獲取我們想要的兩部分?jǐn)?shù)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:
        # 獲取輪播圖地址
        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()   # 獲取到網(wǎng)頁源碼
                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("基本錯誤")
                print(e)

代碼完成，我們已經(jīng)獲取到，我們想要的URL了，下面繼續(xù)讀取URL內(nèi)部信息，然后匹配我們想要的圖片鏈接

async def fetch_img_url(num):
    # 去抄上面的代碼
    async with aiohttp.ClientSession() as session:
        # 獲取輪播圖地址
        async with session.get(url,headers=headers) as response:
            try:
                #去抄上面的代碼去吧
                ################################################################
                for img_slider in urls:
                    try:
                        async with session.get(img_slider, headers=headers) as slider:
                            slider_html = await slider.text()   # 獲取到網(wǎng)頁源碼
                            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)  # 圖片列表已經(jīng)拿到
                                print(pic_json)
                            except Exception as e:
                                print("代碼調(diào)試錯誤")
                                print(pic_list)
                                print("*"*100)
                                print(e)

                    except Exception as e:
                        print("獲取圖片列表錯誤")
                        print(img_slider)
                        print(e)
                        continue
                ################################################################


                print("{}已經(jīng)操作完畢".format(url))
            except Exception as e:
                print("基本錯誤")
                print(e)

圖片最終的JSON已經(jīng)拿到，最后一步，下載圖片，當(dāng)當(dāng)當(dāng)~~~~，一頓迅猛的操作之后，圖片就拿下來了

async def fetch_img_url(num):
    # 代碼去上面找
    async with aiohttp.ClientSession() as session:
        # 獲取輪播圖地址
        async with session.get(url,headers=headers) as response:
            try:
                # 代碼去上面找
                for img_slider in urls:
                    try:
                        async with session.get(img_slider, headers=headers) as slider:
                            # 代碼去上面找
                            ##########################################################
                            for img in pic_json:
                                try:
                                    img = img["downloadPic"]
                                    async with session.get(img, headers=headers) as img_res:
                                        imgcode = await img_res.read()  # 圖片讀取
                                        with open("images/{}".format(img.split("/")[-1]), "wb") as f:
                                            f.write(imgcode)
                                            f.close()
                                except Exception as e:
                                    print("圖片下載錯誤")
                                    print(e)
                                    continue
                            ###############################################################

                    except Exception as e:
                        print("獲取圖片列表錯誤")
                        print(img_slider)
                        print(e)
                        continue
                print("{}已經(jīng)操作完畢".format(url))
            except Exception as e:
                print("基本錯誤")
                print(e)

圖片會在你提前寫好的images文件夾里面快速的生成

tasks最多可以開1024協(xié)程，但是建議你開100個就OK了，太多并發(fā)，人家服務(wù)器吃不消。

以上操作執(zhí)行完畢，在添加一些細(xì)節(jié)，比如保存到指定文件夾，就OK了。