https://officialrecords.broward.org/AcclaimWeb/search/SearchTypeName
点击BANKATLANTIC
如何提取TransactionItemId? #在DocLink下
如何从第一份文件中提取文字?
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from bs4 import BeautifulSoup
from time import sleep
driverurl = "https://officialrecords.broward.org/AcclaimWeb/search/SearchTypeName"
RecordDateInput = "8/15/2017"
driver = webdriver.Chrome()
driver.get(driverurl)
driver.find_element_by_id("btnButton").click()
driver.find_element_by_id("Direct").click() # Grantor
Name = "ba"
driver.find_element_by_id("SearchOnName").send_keys(Name)
DocType = "RELEASE/REVOKE/SATISFY OR TERMINATE (RST)"
driver.find_element_by_id("DocTypesDisplay-input").clear()
sleep(1)
driver.find_element_by_id("DocTypesDisplay-input").send_keys(DocType)
driver.find_element_by_id("RecordDateFrom").clear()
driver.find_element_by_id("RecordDateFrom").send_keys(RecordDateInput)
driver.find_element_by_id("RecordDateTo").clear()
driver.find_element_by_id("RecordDateTo").send_keys(RecordDateInput)
driver.execute_script("return arguments[0].scrollIntoView();", driver.find_element_by_id("btnSearch"))
driver.find_element_by_id("btnSearch").click()
sleep(7)
driver.find_elements_by_class_name("rowNumClass")[0].click()
sleep(3)
#######################################################
# solution:
driver.switch_to_window(driver.window_handles[1])
sleep(3)
html = driver.page_source
soup = BeautifulSoup(html, "lxml")
TransactionItemId = soup.findAll("div", { "class" : "listDocDetails" })[-1].find("a")['onclick'].split("'")[1]
答案 0 :(得分:0)
我能看到获得包含$ 600,000的元素的唯一方法是获取包含“Consideration:”标签的元素,然后找到包含美元金额的以下DIV
。通过包含文本查找元素的唯一方法是使用XPath。下面的一个工作。
//div[@class='detailLabel'][contains(.,'Consideration:')]/following-sibling::div
答案 1 :(得分:0)
试试这个:
driver.switch_to_window(driver.window_handles[1])
sleep(3)
html = driver.page_source
soup = BeautifulSoup(html, "lxml")
TransactionItemId = soup.findAll("div", { "class" : "listDocDetails" })[-1].find("a")['onclick'].split("'")[1]