You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
336 lines
16 KiB
336 lines
16 KiB
import asyncio |
|
import base64 |
|
import pandas as pd |
|
from pandas import DataFrame |
|
from playwright.async_api import Playwright, async_playwright, Error |
|
from asgiref.sync import sync_to_async |
|
import time |
|
from django.http import HttpResponseBadRequest, HttpResponse |
|
from django.views import View |
|
from Recipe.models import Dish |
|
|
|
|
|
class RecipeCrawlerView(View): |
|
def get(self, request): |
|
sync_main() |
|
return HttpResponse("Success!", content_type="text/plain") |
|
|
|
|
|
# 因應django ORM，以同步函數執行非同步程式 |
|
def sync_main(): |
|
# 使用sync_to_async包装器調用非同步函數 |
|
asyncio.run(main()) |
|
|
|
|
|
async def save_to_db(dish_data): |
|
# 将异步ORM操作转换为同步，以适应Django ORM |
|
dish, created = await sync_to_async(Dish.objects.update_or_create)( |
|
name=dish_data['name'], |
|
defaults=dish_data |
|
) |
|
action = "added" if created else "updated" |
|
print(f"Dish '{dish.name}' was {action}.") |
|
|
|
|
|
# 將圖片轉為base64 |
|
async def fetch_image_as_base64(page, image_url): |
|
print("Fetching image from URL:", image_url) |
|
try: |
|
response = await page.request.get(image_url) |
|
if response.ok: |
|
image_data = await response.body() |
|
image_base64 = base64.b64encode(image_data).decode() |
|
return image_base64 |
|
except Exception as e: |
|
print(f"Error fetching image: {e}") |
|
return None |
|
|
|
|
|
async def run(playwright: Playwright): |
|
browser = await playwright.chromium.launch(headless=False) |
|
context = await browser.new_context() |
|
page = await context.new_page() |
|
await page.goto("https://oishi-kenko.com/recipes") |
|
await page.get_by_role("link", name="ログイン").click() |
|
await page.get_by_role("link", name="メールアドレス でログイン").click() |
|
await page.locator("#secure_account_credential_email").click() |
|
await page.locator("#secure_account_credential_email").fill("asd851117005545@gmail.com") |
|
await page.locator("#secure_account_credential_email").press("Tab") |
|
await page.locator("#secure_account_credential_password").fill("a22897051") |
|
await page.get_by_role("button", name="ログイン").click() |
|
await page.goto("https://oishi-kenko.com/recipes") |
|
|
|
|
|
|
|
max_retries = 3 |
|
|
|
while True: |
|
# 訂位到所有匹配連結 |
|
links = page.locator('a.p-recipe-list-item__title-link') |
|
|
|
# 獲取連結數量 |
|
link_count = await links.count() |
|
|
|
# 點擊每個連結 |
|
for i in range(link_count): |
|
retry_count = 0 # 设置重试次数计数器 |
|
while retry_count < 3: # 假设最多重试3次 |
|
# 使用 nth(i) 定位第 i 個元素，並點擊 |
|
|
|
try: |
|
await page.locator('a.p-recipe-list-item__title-link').nth(i).click() |
|
|
|
# 等待頁面 |
|
await page.wait_for_load_state('networkidle') |
|
# await asyncio.sleep(5) |
|
|
|
print("------菜名-----") |
|
# 輸出名稱 |
|
dishname = await page.text_content('.p-recipe-detail__title') |
|
print(dishname) |
|
dishname_clean = dishname.strip().replace('\n', '') |
|
|
|
# 菜名圖片 |
|
image_element = page.locator('.p-recipe-detail__photo-image--pc-only') |
|
|
|
# 从元素的 'src' 属性中获取图片的 URL |
|
image_url = await image_element.get_attribute('src') |
|
|
|
# 确保获取到的 URL 不为空 |
|
if image_url: |
|
# 获取图片的 Base64 编码 |
|
Dish_image_base64 = await fetch_image_as_base64(page, image_url) |
|
else: |
|
Dish_image_base64 = None |
|
|
|
# print("------按讚數-----") |
|
# 輸出按讚數 |
|
Like_count = await page.text_content('.c-button-circle__top-text') |
|
# print(Likes_count) |
|
Likes_count_clean = Like_count.strip().replace('\n', '') |
|
|
|
# print("------標籤-----") |
|
# 輸出標籤 |
|
tags = await page.locator('.c-button-round-tag__link').all_text_contents() |
|
# for tag in tags: |
|
# print(tag) |
|
tags_clean = [tag.strip() for tag in tags] |
|
|
|
# print("------適應症-----") |
|
# 輸出適應症 |
|
Indications = await page.locator('.c-recipes-relevant-dietary-concerns__text').all_text_contents() |
|
# for Indication in Indications: |
|
# print(Indication) |
|
Indications_clean = [Indication.strip() for Indication in Indications] |
|
|
|
# print("------營養標示-----") |
|
# 輸出營養標示 |
|
|
|
# 各營養標示分類 |
|
Calorie = '' |
|
Salt = '' |
|
Protein = '' |
|
Fat = '' |
|
Carbohydrate = '' |
|
Sugar = '' |
|
Dietary_fiber = '' |
|
Soluble_fiber = '' |
|
Insoluble_fiber = '' |
|
Potassium = '' |
|
Calcium = '' |
|
Magnesium = '' |
|
Phosphorous = '' |
|
Iron = '' |
|
Zinc = '' |
|
Iodine = '' |
|
Cholesterol = '' |
|
Vitamin_B1 = '' |
|
Vitamin_B2 = '' |
|
Vitamin_C = '' |
|
Vitamin_B6 = '' |
|
Vitamin_B12 = '' |
|
Folate = '' |
|
Vitamin_A = '' |
|
Vitamin_D = '' |
|
Vitamin_K = '' |
|
Vitamin_E = '' |
|
Saturated_fatty_acid = '' |
|
Monounsaturated_fatty_acid = '' |
|
Polyunsaturated_fatty_acid = '' |
|
|
|
nutritions1 = await page.locator('.c-nutrition-table__cell--1').all_text_contents() |
|
# for nutrition in nutritions1: |
|
# print(nutrition) |
|
# nutritions_clean = [nutrition.strip().replace('\n', '') for nutrition in nutritions] |
|
for nutrition1 in nutritions1: |
|
if 'エネルギー' in nutrition1: |
|
Calorie = nutrition1.split('エネルギー')[1].strip().replace('\n', '') |
|
if '食塩相当量' in nutrition1: |
|
Salt = nutrition1.split('食塩相当量')[1].strip().replace('\n', '') |
|
if 'たんぱく質' in nutrition1: |
|
Protein = nutrition1.split('たんぱく質')[1].strip().replace('\n', '') |
|
if '脂質' in nutrition1: |
|
Fat = nutrition1.split('脂質')[1].strip().replace('\n', '') |
|
if '炭水化物' in nutrition1: |
|
Carbohydrate = nutrition1.split('炭水化物')[1].strip().replace('\n', '') |
|
if '糖質' in nutrition1: |
|
Sugar = nutrition1.split('糖質')[1].strip().replace('\n', '') |
|
if '食物繊維' in nutrition1: |
|
Dietary_fiber = nutrition1.split('食物繊維')[1].strip().replace('\n', '') |
|
if '水溶性食物繊維' in nutrition1: |
|
Soluble_fiber = nutrition1.split('水溶性食物繊維')[1].strip().replace('\n', '') |
|
if '不溶性食物繊維' in nutrition1: |
|
Insoluble_fiber = nutrition1.split('不溶性食物繊維')[1].strip().replace('\n', '') |
|
if 'カリウム' in nutrition1: |
|
Potassium = nutrition1.split('カリウム')[1].strip().replace('\n', '') |
|
|
|
nutritions2 = await page.locator('.c-nutrition-table__cell--2').all_text_contents() |
|
|
|
for nutrition2 in nutritions2: |
|
if 'カルシウム' in nutrition2: |
|
Calcium = nutrition2.split('カルシウム')[1].strip().replace('\n', '') |
|
if 'マグネシウム' in nutrition2: |
|
Magnesium = nutrition2.split('マグネシウム')[1].strip().replace('\n', '') |
|
if 'リン' in nutrition2: |
|
Phosphorous = nutrition2.split('リン')[1].strip().replace('\n', '') |
|
if '鉄' in nutrition2: |
|
Iron = nutrition2.split('鉄')[1].strip().replace('\n', '') |
|
if '亜鉛' in nutrition2: |
|
Zinc = nutrition2.split('亜鉛')[1].strip().replace('\n', '') |
|
if 'ヨウ素' in nutrition2: |
|
Iodine = nutrition2.split('ヨウ素')[1].strip().replace('\n', '') |
|
if 'コレステロール' in nutrition2: |
|
Cholesterol = nutrition2.split('コレステロール')[1].strip().replace('\n', '') |
|
if 'ビタミンB1' in nutrition2: |
|
Vitamin_B1 = nutrition2.split('ビタミンB1')[1].strip().replace('\n', '') |
|
if 'ビタミンB2' in nutrition2: |
|
Vitamin_B2 = nutrition2.split('ビタミンB2')[1].strip().replace('\n', '') |
|
if 'ビタミンC' in nutrition2: |
|
Vitamin_C = nutrition2.split('ビタミンC')[1].strip().replace('\n', '') |
|
|
|
nutritions3 = await page.locator('.c-nutrition-table__cell--3').all_text_contents() |
|
|
|
for nutrition3 in nutritions3: |
|
if 'ビタミンB6' in nutrition3: |
|
Vitamin_B6 = nutrition3.split('ビタミンB6')[1].strip().replace('\n', '') |
|
if 'ビタミンB12' in nutrition3: |
|
Vitamin_B12 = nutrition3.split('ビタミンB12')[1].strip().replace('\n', '') |
|
if '葉酸' in nutrition3: |
|
Folate = nutrition3.split('葉酸')[1].strip().replace('\n', '') |
|
if 'ビタミンA' in nutrition3: |
|
Vitamin_A = nutrition3.split('ビタミンA')[1].strip().replace('\n', '') |
|
if 'ビタミンD' in nutrition3: |
|
Vitamin_D = nutrition3.split('ビタミンD')[1].strip().replace('\n', '') |
|
if 'ビタミンK' in nutrition3: |
|
Vitamin_K = nutrition3.split('ビタミンK')[1].strip().replace('\n', '') |
|
if 'ビタミンE' in nutrition3: |
|
Vitamin_E = nutrition3.split('ビタミンE')[1].strip().replace('\n', '') |
|
if '飽和脂肪酸' in nutrition3: |
|
Saturated_fatty_acid = nutrition3.split('飽和脂肪酸')[1].strip().replace('\n', '') |
|
if '一価不飽和脂肪酸' in nutrition3: |
|
Monounsaturated_fatty_acid = nutrition3.split('一価不飽和脂肪酸')[1].strip().replace('\n', '') |
|
if '多価不飽和脂肪酸' in nutrition3: |
|
Polyunsaturated_fatty_acid = nutrition3.split('多価不飽和脂肪酸')[1].strip().replace('\n', '') |
|
|
|
# 食料 |
|
Ingredients = await page.locator('.p-recipe-ingredient-list__item').all_text_contents() |
|
# for Ingredient in Ingredients: |
|
# print(Ingredient) |
|
Ingredients_clean = [Ingredient.strip().replace('\n', '') for Ingredient in Ingredients] |
|
|
|
print('------作法步驟-----') |
|
|
|
# 作法 |
|
Steps = await page.locator('.p-recipe-step__item').all_text_contents() |
|
# for Step in Steps: |
|
# print(Step) |
|
Steps_clean = [Step.strip().replace('\n', '') for Step in Steps] |
|
|
|
# 定位到所有步骤的图片元素 |
|
image_elements = page.locator('.p-recipe-step__item-image') |
|
|
|
# 获取所有图片元素的 src 属性（即图片的 URL） |
|
image_urls = await image_elements.evaluate_all("elements => elements.map(e => e.getAttribute('src'))") |
|
|
|
# 遍历图片 URL 列表，下载图片并转换为 Base64 |
|
Step_images_base64 = [] |
|
for image_url in image_urls: |
|
# 直接使用图片的 URL 下载图片并转换为 Base64 |
|
image_base64 = await fetch_image_as_base64(page, image_url) |
|
if image_base64: |
|
Step_images_base64.append(image_base64) |
|
|
|
dish_data = { |
|
'name': dishname_clean, |
|
'image': Dish_image_base64, |
|
'likes': Likes_count_clean, |
|
'tags': ", ".join(tags_clean), |
|
'indications': ", ".join(Indications_clean), |
|
'Calories': Calorie, |
|
'Salt': Salt, |
|
'Protein': Protein, |
|
'Total_fat': Fat, |
|
'Total_Carbohydrate': Carbohydrate, |
|
'Total_sugar': Sugar, |
|
'Dietary_fiber': Dietary_fiber, |
|
'Soluble_fiber': Soluble_fiber, |
|
'Insoluble_fiber': Insoluble_fiber, |
|
'K': Potassium, |
|
'Ca': Calcium, |
|
'Mg': Magnesium, |
|
'P': Phosphorous, |
|
'Fe': Iron, |
|
'Zn': Zinc, |
|
'I': Iodine, |
|
'Cholesterol': Cholesterol, |
|
'Vitamin_B1': Vitamin_B1, |
|
'Vitamin_B2': Vitamin_B2, |
|
'Vitamin_C': Vitamin_C, |
|
'Vitamin_B6': Vitamin_B6, |
|
'Vitamin_B12': Vitamin_B12, |
|
'Folate': Folate, |
|
'Vitamin_A': Vitamin_A, |
|
'Vitamin_D': Vitamin_D, |
|
'Vitamin_K': Vitamin_K, |
|
'Vitamin_E': Vitamin_E, |
|
'Saturated_fatty_acid': Saturated_fatty_acid, |
|
'Monounsaturated_fatty_acid': Monounsaturated_fatty_acid, |
|
'Polyunsaturated_fatty_acid': Polyunsaturated_fatty_acid, |
|
'Ingredients': ", ".join(Ingredients_clean), |
|
'Steps': Steps_clean, |
|
'Step_images_Base64': Step_images_base64 |
|
} |
|
|
|
await save_to_db(dish_data) |
|
|
|
break |
|
except Exception as e: # 捕获可能发生的异常 |
|
print(f"遇到错误：{e}，尝试返回并重试") |
|
await page.go_back() # 返回前一页 |
|
retry_count += 1 # 重试计数器加1 |
|
if retry_count >= 3: |
|
print("重试次数超限，跳过当前链接") |
|
break # 跳出循环，处理下一个链接 |
|
# 使用浏览器的后退功能返回列表页，这样不需要重新加载初始URL |
|
await page.go_back() |
|
|
|
try: |
|
await page.click('span.next a[rel="next"]') |
|
await page.wait_for_load_state('networkidle') |
|
except Error: |
|
# 如果“下一頁”不存在，break |
|
break |
|
# --------------------- |
|
await context.close() |
|
await browser.close() |
|
|
|
|
|
async def main() -> None: |
|
async with async_playwright() as playwright: |
|
await run(playwright) |
|
|
|
# asyncio.run(main()) |
|
# async def simple_test(): |
|
# print("Simple async test") |
|
# |
|
# asyncio.run(simple_test()) |