Python爬虫入门教程 7-100 蜂鸟网图片爬取之二

获取我们想要的两部分数字

async def fetch_img_url(num):
    url = f"http://bbs.fengniao.com/forum/forum_101_{num}_lastpost.html"
    print(url)
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.26 Safari/537.36 Core/1.63.6726.400 QQBrowser/10.2.2265.400",
    }

    async with aiohttp.ClientSession() as session:
        # 获取轮播图地址
        async with session.get(url,headers=headers) as response:
            try:
                ###############################################
                url_format = "http://bbs.fengniao.com/forum/pic/slide_101_{0}_{1}.html"
                html = await response.text()   # 获取到网页源码
                pattern = re.compile("
([sS.]*?)
")
                first_match = pattern.findall(html)
                href_pattern = re.compile("href="/forum/(d+?)_p(d+?).html")
                urls = [url_format.format(href_pattern.search(url).group(1), href_pattern.search(url).group(2)) for url in first_match]
                ##############################################

            except Exception as e:
                print("基本错误")
                print(e)

代码完成，我们已经获取到，我们想要的URL了，下面继续读取URL内部信息，然后匹配我们想要的图片链接

async def fetch_img_url(num):
    # 去抄上面的代码
    async with aiohttp.ClientSession() as session:
        # 获取轮播图地址
        async with session.get(url,headers=headers) as response:
            try:
                #去抄上面的代码去吧
                ################################################################
                for img_slider in urls:
                    try:
                        async with session.get(img_slider, headers=headers) as slider:
                            slider_html = await slider.text()   # 获取到网页源码
                            try:
                                pic_list_pattern = re.compile("var picList = [(.*)?];")
                                pic_list = "[{}]".format(pic_list_pattern.search(slider_html).group(1))
                                pic_json = json.loads(pic_list)  # 图片列表已经拿到
                                print(pic_json)
                            except Exception as e:
                                print("代码调试错误")
                                print(pic_list)
                                print("*"*100)
                                print(e)

                    except Exception as e:
                        print("获取图片列表错误")
                        print(img_slider)
                        print(e)
                        continue
                ################################################################


                print("{}已经操作完毕".format(url))
            except Exception as e:
                print("基本错误")
                print(e)

图片最终的JSON已经拿到，最后一步，下载图片，当当当~~~~，一顿迅猛的操作之后，图片就拿下来了

async def fetch_img_url(num):
    # 代码去上面找
    async with aiohttp.ClientSession() as session:
        # 获取轮播图地址
        async with session.get(url,headers=headers) as response:
            try:
                # 代码去上面找
                for img_slider in urls:
                    try:
                        async with session.get(img_slider, headers=headers) as slider:
                            # 代码去上面找
                            ##########################################################
                            for img in pic_json:
                                try:
                                    img = img["downloadPic"]
                                    async with session.get(img, headers=headers) as img_res:
                                        imgcode = await img_res.read()  # 图片读取
                                        with open("images/{}".format(img.split("/")[-1]), "wb") as f:
                                            f.write(imgcode)
                                            f.close()
                                except Exception as e:
                                    print("图片下载错误")
                                    print(e)
                                    continue
                            ###############################################################

                    except Exception as e:
                        print("获取图片列表错误")
                        print(img_slider)
                        print(e)
                        continue
                print("{}已经操作完毕".format(url))
            except Exception as e:
                print("基本错误")
                print(e)

图片会在你提前写好的images文件夹里面快速的生成

tasks最多可以开1024协程，但是建议你开100个就OK了，太多并发，人家服务器吃不消。

以上操作执行完毕，在添加一些细节，比如保存到指定文件夹，就OK了。