Question

我知道如何到达要通过硒刮取的结果页面，但是我不知道如何实际刮取结果页面。我也尝试过机械化，但这并没有使我进一步。这是我现在的位置：

import re
import urllib2
import csv
import os
from selenium import webdriver
from selenium.webdriver.support.ui import Select
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
from bs4 import BeautifulSoup, SoupStrainer
import datetime
import time
import smtplib
import atexit
import signal
import json
import os
import gspread
import sys
import gc

script_path = os.path.dirname(os.path.realpath(__file__))

driver = webdriver.PhantomJS(executable_path="/usr/bin/phantomjs", service_args=['--ignore-ssl-errors=true', '--ssl-protocol=any'])

#launches headless browser, completes proper search in Casenet
def main():

    driver.get('https://www.courts.mo.gov/casenet/cases/nameSearch.do')

    if 'Service Unavailable' in driver.page_source:
        log('Casenet website seems to be down. Receiving "service unavailable"')
        driver.quit()
        gc.collect()
        return False

    court = Select(driver.find_element_by_id('courtId'))

    court.select_by_visible_text('All Participating Courts')

    case_enter = driver.find_element_by_id('inputVO.lastName')

    case_enter.send_keys('Wakefield & Associates')

    driver.find_element_by_id('findButton').click()

    time.sleep(1)

    number_of_pages = 204

    for i in range(number_of_pages):

        output_trs = []

        party = (driver.find_element_by_class_name('outerTable'))

        output_trs.append(party)

        print output_trs

main()

最终的想法是将当事人，案件编号和申请日期作为字符串存储在.csv中。当我现在打印output_trs时，我得到：

selenium.webdriver.remote.webelement.WebElement (session="c4e7b9e0-7a3b-11e8-83f2-b9030062270d", element=":wdc:1530125781332")

感谢任何帮助。

Answer 1

您正在尝试打印网络元素对象rather than its text content。

一种打印文本内容的方式（请注意编码）：

for content in output_trs:
    print content.text

无法弄清楚如何用硒刮页

1 个答案: