stephen.yu/RecipeCrawler
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

second commit

Browse Source
This commit is contained in:
stephen.yu
2024-03-14 16:00:29 +08:00
parent 5063429ab8
commit 50abf465c8
2 changed files with 213 additions and 217 deletions
Download Patch File Download Diff File Expand all files Collapse all files

76
Recipe/models.py
View File

@@ -5,41 +5,41 @@ from django.contrib.postgres.fields import JSONField
# Create your models here. # Create your models here.
class Dish(models.Model): class Dish(models.Model):
name = models.CharField(max_length=255, unique=True) # 假设每个菜名是唯一的 name = models.CharField(max_length=255, unique=True, help_text='菜名')
image = models.TextField() # 存储图片的 Base64 编码 image = models.TextField(help_text='菜品圖片')
likes = models.IntegerField(default=0) likes = models.IntegerField(default=0, help_text='按讚數')
tags = models.TextField() # 可以存储标签列表，例如以逗号分隔的字符串 tags = models.TextField(help_text='標籤')
indications = models.TextField() indications = models.TextField(help_text='適應症')
Calories = models.CharField(max_length=255, unique=False, blank=True, null=True) Calories = models.CharField(max_length=255, unique=False, blank=True, null=True, help_text='熱量')
Salt = models.CharField(max_length=255, unique=False, blank=True, null=True) Salt = models.CharField(max_length=255, unique=False, blank=True, null=True, help_text='食鹽相當量')
Protein = models.CharField(max_length=255, unique=False, blank=True, null=True) Protein = models.CharField(max_length=255, unique=False, blank=True, null=True, help_text='蛋白質')
Total_fat = models.CharField(max_length=255, unique=False, blank=True, null=True) Total_fat = models.CharField(max_length=255, unique=False, blank=True, null=True, help_text='總脂肪')
Total_Carbohydrate = models.CharField(max_length=255, unique=False, blank=True, null=True) Total_Carbohydrate = models.CharField(max_length=255, unique=False, blank=True, null=True, help_text='總碳水化合物')
Total_sugar = models.CharField(max_length=255, unique=False, blank=True, null=True) Total_sugar = models.CharField(max_length=255, unique=False, blank=True, null=True, help_text='總糖分')
Dietary_fiber = models.CharField(max_length=255, unique=False, blank=True, null=True) Dietary_fiber = models.CharField(max_length=255, unique=False, blank=True, null=True, help_text='膳食纖維')
Soluble_fiber = models.CharField(max_length=255, unique=False, blank=True, null=True) Soluble_fiber = models.CharField(max_length=255, unique=False, blank=True, null=True, help_text='水溶性纖維')
Insoluble_fiber = models.CharField(max_length=255, unique=False, blank=True, null=True) Insoluble_fiber = models.CharField(max_length=255, unique=False, blank=True, null=True, help_text='非水溶性纖維')
K = models.CharField(max_length=255, unique=False, blank=True, null=True) K = models.CharField(max_length=255, unique=False, blank=True, null=True, help_text='鉀')
Ca = models.CharField(max_length=255, unique=False, blank=True, null=True) Ca = models.CharField(max_length=255, unique=False, blank=True, null=True, help_text='鈣')
Mg = models.CharField(max_length=255, unique=False, blank=True, null=True) Mg = models.CharField(max_length=255, unique=False, blank=True, null=True, help_text='鎂')
P = models.CharField(max_length=255, unique=False, blank=True, null=True) P = models.CharField(max_length=255, unique=False, blank=True, null=True, help_text='磷')
Fe = models.CharField(max_length=255, unique=False, blank=True, null=True) Fe = models.CharField(max_length=255, unique=False, blank=True, null=True, help_text='鐵')
Zn = models.CharField(max_length=255, unique=False, blank=True, null=True) Zn = models.CharField(max_length=255, unique=False, blank=True, null=True, help_text='鋅')
I = models.CharField(max_length=255, unique=False, blank=True, null=True) I = models.CharField(max_length=255, unique=False, blank=True, null=True, help_text='碘')
Cholesterol = models.CharField(max_length=255, unique=False, blank=True, null=True) Cholesterol = models.CharField(max_length=255, unique=False, blank=True, null=True, help_text='膽固醇')
Vitamin_B1 = models.CharField(max_length=255, unique=False, blank=True, null=True) Vitamin_B1 = models.CharField(max_length=255, unique=False, blank=True, null=True, help_text='維生素B1')
Vitamin_B2 = models.CharField(max_length=255, unique=False, blank=True, null=True) Vitamin_B2 = models.CharField(max_length=255, unique=False, blank=True, null=True, help_text='維生素B2')
Vitamin_C = models.CharField(max_length=255, unique=False, blank=True, null=True) Vitamin_C = models.CharField(max_length=255, unique=False, blank=True, null=True, help_text='維生素C')
Vitamin_B6 = models.CharField(max_length=255, unique=False, blank=True, null=True) Vitamin_B6 = models.CharField(max_length=255, unique=False, blank=True, null=True, help_text='維生素B6')
Vitamin_B12 = models.CharField(max_length=255, unique=False, blank=True, null=True) Vitamin_B12 = models.CharField(max_length=255, unique=False, blank=True, null=True, help_text='維生素B12')
Folate = models.CharField(max_length=255, unique=False, blank=True, null=True) Folate = models.CharField(max_length=255, unique=False, blank=True, null=True, help_text='葉酸')
Vitamin_A = models.CharField(max_length=255, unique=False, blank=True, null=True) Vitamin_A = models.CharField(max_length=255, unique=False, blank=True, null=True, help_text='維生素A')
Vitamin_D = models.CharField(max_length=255, unique=False, blank=True, null=True) Vitamin_D = models.CharField(max_length=255, unique=False, blank=True, null=True, help_text='維生素D')
Vitamin_K = models.CharField(max_length=255, unique=False, blank=True, null=True) Vitamin_K = models.CharField(max_length=255, unique=False, blank=True, null=True, help_text='維生素K')
Vitamin_E = models.CharField(max_length=255, unique=False, blank=True, null=True) Vitamin_E = models.CharField(max_length=255, unique=False, blank=True, null=True, help_text='維生素E')
Saturated_fatty_acid = models.CharField(max_length=255, unique=False, blank=True, null=True) Saturated_fatty_acid = models.CharField(max_length=255, unique=False, blank=True, null=True, help_text='飽和脂肪酸')
Monounsaturated_fatty_acid = models.CharField(max_length=255, unique=False, blank=True, null=True) Monounsaturated_fatty_acid = models.CharField(max_length=255, unique=False, blank=True, null=True, help_text='單元不飽和脂肪酸')
Polyunsaturated_fatty_acid = models.CharField(max_length=255, unique=False, blank=True, null=True) Polyunsaturated_fatty_acid = models.CharField(max_length=255, unique=False, blank=True, null=True, help_text='多元不飽和脂肪酸')
Ingredients = models.TextField() Ingredients = models.TextField(help_text='食材')
Steps = models.JSONField() Steps = models.JSONField(help_text='製作步驟')
Step_images_Base64 = models.JSONField() Step_images_Base64 = models.JSONField(help_text='製作步驟圖片')

354
Recipe/views.py
View File

@@ -1,10 +1,8 @@
import asyncio import asyncio
import base64 import base64
import pandas as pd
from pandas import DataFrame
from playwright.async_api import Playwright, async_playwright, Error from playwright.async_api import Playwright, async_playwright, Error
from asgiref.sync import sync_to_async from asgiref.sync import sync_to_async
import time
from django.http import HttpResponseBadRequest, HttpResponse from django.http import HttpResponseBadRequest, HttpResponse
from django.views import View from django.views import View
from Recipe.models import Dish from Recipe.models import Dish
@@ -22,14 +20,14 @@ def sync_main():
asyncio.run(main()) asyncio.run(main())
async def save_to_db(dish_data): async def save_to_db(dDish_data):
# 将异步ORM操作转换为同步，以适应Django ORM # 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)( dish, created = await sync_to_async(Dish.objects.update_or_create)(
name=dish_data['name'], name= dDish_data['name'],
defaults=dish_data defaults= dDish_data
) )
action = "added" if created else "updated" sAction = "added" if created else "updated"
print(f"Dish '{dish.name}' was {action}.") print(f"Dish '{dish.name}' was {sAction}.")
# 將圖片轉為base64 # 將圖片轉為base64
@@ -39,8 +37,8 @@ async def fetch_image_as_base64(page, image_url):
response = await page.request.get(image_url) response = await page.request.get(image_url)
if response.ok: if response.ok:
image_data = await response.body() image_data = await response.body()
image_base64 = base64.b64encode(image_data).decode() sImage_base64 = base64.b64encode(image_data).decode()
return image_base64 return sImage_base64
except Exception as e: except Exception as e:
print(f"Error fetching image: {e}") print(f"Error fetching image: {e}")
return None return None
@@ -62,21 +60,19 @@ async def run(playwright: Playwright):
max_retries = 3
while True: while True:
# 訂位到所有匹配連結 # 訂位到所有匹配連結
links = page.locator('a.p-recipe-list-item__title-link') links = page.locator('a.p-recipe-list-item__title-link')
# 獲取連結數量 # 獲取連結數量
link_count = await links.count() iLink_count = await links.count()
# 點擊每個連結 # 點擊每個連結
for i in range(link_count): for i in range(iLink_count):
retry_count = 0 # 设置重试次数计数器 iRetry_count = 0 # 设置重试次数计数器
while retry_count < 3: # 假设最多重试3次 while iRetry_count < 3: # 假设最多重试3次
# 使用 nth(i) 定位第 i 個元素，並點擊
# 使用 nth(i) 定位第 i 個元素，並點擊
try: try:
await page.locator('a.p-recipe-list-item__title-link').nth(i).click() await page.locator('a.p-recipe-list-item__title-link').nth(i).click()
@@ -86,229 +82,229 @@ async def run(playwright: Playwright):
print("------菜名-----") print("------菜名-----")
# 輸出名稱 # 輸出名稱
dishname = await page.text_content('.p-recipe-detail__title') sDishname = await page.text_content('.p-recipe-detail__title')
print(dishname) print(sDishname)
dishname_clean = dishname.strip().replace('\n', '') sDishname_clean = sDishname.strip().replace('\n', '')
# 菜名圖片 # 菜名圖片
image_element = page.locator('.p-recipe-detail__photo-image--pc-only') 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 # 从元素的 'src' 属性中获取图片的 URL
image_url = await image_element.get_attribute('src') sImage_url = await image_element.get_attribute('src')
# 确保获取到的 URL 不为空 # 确保获取到的 URL 不为空
if image_url: if sImage_url:
# 获取图片的 Base64 编码 # 获取图片的 Base64 编码
Dish_image_base64 = await fetch_image_as_base64(page, image_url) sDish_image_base64 = await fetch_image_as_base64(page, sImage_url)
else: else:
Dish_image_base64 = None sDish_image_base64 = None
# print("------按讚數-----") # print("------按讚數-----")
# 輸出按讚數 # 輸出按讚數
Like_count = await page.text_content('.c-button-circle__top-text') sLike_count = await page.text_content('.c-button-circle__top-text')
# print(Likes_count) # print(Likes_count)
Likes_count_clean = Like_count.strip().replace('\n', '') sLikes_count_clean = sLike_count.strip().replace('\n', '')
# print("------標籤-----") # print("------標籤-----")
# 輸出標籤 # 輸出標籤
tags = await page.locator('.c-button-round-tag__link').all_text_contents() lTags = await page.locator('.c-button-round-tag__link').all_text_contents()
# for tag in tags: # for tag in tags:
# print(tag) # print(tag)
tags_clean = [tag.strip() for tag in tags] lTags_clean = [sTag.strip() for sTag in lTags]
# print("------適應症-----") # print("------適應症-----")
# 輸出適應症 # 輸出適應症
Indications = await page.locator('.c-recipes-relevant-dietary-concerns__text').all_text_contents() lIndications = await page.locator('.c-recipes-relevant-dietary-concerns__text').all_text_contents()
# for Indication in Indications: # for Indication in Indications:
# print(Indication) # print(Indication)
Indications_clean = [Indication.strip() for Indication in Indications] lIndications_clean = [sIndication.strip() for sIndication in lIndications]
# print("------營養標示-----") # print("------營養標示-----")
# 輸出營養標示 # 輸出營養標示
# 各營養標示分類 # 各營養標示分類
Calorie = '' sCalorie = ''
Salt = '' sSalt = ''
Protein = '' sProtein = ''
Fat = '' sFat = ''
Carbohydrate = '' sCarbohydrate = ''
Sugar = '' sSugar = ''
Dietary_fiber = '' sDietary_fiber = ''
Soluble_fiber = '' sSoluble_fiber = ''
Insoluble_fiber = '' sInsoluble_fiber = ''
Potassium = '' sPotassium = ''
Calcium = '' sCalcium = ''
Magnesium = '' sMagnesium = ''
Phosphorous = '' sPhosphorous = ''
Iron = '' sIron = ''
Zinc = '' sZinc = ''
Iodine = '' sIodine = ''
Cholesterol = '' sCholesterol = ''
Vitamin_B1 = '' sVitamin_B1 = ''
Vitamin_B2 = '' sVitamin_B2 = ''
Vitamin_C = '' sVitamin_C = ''
Vitamin_B6 = '' sVitamin_B6 = ''
Vitamin_B12 = '' sVitamin_B12 = ''
Folate = '' sFolate = ''
Vitamin_A = '' sVitamin_A = ''
Vitamin_D = '' sVitamin_D = ''
Vitamin_K = '' sVitamin_K = ''
Vitamin_E = '' sVitamin_E = ''
Saturated_fatty_acid = '' sSaturated_fatty_acid = ''
Monounsaturated_fatty_acid = '' sMonounsaturated_fatty_acid = ''
Polyunsaturated_fatty_acid = '' sPolyunsaturated_fatty_acid = ''
nutritions1 = await page.locator('.c-nutrition-table__cell--1').all_text_contents() lNutritions1 = await page.locator('.c-nutrition-table__cell--1').all_text_contents()
# for nutrition in nutritions1: # for nutrition in nutritions1:
# print(nutrition) # print(nutrition)
# nutritions_clean = [nutrition.strip().replace('\n', '') for nutrition in nutritions] # nutritions_clean = [nutrition.strip().replace('\n', '') for nutrition in nutritions]
for nutrition1 in nutritions1: for sNutrition1 in lNutritions1:
if 'エネルギー' in nutrition1: if 'エネルギー' in sNutrition1:
Calorie = nutrition1.split('エネルギー')[1].strip().replace('\n', '') sCalorie = sNutrition1.split('エネルギー')[1].strip().replace('\n', '')
if '食塩相当量' in nutrition1: if '食塩相当量' in sNutrition1:
Salt = nutrition1.split('食塩相当量')[1].strip().replace('\n', '') sSalt = sNutrition1.split('食塩相当量')[1].strip().replace('\n', '')
if 'たんぱく質' in nutrition1: if 'たんぱく質' in sNutrition1:
Protein = nutrition1.split('たんぱく質')[1].strip().replace('\n', '') sProtein = sNutrition1.split('たんぱく質')[1].strip().replace('\n', '')
if '脂質' in nutrition1: if '脂質' in sNutrition1:
Fat = nutrition1.split('脂質')[1].strip().replace('\n', '') sFat = sNutrition1.split('脂質')[1].strip().replace('\n', '')
if '炭水化物' in nutrition1: if '炭水化物' in sNutrition1:
Carbohydrate = nutrition1.split('炭水化物')[1].strip().replace('\n', '') sCarbohydrate = sNutrition1.split('炭水化物')[1].strip().replace('\n', '')
if '糖質' in nutrition1: if '糖質' in sNutrition1:
Sugar = nutrition1.split('糖質')[1].strip().replace('\n', '') sSugar = sNutrition1.split('糖質')[1].strip().replace('\n', '')
if '食物繊維' in nutrition1: if '食物繊維' in sNutrition1:
Dietary_fiber = nutrition1.split('食物繊維')[1].strip().replace('\n', '') sDietary_fiber = sNutrition1.split('食物繊維')[1].strip().replace('\n', '')
if '水溶性食物繊維' in nutrition1: if '水溶性食物繊維' in sNutrition1:
Soluble_fiber = nutrition1.split('水溶性食物繊維')[1].strip().replace('\n', '') sSoluble_fiber = sNutrition1.split('水溶性食物繊維')[1].strip().replace('\n', '')
if '不溶性食物繊維' in nutrition1: if '不溶性食物繊維' in sNutrition1:
Insoluble_fiber = nutrition1.split('不溶性食物繊維')[1].strip().replace('\n', '') sInsoluble_fiber = sNutrition1.split('不溶性食物繊維')[1].strip().replace('\n', '')
if 'カリウム' in nutrition1: if 'カリウム' in sNutrition1:
Potassium = nutrition1.split('カリウム')[1].strip().replace('\n', '') sPotassium = sNutrition1.split('カリウム')[1].strip().replace('\n', '')
nutritions2 = await page.locator('.c-nutrition-table__cell--2').all_text_contents() lNutritions2 = await page.locator('.c-nutrition-table__cell--2').all_text_contents()
for nutrition2 in nutritions2: for sNutrition2 in lNutritions2:
if 'カルシウム' in nutrition2: if 'カルシウム' in sNutrition2:
Calcium = nutrition2.split('カルシウム')[1].strip().replace('\n', '') sCalcium = sNutrition2.split('カルシウム')[1].strip().replace('\n', '')
if 'マグネシウム' in nutrition2: if 'マグネシウム' in sNutrition2:
Magnesium = nutrition2.split('マグネシウム')[1].strip().replace('\n', '') sMagnesium = sNutrition2.split('マグネシウム')[1].strip().replace('\n', '')
if 'リン' in nutrition2: if 'リン' in sNutrition2:
Phosphorous = nutrition2.split('リン')[1].strip().replace('\n', '') sPhosphorous = sNutrition2.split('リン')[1].strip().replace('\n', '')
if '鉄' in nutrition2: if '鉄' in sNutrition2:
Iron = nutrition2.split('鉄')[1].strip().replace('\n', '') sIron = sNutrition2.split('鉄')[1].strip().replace('\n', '')
if '亜鉛' in nutrition2: if '亜鉛' in sNutrition2:
Zinc = nutrition2.split('亜鉛')[1].strip().replace('\n', '') sZinc = sNutrition2.split('亜鉛')[1].strip().replace('\n', '')
if 'ヨウ素' in nutrition2: if 'ヨウ素' in sNutrition2:
Iodine = nutrition2.split('ヨウ素')[1].strip().replace('\n', '') sIodine = sNutrition2.split('ヨウ素')[1].strip().replace('\n', '')
if 'コレステロール' in nutrition2: if 'コレステロール' in sNutrition2:
Cholesterol = nutrition2.split('コレステロール')[1].strip().replace('\n', '') sCholesterol = sNutrition2.split('コレステロール')[1].strip().replace('\n', '')
if 'ビタミンB1' in nutrition2: if 'ビタミンB1' in sNutrition2:
Vitamin_B1 = nutrition2.split('ビタミンB1')[1].strip().replace('\n', '') sVitamin_B1 = sNutrition2.split('ビタミンB1')[1].strip().replace('\n', '')
if 'ビタミンB2' in nutrition2: if 'ビタミンB2' in sNutrition2:
Vitamin_B2 = nutrition2.split('ビタミンB2')[1].strip().replace('\n', '') sVitamin_B2 = sNutrition2.split('ビタミンB2')[1].strip().replace('\n', '')
if 'ビタミンC' in nutrition2: if 'ビタミンC' in sNutrition2:
Vitamin_C = nutrition2.split('ビタミンC')[1].strip().replace('\n', '') sVitamin_C = sNutrition2.split('ビタミンC')[1].strip().replace('\n', '')
nutritions3 = await page.locator('.c-nutrition-table__cell--3').all_text_contents() lNutritions3 = await page.locator('.c-nutrition-table__cell--3').all_text_contents()
for nutrition3 in nutritions3: for sNutrition3 in lNutritions3:
if 'ビタミンB6' in nutrition3: if 'ビタミンB6' in sNutrition3:
Vitamin_B6 = nutrition3.split('ビタミンB6')[1].strip().replace('\n', '') sVitamin_B6 = sNutrition3.split('ビタミンB6')[1].strip().replace('\n', '')
if 'ビタミンB12' in nutrition3: if 'ビタミンB12' in sNutrition3:
Vitamin_B12 = nutrition3.split('ビタミンB12')[1].strip().replace('\n', '') sVitamin_B12 = sNutrition3.split('ビタミンB12')[1].strip().replace('\n', '')
if '葉酸' in nutrition3: if '葉酸' in sNutrition3:
Folate = nutrition3.split('葉酸')[1].strip().replace('\n', '') sFolate = sNutrition3.split('葉酸')[1].strip().replace('\n', '')
if 'ビタミンA' in nutrition3: if 'ビタミンA' in sNutrition3:
Vitamin_A = nutrition3.split('ビタミンA')[1].strip().replace('\n', '') sVitamin_A = sNutrition3.split('ビタミンA')[1].strip().replace('\n', '')
if 'ビタミンD' in nutrition3: if 'ビタミンD' in sNutrition3:
Vitamin_D = nutrition3.split('ビタミンD')[1].strip().replace('\n', '') sVitamin_D = sNutrition3.split('ビタミンD')[1].strip().replace('\n', '')
if 'ビタミンK' in nutrition3: if 'ビタミンK' in sNutrition3:
Vitamin_K = nutrition3.split('ビタミンK')[1].strip().replace('\n', '') sVitamin_K = sNutrition3.split('ビタミンK')[1].strip().replace('\n', '')
if 'ビタミンE' in nutrition3: if 'ビタミンE' in sNutrition3:
Vitamin_E = nutrition3.split('ビタミンE')[1].strip().replace('\n', '') sVitamin_E = sNutrition3.split('ビタミンE')[1].strip().replace('\n', '')
if '飽和脂肪酸' in nutrition3: if '飽和脂肪酸' in sNutrition3:
Saturated_fatty_acid = nutrition3.split('飽和脂肪酸')[1].strip().replace('\n', '') sSaturated_fatty_acid = sNutrition3.split('飽和脂肪酸')[1].strip().replace('\n', '')
if '一価不飽和脂肪酸' in nutrition3: if '一価不飽和脂肪酸' in sNutrition3:
Monounsaturated_fatty_acid = nutrition3.split('一価不飽和脂肪酸')[1].strip().replace('\n', '') sMonounsaturated_fatty_acid = sNutrition3.split('一価不飽和脂肪酸')[1].strip().replace('\n', '')
if '多価不飽和脂肪酸' in nutrition3: if '多価不飽和脂肪酸' in sNutrition3:
Polyunsaturated_fatty_acid = nutrition3.split('多価不飽和脂肪酸')[1].strip().replace('\n', '') sPolyunsaturated_fatty_acid = sNutrition3.split('多価不飽和脂肪酸')[1].strip().replace('\n', '')
# 食料 # 食料
Ingredients = await page.locator('.p-recipe-ingredient-list__item').all_text_contents() lIngredients = await page.locator('.p-recipe-ingredient-list__item').all_text_contents()
# for Ingredient in Ingredients: # for Ingredient in Ingredients:
# print(Ingredient) # print(Ingredient)
Ingredients_clean = [Ingredient.strip().replace('\n', '') for Ingredient in Ingredients] lIngredients_clean = [sIngredient.strip().replace('\n', '') for sIngredient in lIngredients]
print('------作法步驟-----') print('------作法步驟-----')
# 作法 # 作法
Steps = await page.locator('.p-recipe-step__item').all_text_contents() lSteps = await page.locator('.p-recipe-step__item').all_text_contents()
# for Step in Steps: # for Step in Steps:
# print(Step) # print(Step)
Steps_clean = [Step.strip().replace('\n', '') for Step in Steps] lSteps_clean = [sStep.strip().replace('\n', '') for sStep in lSteps]
# 定位到所有步骤的图片元素 # 定位到所有步骤的图片元素
image_elements = page.locator('.p-recipe-step__item-image') 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） # 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'))") lImage_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 # 遍历图片 URL 列表，下载图片并转换为 Base64
Step_images_base64 = [] lStep_images_base64 = []
for image_url in image_urls: for sImage_url in lImage_urls:
# 直接使用图片的 URL 下载图片并转换为 Base64 # 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) sImage_base64 = await fetch_image_as_base64(page, sImage_url)
if image_base64: if sImage_base64:
Step_images_base64.append(image_base64) lStep_images_base64.append(sImage_base64)
dish_data = { dDish_data = {
'name': dishname_clean, 'name': sDishname_clean,
'image': Dish_image_base64, 'image': sDish_image_base64,
'likes': Likes_count_clean, 'likes': sLikes_count_clean,
'tags': ", ".join(tags_clean), 'tags': ", ".join(lTags_clean),
'indications': ", ".join(Indications_clean), 'indications': ", ".join(lIndications_clean),
'Calories': Calorie, 'Calories': sCalorie,
'Salt': Salt, 'Salt': sSalt,
'Protein': Protein, 'Protein': sProtein,
'Total_fat': Fat, 'Total_fat': sFat,
'Total_Carbohydrate': Carbohydrate, 'Total_Carbohydrate': sCarbohydrate,
'Total_sugar': Sugar, 'Total_sugar': sSugar,
'Dietary_fiber': Dietary_fiber, 'Dietary_fiber': sDietary_fiber,
'Soluble_fiber': Soluble_fiber, 'Soluble_fiber': sSoluble_fiber,
'Insoluble_fiber': Insoluble_fiber, 'Insoluble_fiber': sInsoluble_fiber,
'K': Potassium, 'K': sPotassium,
'Ca': Calcium, 'Ca': sCalcium,
'Mg': Magnesium, 'Mg': sMagnesium,
'P': Phosphorous, 'P': sPhosphorous,
'Fe': Iron, 'Fe': sIron,
'Zn': Zinc, 'Zn': sZinc,
'I': Iodine, 'I': sIodine,
'Cholesterol': Cholesterol, 'Cholesterol': sCholesterol,
'Vitamin_B1': Vitamin_B1, 'Vitamin_B1': sVitamin_B1,
'Vitamin_B2': Vitamin_B2, 'Vitamin_B2': sVitamin_B2,
'Vitamin_C': Vitamin_C, 'Vitamin_C': sVitamin_C,
'Vitamin_B6': Vitamin_B6, 'Vitamin_B6': sVitamin_B6,
'Vitamin_B12': Vitamin_B12, 'Vitamin_B12': sVitamin_B12,
'Folate': Folate, 'Folate': sFolate,
'Vitamin_A': Vitamin_A, 'Vitamin_A': sVitamin_A,
'Vitamin_D': Vitamin_D, 'Vitamin_D': sVitamin_D,
'Vitamin_K': Vitamin_K, 'Vitamin_K': sVitamin_K,
'Vitamin_E': Vitamin_E, 'Vitamin_E': sVitamin_E,
'Saturated_fatty_acid': Saturated_fatty_acid, 'Saturated_fatty_acid': sSaturated_fatty_acid,
'Monounsaturated_fatty_acid': Monounsaturated_fatty_acid, 'Monounsaturated_fatty_acid': sMonounsaturated_fatty_acid,
'Polyunsaturated_fatty_acid': Polyunsaturated_fatty_acid, 'Polyunsaturated_fatty_acid': sPolyunsaturated_fatty_acid,
'Ingredients': ", ".join(Ingredients_clean), 'Ingredients': ", ".join(lIngredients_clean),
'Steps': Steps_clean, 'Steps': lSteps_clean,
'Step_images_Base64': Step_images_base64 'Step_images_Base64': lStep_images_base64
} }
await save_to_db(dish_data) await save_to_db(dDish_data)
break break
except Exception as e: # 捕获可能发生的异常 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") print(f"遇到错误：{e}，尝试返回并重试")
await page.go_back() # 返回前一页 await page.go_back() # 返回前一页
retry_count += 1 # 重试计数器加1 iRetry_count += 1 # 重试计数器加1
if retry_count >= 3: if iRetry_count >= 3:
print("重试次数超限，跳过当前链接") 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 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 # 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