基于PhantomJS的网页抓取及写入文件

时间:2021-12-15 23:10:44
# coding=utf-8
from selenium import webdriver
from selenium.webdriver.common.desired_capabilities import DesiredCapabilities if __name__=="__main__":
url = "http://XXX.XXXXX.com/XX.html"
dcap = dict(DesiredCapabilities.PHANTOMJS)
dcap["phantomjs.page.settings.userAgent"] = ("Mozilla/5.0 (Macintosh; Intel Mac OS X 10.9; rv:25.0) Gecko/20100101 Firefox/25.0 ") obj = webdriver.PhantomJS(executable_path=r'D:\phantomjs\bin\phantomjs.exe',desired_capabilities=dcap)
obj.get(url)
html = obj.page_source
obj.quit() fw = open("D:\\test.html","w",encoding='utf-8')
fw.write(html)
fw.close() # cx = sqlite3.connect("D:\SQLite\chuangbing.db")
# cx.execute("insert into page_html (page_time,page_url,page_resource) values (datetime('now'),?,?)",(url,html))
# cx.commit()
# cx.close()