0.1:9222
download_path # Download file path download_path # Download file path
global_tmp_path # Temporary folder path global_tmp_path # Temporary folder path
user_data_path # User data path user_data_path # User data path
cache_path # cache path cache_path # cache path
``` ```
Tips: Tips:
@ -377,12 +377,12 @@ To manually pass in the configuration:
# Create with the incoming configuration information (ignore the ini file) # Create with the incoming configuration information (ignore the ini file)
from DrissionPage.config import DriverOptions from DrissionPage.config import DriverOptions
driver_options = DriverOptions() # Create driver configuration object driver_options = DriverOptions() # Create driver configuration object
driver_options.binary_location ='D:\\chrome\\chrome.exe' # chrome.exe path driver_options.binary_location ='D:\\chrome\\chrome.exe' # chrome.exe path
session_options = {'headers': {'User- Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6)'}} session_options = {'headers': {'User- Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6)'}}
driver_path ='D:\\chrome\\chromedriver.exe' # driver_path path driver_path ='D:\\chrome\\chromedriver.exe' # driver_path path
drission = Drission(driver_options, session_options, driver_path) # incoming configuration drission = Drission(driver_options, session_options, driver_path) # incoming configuration
``` ```
@ -405,10 +405,10 @@ page = MixPage('s')
# Create by passing in the Drission object # Create by passing in the Drission object
page = MixPage(drission) page = MixPage(drission)
page = MixPage(drission, mode='s', timeout=5) # session mode, waiting time is 5 seconds (default 10 seconds) page = MixPage(drission, mode='s', timeout=5) # session mode, waiting time is 5 seconds (default 10 seconds)
# Create with incoming configuration information # Create with incoming configuration information
page = MixPage(driver_options=DriverOption, session_options=SessionOption) # default d mode page = MixPage(driver_options=DriverOption, session_options=SessionOption) # default d mode
``` ```
@ -420,7 +420,7 @@ If there is an error in the connection, the program will automatically retry twi
```python ```python
# Default mode # Default mode
page.get(url) page.get(url)
page.post(url, data, **kwargs) # Only session mode has post method page.post(url, data, **kwargs) # Only session mode has post method
# Specify the number of retries and interval # Specify the number of retries and interval
page.get(url, retry=5, interval=0.5) page.get(url, retry=5, interval=0.5)
@ -433,7 +433,7 @@ page.get(url, retry=5, interval=0.5)
Switch between s and d modes, the cookies and the URL you are visiting will be automatically synchronized when switching. Switch between s and d modes, the cookies and the URL you are visiting will be automatically synchronized when switching.
```python ```python
page.change_mode(go=False) # If go is False, it means that the url is not redirected page.change_mode(go=False) # If go is False, it means that the url is not redirected
``` ```
@ -441,20 +441,20 @@ page.change_mode(go=False) # If go is False, it means that the url is not redire
### Page properties ### Page properties
```python ```python
page.url # currently visited url page.url # currently visited url
page.mode # current mode page.mode # current mode
page.drission # Dirssion object currently in use page.drission # Dirssion object currently in use
page.driver # WebDirver object currently in use page.driver # WebDirver object currently in use
page.session # Session object currently in use page.session # Session object currently in use
page.cookies # Get cookies information page.cookies # Get cookies information
page.html # Page source code page.html # Page source code
page.title # Current page title page.title # Current page title
# d mode unique: # d mode unique:
page.tabs_count # Return the number of tab pages page.tabs_count # Return the number of tab pages
page.tab_handles # Return to the handle list of all tabs page.tab_handles # Return to the handle list of all tabs
page.current_tab_num # Return the serial number of the current tab page page.current_tab_num # Return the serial number of the current tab page
page.current_tab_handle # Return to the current tab page handle page.current_tab_handle # Return to the current tab page handle
``` ```
@ -464,36 +464,36 @@ page.current_tab_handle # Return to the current tab page handle
When calling a method that only belongs to d mode, it will automatically switch to d mode. See APIs for detailed usage. When calling a method that only belongs to d mode, it will automatically switch to d mode. See APIs for detailed usage.
```python ```python
page.change_mode() # switch mode page.change_mode() # switch mode
page.cookies_to_session() # Copy cookies from WebDriver object to Session object page.cookies_to_session() # Copy cookies from WebDriver object to Session object
page.cookies_to_driver() # Copy cookies from Session object to WebDriver object page.cookies_to_driver() # Copy cookies from Session object to WebDriver object
page.get(url, retry, interval, **kwargs) # Use get to access the web page, you can specify the number of retries and the interval page.get(url, retry, interval, **kwargs) # Use get to access the web page, you can specify the number of retries and the interval
page.ele(loc_or_ele, timeout) # Get the first element, node or attribute that meets the conditions page.ele(loc_or_ele, timeout) # Get the first element, node or attribute that meets the conditions
page.eles(loc_or_ele, timeout) # Get all eligible elements, nodes or attributes page.eles(loc_or_ele, timeout) # Get all eligible elements, nodes or attributes
page.download(url, save_path, rename, file_exists, **kwargs) # download file page.download(url, save_path, rename, file_exists, **kwargs) # download file
page.close_driver() # Close the WebDriver object page.close_driver() # Close the WebDriver object
page.close_session() # Close the Session object page.close_session() # Close the Session object
# s mode unique: # s mode unique:
page.post(url, data, retry, interval, **kwargs) # To access the webpage in post mode, you can specify the number of retries and the interval page.post(url, data, retry, interval, **kwargs) # To access the webpage in post mode, you can specify the number of retries and the interval
# d mode unique: # d mode unique:
page.wait_ele(loc_or_ele, mode, timeout) # Wait for the element to be deleted, displayed, and hidden from the dom page.wait_ele(loc_or_ele, mode, timeout) # Wait for the element to be deleted, displayed, and hidden from the dom
page.run_script(js, *args) # Run js statement page.run_script(js, *args) # Run js statement
page.create_tab(url) # Create and locate a tab page, which is at the end page.create_tab(url) # Create and locate a tab page, which is at the end
page.to_tab(num_or_handle) # Jump to tab page page.to_tab(num_or_handle) # Jump to tab page
page.close_current_tab() # Close the current tab page page.close_current_tab() # Close the current tab page
page.close_other_tabs(num) # Close other tabs page.close_other_tabs(num) # Close other tabs
page.to_iframe(iframe) # cut into iframe page.to_iframe(iframe) # cut into iframe
page.screenshot(path) # Page screenshot page.screenshot(path) # Page screenshot
page.scrool_to_see(element) # Scroll until an element is visible page.scrool_to_see(element) # Scroll until an element is visible
page.scroll_to(mode, pixel) # Scroll the page as indicated by the parameter, and the scroll direction is optional:'top','bottom','rightmost','leftmost','up','down','left', ' right' page.scroll_to(mode, pixel) # Scroll the page as indicated by the parameter, and the scroll direction is optional:'top','bottom','rightmost','leftmost','up','down','left', ' right'
page.refresh() # refresh the current page page.refresh() # refresh the current page
page.back() # Browser back page.back() # Browser back
page.et_window_size(x, y) # Set the browser window size, maximize by default page.et_window_size(x, y) # Set the browser window size, maximize by default
page.check_page() # Check whether the page meets expectations page.check_page() # Check whether the page meets expectations
page.chrome_downloading() # Get the list of files that chrome is downloading page.chrome_downloading() # Get the list of files that chrome is downloading
page.process_alert(mode, text) # Process the prompt box page.process_alert(mode, text) # Process the prompt box
``` ```
@ -509,26 +509,26 @@ Note: The default element search timeout is 10 seconds, you can also set it as n
```python ```python
# Find by attribute # Find by attribute
page.ele('@id:ele_id', timeout = 2) # Find the element whose id is ele_id and set the waiting time for 2 seconds page.ele('@id:ele_id', timeout = 2) # Find the element whose id is ele_id and set the waiting time for 2 seconds
page.eles('@class') # Find all elements with class attribute page.eles('@class') # Find all elements with class attribute
page.eles('@class:class_name') # Find all elements that have ele_class in class page.eles('@class:class_name') # Find all elements that have ele_class in class
page.eles('@class=class_name') # Find all elements whose class is equal to ele_class page.eles('@class=class_name') # Find all elements whose class is equal to ele_class
# Find by tag name # Find by tag name
page.ele('tag:li') # Find the first li element page.ele('tag:li') # Find the first li element
page.eles('tag:li') # Find all li elements page.eles('tag:li') # Find all li elements
# Find according to tag name and attributes # Find according to tag name and attributes
page.ele('tag:div@class=div_class') # Find the div element whose class is div_class page.ele('tag:div@class=div_class') # Find the div element whose class is div_class
page.ele('tag:div@class:ele_class') # Find div elements whose class contains ele_class page.ele('tag:div@class:ele_class') # Find div elements whose class contains ele_class
page.ele('tag:div@class=ele_class') # Find div elements whose class is equal to ele_class page.ele('tag:div@class=ele_class') # Find div elements whose class is equal to ele_class
page.ele('tag:div@text():search_text') # Find div elements whose text contains search_text page.ele('tag:div@text():search_text') # Find div elements whose text contains search_text
page.ele('tag:div@text()=search_text') # Find the div element whose text is equal to search_text page.ele('tag:div@text()=search_text') # Find the div element whose text is equal to search_text
# Find according to text content # Find according to text content
page.ele('search text') # find the element containing the incoming text page.ele('search text') # find the element containing the incoming text
page.eles('text:search text') # If the text starts with @, tag:, css:, xpath:, text:, add text: in front to avoid conflicts page.eles('text:search text') # If the text starts with @, tag:, css:, xpath:, text:, add text: in front to avoid conflicts
page.eles('text=search text') # The text is equal to the element of search_text page.eles('text=search text') # The text is equal to the element of search_text
# Find according to xpath or css selector # Find according to xpath or css selector
page.eles('xpath://div[@class="ele_class"]') page.eles('xpath://div[@class="ele_class"]')
@ -542,13 +542,13 @@ page.ele(loc2)
# Find lower- level elements # Find lower- level elements
element = page.ele('@id:ele_id') element = page.ele('@id:ele_id')
element.ele('@class:class_name') # Find the first element whose class is ele_class at the lower level of element element.ele('@class:class_name') # Find the first element whose class is ele_class at the lower level of element
element.eles('tag:li') # find all li elements under ele_id element.eles('tag:li') # find all li elements under ele_id
# Find by location # Find by location
element.parent # parent element element.parent # parent element
element.next # next sibling element element.next # next sibling element
element.prev # previous sibling element element.prev # previous sibling element
# Get shadow- dom, only support open shadow- root # Get shadow- dom, only support open shadow- root
ele1 = element.shadow_root.ele('tag:div') ele1 = element.shadow_root.ele('tag:div')
@ -566,35 +566,36 @@ ele2 = ele1('tag:li')
## Get element attributes ## Get element attributes
```python ```python
element.html # return element outerHTML element.html # Return element outerHTML
element.inner_html # Return element innerHTML element.inner_html # Return element innerHTML
element.tag # return element tag name element.tag # Return element tag name
element.text # return element innerText value element.text # Return element innerText value
element.texts() # Returns the text of all direct child nodes in the element, including elements and text nodes, you can specify to return only text nodes element.link # Returns absolute href or src value of the element.
element.attrs # Return a dictionary of all attributes of the element element.texts() # Returns the text of all direct child nodes in the element, including elements and text nodes, you can specify to return only text nodes
element.attr(attr) # Return the value of the specified attribute of the element element.attrs # Return a dictionary of all attributes of the element
element.css_path # Return the absolute css path of the element element.attr(attr) # Return the value of the specified attribute of the element
element.xpath # Return the absolute xpath path of the element element.css_path # Return the absolute css path of the element
element.parent # return element parent element element.xpath # Return the absolute xpath path of the element
element.next # Return the next sibling element of the element element.parent # Return element parent element
element.prev # Return the previous sibling element of the element element.next # Return the next sibling element of the element
element.parents(num) # Return the numth parent element element.prev # Return the previous sibling element of the element
element.nexts(num, mode) # Return the following elements or nodes element.parents(num) # Return the numth parent element
element.prevs(num, mode) # Return the first few elements or nodes element.nexts(num, mode) # Return the following elements or nodes
element.ele(loc_or_str, timeout) # Return the first sub- element, attribute or node text of the current element that meets the conditions element.prevs(num, mode) # Return the first few elements or nodes
element.eles(loc_or_str, timeout) # Return all eligible sub- elements, attributes or node texts of the current element element.ele(loc_or_str, timeout) # Return the first sub- element, attribute or node text of the current element that meets the conditions
element.eles(loc_or_str, timeout) # Return all eligible sub- elements, attributes or node texts of the current element
# Driver mode unique: # d mode unique:
element.before # Get pseudo element before content element.before # Get pseudo element before content
element.after # Get pseudo element after content element.after # Get pseudo element after content
element.is_valid # Used to determine whether the element is still in dom element.is_valid # Used to determine whether the element is still in dom
element.size # Get element size element.size # Get element size
element.location # Get element location element.location # Get element location
element.shadow_root # Get the ShadowRoot element under the element element.shadow_root # Get the ShadowRoot element under the element
element.get_style_property(style, pseudo_ele) # Get element style attribute value, can get pseudo element element.get_style_property(style, pseudo_ele) # Get element style attribute value, can get pseudo element
element.is_selected() # Returns whether the element is selected element.is_selected() # Returns whether the element is selected
element.is_enabled() # Returns whether the element is available element.is_enabled() # Returns whether the element is available
element.is_displayed() # Returns whether the element is visible element.is_displayed() # Returns whether the element is visible
``` ```
@ -604,17 +605,17 @@ element.is_displayed() # Returns whether the element is visible
Element operation is unique to d mode. Calling the following method will automatically switch to d mode. Element operation is unique to d mode. Calling the following method will automatically switch to d mode.
```python ```python
element.click(by_js) # Click the element, you can choose whether to click with js element.click(by_js) # Click the element, you can choose whether to click with js
element.input(value) # input text element.input(value) # input text
element.run_script(js) # Run JavaScript script on the element element.run_script(js) # Run JavaScript script on the element
element.submit() # Submit element.submit() # Submit
element.clear() # Clear the element element.clear() # Clear the element
element.screenshot(path, filename) # Take a screenshot of the element element.screenshot(path, filename) # Take a screenshot of the element
element.select(text) # Select the drop- down list based on the text element.select(text) # Select the drop- down list based on the text
element.set_attr(attr, value) # Set element attribute value element.set_attr(attr, value) # Set element attribute value
element.drag(x, y, speed, shake) # Drag the relative distance of the element, you can set the speed and whether to shake randomly element.drag(x, y, speed, shake) # Drag the relative distance of the element, you can set the speed and whether to shake randomly
element.drag_to(ele_or_loc, speed, shake) # Drag the element to another element or a certain coordinate, you can set the speed and whether to shake randomly element.drag_to(ele_or_loc, speed, shake) # Drag the element to another element or a certain coordinate, you can set the speed and whether to shake randomly
element.hover() # Hover the mouse over the element element.hover() # Hover the mouse over the element
``` ```
@ -629,8 +630,8 @@ The DrissionPage code can be seamlessly spliced ​​with the selenium code, ei
driver = webdriver.Chrome() driver = webdriver.Chrome()
driver.get('https://www.baidu.com') driver.get('https://www.baidu.com')
page = MixPage(Drission(driver)) # Pass the driver to Drission, create a MixPage object page = MixPage(Drission(driver)) # Pass the driver to Drission, create a MixPage object
print(page.title) # Print result: You will know by clicking on Baidu print(page.title) # Print result: You will know by clicking on Baidu
``` ```
@ -641,8 +642,8 @@ print(page.title) # Print result: You will know by clicking on Baidu
page = MixPage() page = MixPage()
page.get('https://www.baidu.com') page.get('https://www.baidu.com')
driver = page.driver # Get the WebDriver object from the MixPage object driver = page.driver # Get the WebDriver object from the MixPage object
print(driver.title) # Print results: You will know by clicking on Baidu print(driver.title) # Print results: You will know by clicking on Baidu
``` ```
@ -666,8 +667,8 @@ To make up for the shortcomings of selenium, make the download simple and effici
### Demo ### Demo
```python ```python
url ='https://www.baidu.com/img/flexible/logo/pc/result.png' # file url url ='https://www.baidu.com/img/flexible/logo/pc/result.png' # file url
save_path = r'C:\download' # save path save_path = r'C:\download' # save path
# Rename to img.png, and automatically add a serial number to the end of the file name when there is a duplicate name to display the download progress # Rename to img.png, and automatically add a serial number to the end of the file name when there is a duplicate name to display the download progress
page.download(url, save_path,'img','rename', show_msg=True) page.download(url, save_path,'img','rename', show_msg=True)
@ -685,19 +686,19 @@ The configuration of chrome is very cumbersome. In order to simplify the use, th
The DriverOptions object inherits from the Options object of selenium.webdriver.chrome.options, and the following methods are added to it: The DriverOptions object inherits from the Options object of selenium.webdriver.chrome.options, and the following methods are added to it:
```python ```python
remove_argument(value) # delete an argument value remove_argument(value) # delete an argument value
remove_experimental_option(key) # delete an experimental_option setting remove_experimental_option(key) # delete an experimental_option setting
remove_all_extensions() # Remove all plugins remove_all_extensions() # Remove all plugins
save() # Save the configuration to the default ini file save() # Save the configuration to the default ini file
save('D:\\settings.ini') # save to other path save('D:\\settings.ini') # save to other path
set_argument(arg, value) # set argument attribute set_argument(arg, value) # set argument attribute
set_headless(on_off) # Set whether to use no interface mode set_headless(on_off) # Set whether to use no interface mode
set_no_imgs(on_off) # Set whether to load images set_no_imgs(on_off) # Set whether to load images
set_no_js(on_off) # Set whether to disable js set_no_js(on_off) # Set whether to disable js
set_mute(on_off) # Set whether to mute set_mute(on_off) # Set whether to mute
set_user_agent(user_agent) # set user agent set_user_agent(user_agent) # set user agent
set_proxy(proxy) # set proxy address set_proxy(proxy) # set proxy address
set_paths(driver_path, chrome_path, debugger_address, download_path, user_data_path, cache_path) # Set browser- related paths set_paths(driver_path, chrome_path, debugger_address, download_path, user_data_path, cache_path) # Set browser- related paths
``` ```
@ -705,16 +706,16 @@ set_paths(driver_path, chrome_path, debugger_address, download_path, user_data_p
### Instructions ### Instructions
```python ```python
do = DriverOptions(read_file=False) # Create chrome configuration object, not read from ini file do = DriverOptions(read_file=False) # Create chrome configuration object, not read from ini file
do.set_headless(False) # show the browser interface do.set_headless(False) # show the browser interface
do.set_no_imgs(True) # Do not load pictures do.set_no_imgs(True) # Do not load pictures
do.set_paths(driver_path='D:\\chromedriver.exe', chrome_path='D:\\chrome.exe') # set path do.set_paths(driver_path='D:\\chromedriver.exe', chrome_path='D:\\chrome.exe') # set path
do.set_headless(False).set_no_imgs(True) # Support chain operation do.set_headless(False).set_no_imgs(True) # Support chain operation
drission = Drission(driver_options=do) # Create Drission object with configuration object drission = Drission(driver_options=do) # Create Drission object with configuration object
page = MixPage(drission) # Create a MixPage object with Drission object page = MixPage(drission) # Create a MixPage object with Drission object
do.save() # Save the configuration to the default ini file do.save() # Save the configuration to the default ini file
``` ```
@ -789,11 +790,11 @@ headers = {
The OptionsManager object is used to read, set and save the configuration. The OptionsManager object is used to read, set and save the configuration.
```python ```python
get_value(section, item) - > str # Get the value of a configuration get_value(section, item) - > str # Get the value of a configuration
get_option(section) - > dict # Return all attributes of configuration in dictionary format get_option(section) - > dict # Return all attributes of configuration in dictionary format
set_item(section, item, value) # Set configuration attributes set_item(section, item, value) # Set configuration attributes
save() # Save the configuration to the default ini file save() # Save the configuration to the default ini file
save('D:\\settings.ini') # save to other path save('D:\\settings.ini') # save to other path
``` ```
@ -803,13 +804,13 @@ save('D:\\settings.ini') # save to other path
```python ```python
from DrissionPage.configs import * from DrissionPage.configs import *
options_manager = OptionsManager() # Create OptionsManager object from the default ini file options_manager = OptionsManager() # Create OptionsManager object from the default ini file
options_manager = OptionsManager('D:\\settings.ini') # Create OptionsManager object from other ini files options_manager = OptionsManager('D:\\settings.ini') # Create OptionsManager object from other ini files
driver_path = options_manager.get_value('paths','chromedriver_path') # read path information driver_path = options_manager.get_value('paths','chromedriver_path') # read path information
options_manager.save() # Save to the default ini file options_manager.save() # Save to the default ini file
options_manager.save('D:\\settings.ini') # save to other path options_manager.save('D:\\settings.ini') # save to other path
drission = Drission(ini_path ='D:\\settings.ini') # Use other ini files to create objects drission = Drission(ini_path ='D:\\settings.ini') # Use other ini files to create objects
``` ```
**Note**: If you do not pass in the path when saving, it will be saved to the ini file in the module directory, even if the read is not the default ini file. **Note**: If you do not pass in the path when saving, it will be saved to the ini file in the module directory, even if the read is not the default ini file.
@ -821,14 +822,14 @@ drission = Drission(ini_path ='D:\\settings.ini') # Use other ini files to creat
Calling the easy_set method will modify the content of the default ini file. Calling the easy_set method will modify the content of the default ini file.
```python ```python
set_headless(True) # Turn on headless mode set_headless(True) # Turn on headless mode
set_no_imgs(True) # Turn on no image mode set_no_imgs(True) # Turn on no image mode
set_no_js(True) # Disable JS set_no_js(True) # Disable JS
set_mute(True) # Turn on mute mode set_mute(True) # Turn on mute mode
set_user_agent('Mozilla/5.0 (Macintosh; Int......') # set user agent set_user_agent('Mozilla/5.0 (Macintosh; Int......') # set user agent
set_proxy('127.0.0.1:8888') # set proxy set_proxy('127.0.0.1:8888') # set proxy
set_paths(paths) # See [Initialization] section set_paths(paths) # See [Initialization] section
set_argument(arg, value) # Set the attribute. If the attribute has no value (such as'zh_CN.UTF- 8'), the value is bool, which means switch; otherwise, the value is str. When the value is'' or False, delete the attribute item set_argument(arg, value) # Set the attribute. If the attribute has no value (such as'zh_CN.UTF- 8'), the value is bool, which means switch; otherwise, the value is str. When the value is'' or False, delete the attribute item
``` ```
# POM mode # POM mode
@ -850,10 +851,10 @@ class ListPage(MixPage):
def __init__(self, drission: Drission, url: str = None, **xpaths): def __init__(self, drission: Drission, url: str = None, **xpaths):
super().__init__(drission) super().__init__(drission)
self._url = url self._url = url
self.xpath_column name = xpaths['column name'] # [xpath string, regular expression] self.xpath_column name = xpaths['column name'] # [xpath string, regular expression]
self.xpath_next page = xpaths['next page'] self.xpath_next page = xpaths['next page']
self.xpath_lines = xpaths['line'] self.xpath_lines = xpaths['line']
self.xpath_page number = xpaths['page number'] # [xpath string, regular expression] self.xpath_page number = xpaths['page number'] # [xpath string, regular expression]
self.total pages = self.get_total pages() self.total pages = self.get_total pages()
if url: if url:
self.get(url) self.get(url)
@ -915,14 +916,14 @@ from DrissionPage.session_page import SessionPage
from DrissionPage.drission import Drission from DrissionPage.drission import Drission
session = Drission().session session = Drission().session
page = SessionPage(session) # Pass in Session object page = SessionPage(session) # Pass in Session object
page.get('http://www.baidu.com') page.get('http://www.baidu.com')
print(page.ele('@id:su').text) # Output: Baidu print(page.ele('@id:su').text) # Output: Baidu
driver = Drission().driver driver = Drission().driver
page = DriverPage(driver) # Pass in Driver object page = DriverPage(driver) # Pass in Driver object
page.get('http://www.baidu.com') page.get('http://www.baidu.com')
print(page.ele('@id:su').text) # Output: Baidu print(page.ele('@id:su').text) # Output: Baidu
``` ```
# APIs # APIs
@ -1611,6 +1612,14 @@ Returns: str
### link
Returns absolute href or src value of the element.
Returns: str
### css_path ### css_path
Returns the absolute path of the element css selector. Returns the absolute path of the element css selector.
@ -2003,22 +2012,6 @@ Returns: HtmlElement
### attrs
Returns the names and values of all attributes of the element in dictionary format.
Returns: dict
### text
Returns the text within the element, namely innerText.
Returns: str
### html ### html
Returns the outerHTML text of the element. Returns the outerHTML text of the element.
@ -2043,6 +2036,30 @@ Returns: srt
### attrs
Returns the names and values of all attributes of the element in dictionary format.
Returns: dict
### text
Returns the text within the element, namely innerText.
Returns: str
### link
Returns absolute href or src value of the element.
Returns: str
### css_path ### css_path
Returns the absolute path of the element css selector. Returns the absolute path of the element css selector.

51
README.zh-cn.md
View File

@ -570,6 +570,7 @@ element.html # 返回元素outerHTML
element.inner_html # 返回元素innerHTML element.inner_html # 返回元素innerHTML
element.tag # 返回元素tag name element.tag # 返回元素tag name
element.text # 返回元素innerText值 element.text # 返回元素innerText值
element.link # 返回元素href或src绝对url
element.texts() # 返回元素内所有直接子节点的文本，包括元素和文本节点，可指定只返回文本节点 element.texts() # 返回元素内所有直接子节点的文本，包括元素和文本节点，可指定只返回文本节点
element.attrs # 返回元素所有属性的字典 element.attrs # 返回元素所有属性的字典
element.attr(attr) # 返回元素指定属性的值 element.attr(attr) # 返回元素指定属性的值
@ -584,7 +585,7 @@ element.prevs(num, mode) # 返回前面第几个元素或节点
element.ele(loc_or_str, timeout) # 返回当前元素下级第一个符合条件的子元素、属性或节点文本 element.ele(loc_or_str, timeout) # 返回当前元素下级第一个符合条件的子元素、属性或节点文本
element.eles(loc_or_str, timeout) # 返回当前元素下级所有符合条件的子元素、属性或节点文本 element.eles(loc_or_str, timeout) # 返回当前元素下级所有符合条件的子元素、属性或节点文本
# driver模式独有： # d 模式独有：
element.before # 获取伪元素before内容 element.before # 获取伪元素before内容
element.after # 获取伪元素after内容 element.after # 获取伪元素after内容
element.is_valid # 用于判断元素是否还在dom中 element.is_valid # 用于判断元素是否还在dom中
@ -1611,6 +1612,14 @@ driver模式的元素对象，包装了一个WebElement对象，并封装了常
### link
返回元素href或src绝对url。
返回: str
### css_path ### css_path
返回元素css selector绝对路径。 返回元素css selector绝对路径。
@ -2003,22 +2012,6 @@ session模式的元素对象，包装了一个Element对象，并封装了常用
### attrs
以字典格式返回元素所有属性的名称和值。
返回: dict
### text
返回元素内的文本，即innerText。
返回: str
### html ### html
返回元素outerHTML文本。 返回元素outerHTML文本。
@ -2043,6 +2036,30 @@ session模式的元素对象，包装了一个Element对象，并封装了常用
### attrs
以字典格式返回元素所有属性的名称和值。
返回: dict
### text
返回元素内的文本，即innerText。
返回: str
### link
返回元素href或src绝对url。
返回: str
### css_path ### css_path
返回元素css selector绝对路径。 返回元素css selector绝对路径。