import requests  # 數(shù)據(jù)請(qǐng)求模塊 第三方模塊 pip install requests
import parsel  # 數(shù)據(jù)解析模塊 第三方模塊 pip install parsel
import re  # 正則表達(dá)式模塊
import time  # 時(shí)間模塊
import concurrent.futures

start_time = time.time()

for page in range(1, 11):
    url = f'https://fabiaoqing.com/biaoqing/lists/page/{page}html'
     headers = {
         'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.54 Safari/537.36'
     }
     response = requests.get(url=url, headers=headers)
     # <Response [200]> response 對(duì)象 200狀態(tài)碼 表示請(qǐng)求成功

# 在開(kāi)發(fā)者工具上面 元素面板 看到有相應(yīng)標(biāo)簽數(shù)據(jù), 但是我發(fā)送請(qǐng)求之后 沒(méi)有這樣的數(shù)據(jù)返回
# 我們要提取數(shù)據(jù), 要根據(jù)服務(wù)器返回?cái)?shù)據(jù)內(nèi)容
# xpath 解析方法 parsel 解析模塊  parsel這個(gè)模塊里面就可以調(diào)用xpath解析方法
# print(response.text)

# 解析速度 bs4 解析速度會(huì)慢一些 如果你想要對(duì)于字符串?dāng)?shù)據(jù)內(nèi)容 直接取值 只能正則表達(dá)式
     selector = parsel.Selector(response.text) # 把獲取下來(lái)html字符串?dāng)?shù)據(jù)內(nèi)容 轉(zhuǎn)成 selector 對(duì)象
     title_list = selector.css('.ui.image.lazy::attr(title)').getall()
     img_list = selector.css('.ui.image.lazy::attr(data-original)').getall()
# 把獲取下來(lái)的這兩個(gè)列表 提取里面元素 一一提取出來(lái)
# 提取列表元素 for循環(huán) 遍歷
     for title, img_url in zip(title_list, img_list):

# split() 字符串分割的方法 根據(jù)列表索引位置取值
# img_name_1 = img_url[-3:] # 通過(guò)字符串?dāng)?shù)據(jù) 進(jìn)行切片
# 從左往右 索引位置 是從 0 開(kāi)始 從右往左 是 -1開(kāi)始
         # print(title, img_url)
         title = re.sub(r'[\/:*?"<>|\n]', '_', title)
         # 名字太長(zhǎng) 報(bào)錯(cuò)
         img_name = img_url.split('.')[-1]   # 通過(guò)split() 字符串分割的方法 根據(jù)列表索引位置取值
         img_content = requests.get(url=img_url).content # 獲取圖片的二進(jìn)制數(shù)據(jù)內(nèi)容
         with open('img\\' + title + '.' + img_name, mode='wb') as f:
             f.write(img_content)
         print(title)

def get_response(html_url):
    """發(fā)送請(qǐng)求"""
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.54 Safari/537.36'
    }
    response = requests.get(url=html_url, headers=headers)
    return response

def get_img_info(html_url):
    """獲取圖片url地址 以及 圖片名字"""
    response = get_response(html_url)
    selector = parsel.Selector(response.text)  # 把獲取下來(lái)html字符串?dāng)?shù)據(jù)內(nèi)容 轉(zhuǎn)成 selector 對(duì)象
    title_list = selector.css('.ui.image.lazy::attr(title)').getall()
    img_list = selector.css('.ui.image.lazy::attr(data-original)').getall()
    zip_data = zip(title_list, img_list)
    return zip_data

def save(title, img_url):
    """保存數(shù)據(jù)"""
    title = re.sub(r'[\/:*?"<>|\n]', '_', title)
    # 名字太長(zhǎng) 報(bào)錯(cuò)
    img_name = img_url.split('.')[-1]  # 通過(guò)split() 字符串分割的方法 根據(jù)列表索引位置取值
    img_content = requests.get(url=img_url).content  # 獲取圖片的二進(jìn)制數(shù)據(jù)內(nèi)容
    with open('img\\' + title + '.' + img_name, mode='wb') as f:
        f.write(img_content)
    print(title)

def main(html_url):
    zip_data = get_img_info(html_url)
    for title, img_url in zip_data:
        save(title, img_url)

if __name__ == '__main__':
    start_time = time.time()
    exe = concurrent.futures.ThreadPoolExecutor(max_workers=10)
    for page in range(1, 11):
        # 1. 發(fā)送請(qǐng)求
        url = f'https://fabiaoqing.com/biaoqing/lists/page/{page}html'
        exe.submit(main, url)
    exe.shutdown()
    end_time = time.time()
    use_time = int(end_time - start_time)
    print('程序耗時(shí): ', use_time)