虽然存在大量的PhantomJS的文章,但是PhantomJS的维护和开发已经停止,不建议使用。建议使用chromedriver、geckodriver
第一种使用方式:simply.py
from selenium import webdriver
import json,time
import random
from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
# 因 ssl 三次握手链接报错,而添加的代码。
USER_AGENTS = [
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; AcooBrowser; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; Acoo Browser; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)",
"Mozilla/4.0 (compatible; MSIE 7.0; AOL 9.5; AOLBuild 4337.35; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
"Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)",
"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)",
"Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)",
"Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)",
"Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)",
"Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6",
"Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1",
"Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0",
"Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5",
"Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.8) Gecko Fedora/1.9.0.8-1.fc10 Kazehakase/0.5.6",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/535.20 (KHTML, like Gecko) Chrome/19.0.1036.7 Safari/535.20",
"Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; fr) Presto/2.9.168 Version/11.52",
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.11; rv:57.0) Gecko/20100101 Firefox/57.0',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.95 Safari/537.36'
]
dcap = dict(webdriver.DesiredCapabilities.PHANTOMJS)
dcap["phantomjs.page.settings.userAgent"] = (random.choice(USER_AGENTS))
service_args = ['--load-images=false', '--proxy-type=None','--ignore-ssl-errors=true','--ssl-protocol=tlsv1']
browser = webdriver.PhantomJS(service_args=service_args, desired_capabilities=dcap)
browser.get("https://www.csdn.net/")
print(browser.current_url)
print(browser.title)
print(browser.find_element_by_id('product').text)
js = "document.body.scrollTop=10000"
browser.execute_script(js)
# 截图
browser.save_screenshot("douban1.png")
# browser.quit()
第二种使用方式: pageloa .js
var page = require('webpage').create()
phantom.outputEncoding = 'gbk'
page.open('http://www.cnblogs.com/front-Thinking', function (status) {
if (status === 'success') {
console.log(page.title)
} else {
console.log(status, 'reason', page.reason)
}
phantom.exit(0)
})
page.onResourceError = function (e) {
page.reason = e.errorString
}
启动:PhantomJS .\pageloa.js
网友评论