python爬虫代码示例:爬取京东详情页图片

python爬虫代码示例:爬取京东详情页图片

一、Requests安装及示例

爬虫爬取网页内容首先要获取网页的内容，通过requests库进行获取。

• GitHub: https://github.com/requests/requests

• PyPl: https://pypi.python.org/pypi/requests

• 官方文档:http://wwwpython-requests.org

• 中文文档:http://docs.python-requests.org/zh CN/latest

安装

pip install requests

示例代码

import requests
url  = "http://store.weigou365.cn"res = requests.get(url)res.text

执行效果如下：

二、Selenium库

爬虫爬取网页有时需要模拟网页行为，比如京东、淘宝详情页面，图片加载随着滚动自动加载的。这种情况我们就要进行浏览器模拟操作才能获取要爬取的数据。

Selenium 是一个用于自动化浏览器操作的开源框架，主要用于网页测试，支持多种浏览器包括 Chrome、Firefox、Safari 等。它提供了一系列的API，允许你模拟用户在浏览器中的行为，例如点击按钮、填写表单、导航等。

官方网站: https://sites.google.com/a/chromium.org/chromedriver114之前版本：http://chromedriver.storage.googleapis.com/index.html116版本:https://edgedl.me.gvt1.com/edgedl/chrome/chrome-for-testing/116.0.5845.96/win64/chromedriver-win64.zip117之后的版本：https://googlechromelabs.github.io/chrome-for-testing/

安装

pip install selenium

示例代码

from selenium import webdriverbrowser = webdriver.Chrome()browser.get("https://baidu.com/")print(browser.title)browser.quit() 

三、爬取京东详情页面代码

from selenium import webdriverfrom lxml import etreeimport timeimport openpyxlimport reimport osimport requests

headers = {'content-type': 'application/json', 'User-Agent': 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:22.0) Gecko/20100101 Firefox/22.0'}

def exchange_url(small,big,flag=0):    lists = small[0].strip('/').split('/')    return lists[0] + "/n" + str(flag) + "/" + big[0]

def get_image_path(model=""):    path = "./imgs/" +  str(time.strftime("%Y%m%d%H%M", time.localtime()) ) + "/"    if model != "":        path += model            if(os.path.exists(path)):        pass    else:        os.makedirs(path)    return path

def download_img(title,url,headers,model=""):    img_data = requests.get(url,headers=headers).content        filename = url.strip('/').split('/').pop()    if model != "":        filename = model + "_" + filename
    img_path = os.path.join(get_image_path(model),filename)    with open(img_path,'wb') as f:            f.write(img_data)    return

def get_source(driver,url):  #发起请求    driver.get(url)    time.sleep(1)   #休息一秒然后操纵滚轮滑到最底部，这时浏览器数据全部加载，返回的源码中是全部数据    driver.execute_script("window.scrollTo(0,document.body.scrollHeight);")    time.sleep(2)    #得到代码    source = driver.page_source
    #返回source源码以供解析    return source
def writeExcel(title):    wb = openpyxl.load_workbook("records.xlsx")    ws = wb.active    path = get_image_path()    path = os.path.abspath('.') + path.strip('.')    ws.append([title,path])    wb.save("records.xlsx")
    def get_page_title(html):    db_title = html.xpath('//*[@class="itemInfo-wrap"]/div[@class="sku-name"]/text()')    if(len(db_title) == 1):        return db_title[0].replace("\n","").replace('\'',"").replace(" ","")            return db_title[1].replace("\n","").replace('\'',"").replace(" ","")

def get_page_logos(html):    db_logo_items = html.xpath('//*[@id="spec-list"]/ul[@class="lh"]/li')        bigs = mids = []    for db_logo_item in db_logo_items:        db_logo_small = db_logo_item.xpath("img/@src")        db_logo_big = db_logo_item.xpath("img/@data-url")        bigs.append(exchange_url(db_logo_small,db_logo_big))        mids.append(exchange_url(db_logo_small,db_logo_big,1))        return [mids,bigs]        
def get_page_content(html):    images = html.xpath('//div[@id="J-detail-content"]/p/img/@href')    #pattern = re.compile(r"background-image:url\(([^)]*)",re.S)    return images

def process(url):    try:        driver = webdriver.Chrome()        driver.implicitly_wait(10)        content = get_source(driver,url)        html = etree.HTML(content)        title = get_page_title(html)        logos = get_page_logos(html)        images = get_page_content(html)            print(title,logos,images)
        #记录标题和图片地址        writeExcel(title)        print("write title done!")
        #下载中图        for mid_url in logos[0]:            img_url = "http://" + mid_url.replace("http","").replace(":","").replace("//","")            download_img(title,img_url,headers,model="mid")        print("download mid logos done!")
        #下载大图        for big_url in logos[1]:            img_url  = "http://" + big_url.replace("http","").replace(":","").replace("//","")            download_img(title,img_url,headers,model="big")
        print("download big logos done!")
        for img_url in images:            img_url = "http://" + img_url.replace("http","").replace(":","").replace("//","")            download_img(title,img_url,headers,model="imgs")
        print("download content images done!")
    finally:        driver.close()

if __name__ == "__main__":    while(True):        url = input('京东详情页地址(quit退出):')        if(url == "quit"):            break;                process(url)    

上面代码保存.py文件。通过下面命令执行

python scrawler.py

执行如下：