Загрузить файлы в «/»

pars_oem.py

@@ -0,0 +1,81 @@
+import csv
+import re
+import time
+import requests
+from bs4 import BeautifulSoup
+from tqdm import tqdm
+
+f = open('lynx_pn_input.txt', 'r')
+urls = f.read().split()
+f.close()
+with open('oen.csv', 'w', newline='', encoding='windows-1251') as csvfile:
+    writer = csv.writer(csvfile)
+    writer.writerow(
+        ['url', 'ID', 'Название', 'Описание', 'Фото', 'OeN', 'Аналоги'])
+    for url in tqdm(urls, desc="Processing", unit="iteration"):
+        try:
+            # Отправляем GET-запрос к странице
+            response = requests.get(url)
+
+            html_content = response.text
+
+            soup = BeautifulSoup(html_content, "html.parser")
+
+            data = [url]
+            IDD = soup.find("div", class_="pcard-model").get_text(strip=True)
+            if IDD:
+                data.append(IDD)
+            else:
+                data.append('None')
+            Name = soup.find("div", class_="pcard-name").get_text(strip=True)
+
+            if Name:
+                data.append(Name)
+            else:
+                data.append('None')
+
+            form_element = soup.find("div", id="pcard-props")
+            if form_element:
+                data.append(' | '.join([
+                                           f'{row.find("td", class_="title").get_text(strip=True)} {row.find("td", class_="value").get_text(strip=True)}'
+                                           for row in form_element.find_all("tr")]))
+            else:
+                data.append('None')
+
+            pcard_view_wrapper = soup.find("div", id="pcard-view-images")
+            if pcard_view_wrapper:
+                img = ' | '.join([img['src'] for img in pcard_view_wrapper.find_all('img')])
+                if img == 'https://lynxauto.info/image/trumb/400x300/no_image.jpg':
+                    data.append('None')
+                else:
+                    data.append(img)
+            else:
+                data.append('None')
+
+            OeN = []
+            table = soup.find('div', id='pcard-oeno')
+            if table:
+                for row in table.find_all('tr')[1:]:
+                    row_data = [re.sub(r'\n+', ' | ', (
+                        cell.get_text().strip().replace('\t', '').replace('  ', ''))) for cell in
+                                row.find_all(['td', 'th'])]
+                    OeN.append(' | '.join(row_data))
+                data.append(' <> '.join(OeN))
+            else:
+                data.append('None')
+
+            analog = []
+            table = soup.find('div', id='pcard-analog')
+            if table:
+                for row in table.find_all('tr')[1:]:
+                    row_data = [re.sub(r'\n+', ' | ', (
+                        cell.get_text().strip().replace('\t', '').replace('  ', ''))) for cell in
+                                row.find_all(['td', 'th'])]
+                    analog.append(' | '.join(row_data))
+                data.append(' <> '.join(analog))
+            else:
+                data.append('None')
+            writer.writerow(data)
+        except Exception as e:
+            print(e)
+            time.sleep(60)

ДОПАРСИНГ.py

@@ -0,0 +1,48 @@
+import csv
+from tqdm import tqdm
+
+def chort_text(parts):
+    if parts[0] == 'None':
+        return 'None'
+    # Создаем словарь для хранения данных
+    processed_data = {}
+
+    # Обрабатываем каждую часть
+    for part in parts:
+        # Разбиваем часть по разделителю |
+        subparts = part.split('|')
+        # Получаем производителя и номер детали
+        manufacturer = subparts[0].strip()
+        number = subparts[1].strip()
+        # Получаем дополнительную информацию
+        info = subparts[2].strip() if len(subparts) > 2 else ''
+        # Добавляем данные в словарь
+        if manufacturer in processed_data:
+            processed_data[manufacturer].append(f"{number}")
+        else:
+            processed_data[manufacturer] = [info, number]
+    # Преобразуем словарь в требуемый формат
+    string = ''
+    for key, value in processed_data.items():
+        if value[0] == '':
+            string += f'{key} : {" | ".join(value[1:])} <> '
+        else:
+            string += f'{key} : {" | ".join(value[1:])} : {value[0]} <> '
+    return string
+
+with open('oen.csv', newline='') as csvfile:
+    reader = csv.reader(csvfile)
+    csv_data = list(reader)
+
+
+
+with open('oem2.csv', 'w', newline='', encoding='windows-1251') as csvfile:
+    writer = csv.writer(csvfile)
+
+    for datas in tqdm(csv_data[1:], desc="Processing", unit="iteration"):
+        row = datas
+        parts = datas[5].split('<>')
+        row[5] = chort_text(parts)
+        parts = datas[6].split('<>')
+        row[6] = chort_text(parts)
+        writer.writerow(row)