python3网络爬虫selenium应用

       selenium 是一个用于Web应用程序测试的工具。Selenium测试直接运行在浏览器中，就像真正的用户在操作一样。支持的浏览器包括IE（7, 8, 9, 10, 11），Mozilla Firefox，Safari，Google Chrome，Opera等。这个工具的主要功能包括：测试与浏览器的兼容性——测试你的应用程序看是否能够很好得工作在不同浏览器和操作系统之上。测试系统功能——创建回归测试检验软件功能和用户需求。支持自动录制动作和自动生成 .Net、Java、Perl等不同语言的测试脚本。 
selenium用于爬虫，主要是用来解决javascript渲染的问题

 

 

1、selenium打开百度

# encoding=utf-8
__author__ = 'SK'

import pymongo
from selenium import webdriver
from selenium.common.exceptions import TimeoutException
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.wait import WebDriverWait
from pyquery import PyQuery as pq
from config import *
from urllib.parse import quote

browser = webdriver.Chrome()
try:
    browser.get("https://www.baidu.com")
    input =browser.find_element_by_id("kw")
    input.send_keys("Python")
    input.send_keys(Keys.ENTER)
    wait=WebDriverWait(browser,10)
    wait.until(EC.presence_of_element_located((By.ID,'content_left')))
    print(browser.current_url)
    print(browser.get_cookies())
    print(browser.page_source)
finally:
 browser.close()

2、selenium拖拽或者运行javascript

# encoding=utf-8
__author__ = 'SK'
from  selenium.webdriver import ActionChains
import pymongo
from selenium import webdriver
from selenium.common.exceptions import TimeoutException
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.wait import WebDriverWait
from pyquery import PyQuery as pq
from config import *
from urllib.parse import quote
'''
brower=webdriver.Chrome()
url='http://www.runoob.com/try/try.php?filename=jqueryui-api-droppable'
brower.get(url)
brower.switch_to.frame('iframeResult')
source=brower.find_element_by_css_selector('#draggable')
target=brower.find_element_by_css_selector('#droppable')
action=ActionChains(brower)
action.drag_and_drop(source,target)
action.perform();
'''

'''
browser=webdriver.Chrome()
browser.get("https://www.zhihu.com/explore")
browser.execute_script("window.scrollTo(0,document.body.scrollHeight)")
browser.execute_script("alert('To bottom')")
'''

3、selenium爬虫

import pymongo
from selenium import webdriver
from selenium.common.exceptions import TimeoutException
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.wait import WebDriverWait
from pyquery import PyQuery as pq
from config import *
from urllib.parse import quote

# browser = webdriver.Chrome()
# browser = webdriver.PhantomJS(service_args=SERVICE_ARGS)

chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument('--headless')
browser = webdriver.Chrome(chrome_options=chrome_options)

wait = WebDriverWait(browser, 10)
def get_products():
    """
    提取商品数据
    """
    html = browser.page_source
    doc = pq(html)
    items = doc('#mainsrp-itemlist .items .item').items()
    for item in items:
        product = {
            'image': item.find('.pic .img').attr('data-src'),
            'price': item.find('.price').text(),
            'deal': item.find('.deal-cnt').text(),
            'title': item.find('.title').text(),
            'shop': item.find('.shop').text(),
            'location': item.find('.location').text()
        }
        print(product)





if __name__ == '__main__':
    wait.until(
        EC.text_to_be_present_in_element((By.CSS_SELECTOR, '#mainsrp-pager li.item.active > span'), str(page)))
    wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '.m-itemlist .items .item')))
    get_products()

这是我对selenium的理解，以后每周两篇关于python的东西，希望大家加我微信zcy2366585970，一起学习