Selenium / PhantomJS / requests

2018-07-18  本文已影响0人  pyHorse
from selenium import webdriver
import  requests
import urllib.request

def get_selenium_content(page):
    br = webdriver.PhantomJS(executable_path=r'phantomjs.exe')
    br.get('https://www.guazi.com/sh/buy/o'+str(page)+'/')
    data = br.page_source
    br.close()
    return data

def get_request_content(page):
    url = 'https://www.guazi.com/sh/buy/o'+str(page)+'/'
    r = requests.get(
        url,params = None,headers = {
            'User - Agent': 'Mozilla / 5.0(Windows NT 10.0;WOW64) AppleWebKit / 537.36(KHTML, like Gecko) Chrome / 67.0.3396.99 Safari / 537.36'
        }
    )
    return r.text

def get_urllib_content(page):
    url = 'https://www.guazi.com/sh/buy/o' + str(page) + '/'
    request = urllib.request.Request(url)
    r = request.add_header(
            'User - Agent','Mozilla / 5.0(Windows NT 10.0;WOW64) AppleWebKit / 537.36(KHTML, like Gecko) Chrome / 67.0.3396.99 Safari / 537.36'
    )
    content = urllib.request.urlopen(request).read().decode('utf-8')
    return content

print(get_selenium_content(2))
print(get_request_content(2))
print(get_urllib_content(2))
上一篇下一篇

猜你喜欢

热点阅读