学习爬虫记录

Posted 2020-11-25 zmdz-134

使用selenium 自动化搜索 获取URL 并爬取图片，并保存
总结：入口程序写的差，内容繁琐，用到知识点多

import os
from chrome_Demo.handless import shaer_browser
import time
import requests
from lxml import etree
import urllib.request
from urllib.request import urlparse

def browser_url():
    browser = shaer_browser() #构造无头浏览器
    # path = ‘./chromedriver.exe‘
    # browser= webdriver.Chrome(path)
    browser.get(‘https://www.baidu.com/‘)
    input_key = browser.find_element_by_id(‘kw‘)#定位百度一下的输入框
    input_key.send_keys(‘下厨房‘)#在输入框内输入搜素内容
    time.sleep(1)
    bd_key = browser.find_element_by_id(‘su‘)#定位百度一下
    bd_key.click()#点击百度一下
    time.sleep(2)
    xcf_key = browser.find_element_by_xpath(‘//*[@id="1"]/h3/a[1]‘)#定位搜索的标题
    xcf_key.click()#点击跳转新网页
  
    n = browser.window_handles
    browser.switch_to.window(n[1])#固定在跳转的网页
    browser.save_screenshot(‘mn.png‘)#截图
    # browser.get_screenshot_as_png()
    time.sleep(6)
    url = browser.current_url #获取当前页面的url
    browser.quit()
    return url
#使用xpath语法定位到数据
def create_req(url):
    headers = {
        ‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (Khtml, like Gecko) Chrome/78.0.3904.108 Safari/537.36‘
    }
    req = urllib.request.Request(url=url,headers=headers)
    res = urllib.request.urlopen(req)
    x_etr = etree.HTML(res.read().decode(‘utf-8‘))
    img_list = x_etr.xpath(‘//div[@class="headline"]//ul//li//a//img/@src‘)
    return img_list
#创建文件夹并保存数据
def save_data(img_list):
    img_dir = os.path.join(os.curdir, ‘mei_shi‘)
    for img in img_list:
        o = urlparse(img)
        filename = o.path[1:].split(‘@‘)[0]
        filepath = os.path.join(img_dir,filename)
        if not os.path.isdir(os.path.dirname(filepath)):
            os.mkdir(os.path.dirname(filepath))
        url = ‘%s://%s/%s‘% (o.scheme,o.netloc,o.path)
        p = requests.get(url)
        with open(filepath,‘wb‘) as fp:
            for block in p.iter_content(1024):
                fp.write(block)


def main():
    url = browser_url()
    img_list = create_req(url)
    save_data(img_list)

if __name__ == ‘__main__‘:
    main()