python爬虫添加请求头

request

import requests


headers = {
    # 'Accept': 'application/json, text/javascript, */*; q=0.01',
    # 'Accept': '*/*',
    # 'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8,en-US;q=0.7',
    # 'Cache-Control': 'no-cache',
    # 'accept-encoding': 'gzip, deflate, br',
    'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.97 Safari/537.36',
    'Referer': 'https://www.google.com/'
}

resp = requests.get('http://httpbin.org/get', headers=headers)
print(resp.content)

urllib

import urllib, urllib2
def get_page_source(url):
    headers = {'Accept': '*/*',
               'Accept-Language': 'en-US,en;q=0.8',
               'Cache-Control': 'max-age=0',
               'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.116 Safari/537.36',
               'Connection': 'keep-alive',
               'Referer': 'http://www.baidu.com/'
               }
    req = urllib2.Request(url, None, headers)
    response = urllib2.urlopen(req)
    page_source = response.read()
    return page_source

phantomjs请求页面

from selenium import webdriver
from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
def get_headers_driver():
    desire = DesiredCapabilities.PHANTOMJS.copy()
    headers = {'Accept': '*/*',
               'Accept-Language': 'en-US,en;q=0.8',
               'Cache-Control': 'max-age=0',
               'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.116 Safari/537.36',
               'Connection': 'keep-alive',
               'Referer': 'http://www.baidu.com/'
               }
    for key, value in headers.iteritems():
        desire['phantomjs.page.customHeaders.{}'.format(key)] = value
    driver = webdriver.PhantomJS(desired_capabilities=desire, service_args=['--load-images=yes'])#将yes改成no可以让浏览器不加载图片
    return driver

#原文链接：https://blog.csdn.net/aaronjny/article/details/62088640