Python 刮取隐藏帧JavaScript

我试图在一个隐藏的框架内抓取数据；框架如下所示

<!-- Content of the details tabs here  -->
    <div id="tabDetail_0" class="tab_content tab_detail" style="display: 
    block;"><iframe id="iframe_0" src="https://www.tmdn.org/tmview/get- 
    detail?st13=GB500000003342197" width="100%" height="600px;" 
    frameborder="0"></iframe></div></div></div> <!-- resultTabs -->

---

您需要做的是

切换到.frame

：

iframe = driver.find_element_by_xpath('//iframe[@id="iframe_0"]')
driver.switch_to.frame(iframe)
# than switch back:
driver.switch_to.default_content()

编辑：

您已经询问过id是否会更改要执行的操作，您可以在xpath中使用

contains

，如下所示：

# this will find any iframe with and id of iframe_ 
# you should check there is only one, you can do so with: `iframes = driver.find_elements_by_xpath('//iframe[contains(@id,"iframe_")]')`
# than `print(len(iframes))` to see the amount of iframes 
iframe = driver.find_element_by_xpath('//iframe[contains(@id,"iframe_")]')
driver.switch_to.frame(iframe)
# than switch back:
driver.switch_to.default_content()

在代码使用中：

import time
from selenium import webdriver
from selenium.common.exceptions import NoSuchElementException
from selenium.webdriver import ActionChains
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support.ui import Select

url ="https://www.tmdn.org/tmview/welcome#"

driver = webdriver.Chrome(executable_path=r"D:\New Proj\chromedriver.exe")
driver.get(url)
time.sleep(3)
driver.find_element_by_xpath('//*[@id="buttonBox"]/a').click()
time.sleep(3)

#Click advanced search
driver.find_element_by_name("lnkAdvancedSearch").click()
#
time.sleep(5)
#to select Designated territories
driver.find_element_by_id('DesignatedTerritories').click()
time.sleep(5)   
TerritoryLabelElements = driver.find_elements_by_css_selector( 'div.optEUGroupContainer label')
for elem in TerritoryLabelElements:
    if elem.text == 'United Kingdom':
        elem.click()
time.sleep(5)
driver.find_element_by_id('DesignatedTerritories').click()
#
time.sleep(5)
#to select from Trade mark offices
driver.find_element_by_id('SelectedOffices').click()
time.sleep(5)   
TerritoryLabelElements = driver.find_elements_by_css_selector( 'div.multiSelectOptions label')
for elem in TerritoryLabelElements:
    if elem.text == 'GB United Kingdom ( UKIPO )':
        elem.click()
time.sleep(5)
driver.find_element_by_id('SelectedOffices').click()
#Trade mark status
driver.find_element_by_id('TradeMarkStatus').click()
time.sleep(5)   
TerritoryLabelElements = driver.find_elements_by_css_selector( 'div.multiSelectOptions label')
for elem in TerritoryLabelElements:
    if elem.text == 'Filed':
        elem.click()
    if elem.text == 'Registered':
        elem.click()
time.sleep(5)
driver.find_element_by_id('TradeMarkStatus').click()
# dates
startdate = driver.find_element_by_id("ApplicationDateFrom")
startdate.clear()
startdate.send_keys ('10-01-2018')
enddate = driver.find_element_by_id("ApplicationDateTo")
enddate.clear()
enddate.send_keys ('10-01-2018' )   
# click search
time.sleep(5)
driver.find_element_by_id("SearchCopy").click()
time.sleep(30)

#Click first link
el=driver.find_elements_by_class_name('cell_tmName_column')[0]
action = ActionChains(driver)
action.move_to_element_with_offset(el, 0, 0)
action.click()
action.perform()
time.sleep(10)
iframe = driver.find_element_by_xpath('//iframe[@id="iframe_0"]')
driver.switch_to.frame(iframe)
# do something here I am printing the HTML
print(iframe.get_attribute('innerHTML'))
# than switch back:
driver.switch_to.default_content()

---

希望这对你有帮助

嗨，Milah，如果

切换到.frame

请告诉我，如图所示是我的答案…嗨，Moshe，它工作得很好，但是iframe id一直在变化。这是iframe_0 somtimes iframe_1…嗨，米拉，我已经编辑了我的答案，用

contains

参见编辑。如果您需要更多的解释，请askHi Moshe，谢谢您的帮助；我编辑了上面的代码，我把所有的代码，包括刮削部分。第一个链接的代码运行正常，但是当第二个链接出现时，代码会停止，似乎驱动程序。切换到默认值不起作用。我不在工作，也不在电脑旁，但您可以使用

切换到活动元素（）。。。明天我会尽力帮助更多。。。
import time
from selenium import webdriver
from selenium.common.exceptions import NoSuchElementException
from selenium.webdriver import ActionChains
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support.ui import Select

url ="https://www.tmdn.org/tmview/welcome#"

driver = webdriver.Chrome(executable_path=r"D:\New Proj\chromedriver.exe")
driver.get(url)
time.sleep(3)
driver.find_element_by_xpath('//*[@id="buttonBox"]/a').click()
time.sleep(3)

#Click advanced search
driver.find_element_by_name("lnkAdvancedSearch").click()
#
time.sleep(5)
#to select Designated territories
driver.find_element_by_id('DesignatedTerritories').click()
time.sleep(5)   
TerritoryLabelElements = driver.find_elements_by_css_selector( 'div.optEUGroupContainer label')
for elem in TerritoryLabelElements:
    if elem.text == 'United Kingdom':
        elem.click()
time.sleep(5)
driver.find_element_by_id('DesignatedTerritories').click()
#
time.sleep(5)
#to select from Trade mark offices
driver.find_element_by_id('SelectedOffices').click()
time.sleep(5)   
TerritoryLabelElements = driver.find_elements_by_css_selector( 'div.multiSelectOptions label')
for elem in TerritoryLabelElements:
    if elem.text == 'GB United Kingdom ( UKIPO )':
        elem.click()
time.sleep(5)
driver.find_element_by_id('SelectedOffices').click()
#Trade mark status
driver.find_element_by_id('TradeMarkStatus').click()
time.sleep(5)   
TerritoryLabelElements = driver.find_elements_by_css_selector( 'div.multiSelectOptions label')
for elem in TerritoryLabelElements:
    if elem.text == 'Filed':
        elem.click()
    if elem.text == 'Registered':
        elem.click()
time.sleep(5)
driver.find_element_by_id('TradeMarkStatus').click()
# dates
startdate = driver.find_element_by_id("ApplicationDateFrom")
startdate.clear()
startdate.send_keys ('10-01-2018')
enddate = driver.find_element_by_id("ApplicationDateTo")
enddate.clear()
enddate.send_keys ('10-01-2018' )   
# click search
time.sleep(5)
driver.find_element_by_id("SearchCopy").click()
time.sleep(30)

#Click first link
el=driver.find_elements_by_class_name('cell_tmName_column')[0]
action = ActionChains(driver)
action.move_to_element_with_offset(el, 0, 0)
action.click()
action.perform()
time.sleep(10)
iframe = driver.find_element_by_xpath('//iframe[@id="iframe_0"]')
driver.switch_to.frame(iframe)
# do something here I am printing the HTML
print(iframe.get_attribute('innerHTML'))
# than switch back:
driver.switch_to.default_content()