Невозможно очистить Myntra - PullRequest
Новая
       164

Невозможно очистить Myntra

3 голосов
/ 06 августа 2020

Я пытаюсь очистить Myntra, но получаю ошибки. Я сделал много изменений в коде. Я пробовал пакет запросов, а также urllib, но все равно получаю ошибку.

Иногда я получал ошибку тайм-аута или urllib.error.URLError: 

urllib.error.URLError: <urlopen error Tunnel connection failed: 502 Proxy Error (no funds available)>

Вот мой код. 

import os, ssl, http, gzip
import urllib.request
from bs4 import BeautifulSoup
import re
from http.cookiejar import CookieJar
import json
import  http
import requests

def myntraScraper(url):
    if (not os.environ.get('PYTHONHTTPSVERIFY', '') and getattr(ssl, '_create_unverified_context', None)):
        ssl._create_default_https_context = ssl._create_unverified_context
    cj = CookieJar()

    proxy = {
        'https': '------',
        'http': '-------'
    }
    # user_agent = 'Mozilla/5.0 (Windows NT 6.1; Win64; x64)'

    try:
        import urllib.request as urllib2
    except ImportError:
        import urllib2

    urllib2.install_opener(
        urllib2.build_opener(
            urllib2.ProxyHandler(proxy),
            urllib.request.HTTPCookieProcessor(cj)
        )
    )

    request = urllib2.Request(url, headers={
        'accept-encoding': 'gzip',
        'User-Agent':  'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36',

    })

    page = urllib2.urlopen(request)

    html = gzip.decompress(page.read()).decode('utf-8')

    soup = BeautifulSoup(html, 'lxml')

    print(soup)

myntraScraper("https://www.myntra.com/sports-shoes/puma/puma-men-blue-hybrid-fuego-running-shoes/11203218/buy")

В настоящее время я использую Smartproxy. Но я попробовал то же самое с PacketStream и Luminati. В большинстве случаев я получал ошибку прокси.

1 Ответ

2 голосов
/ 06 августа 2020

Myntra сохраняет все данные о продукте в переменной скрипта с именем pdpData.

Приведенный ниже скрипт получает все json, содержащие все данные о продукте. 

import requests, json
from bs4 import BeautifulSoup

headers = {'User-Agent' : 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.89 Safari/537.36'}

s = requests.Session()
res = s.get("https://www.myntra.com/sports-shoes/puma/puma-men-blue-hybrid-fuego-running-shoes/11203218/buy", headers=headers, verify=False)

soup = BeautifulSoup(res.text,"lxml")

script = None
for s in soup.find_all("script"):
    if 'pdpData' in s.text:
        script = s.get_text(strip=True)
        break

print(json.loads(script[script.index('{'):]))

Вывод: 

{'pdpData': {'id': 11203218, 'name': 'Puma Men Blue Hybrid Fuego Running Shoes', 'mrp': 6499, 'manufacturer': 'SSIPL RETAIL LIMITED, KUNDLI,75, SERSA ROAD, 131028 SONEPAT', 'countryOfOrigin': 'India', 'colours': None, 'baseColour': 'Blue', 'brand': {'uidx': '', 'name': 'Puma', 'image': '', 'bio': ''}, 'media': {'videos': [], 'albums': [{'name': 'default', 'images': [{'src': 'http://assets.myntassets.com/h_($height),q_($qualityPercentage),w_($width)/v1/assets/images/productimage/2019/12/20/0c15e03c-863b-4a4a-9bb7-709a733fd4821576816965952-1.jpg', 'secureSrc': 'https://assets.myntassets.com/h_($height),q_($qualityPercentage),w_($width)/v1/assets/images/productimage/2019/12/20/0c15e03c-863b-4a4a-9bb7-709a733fd4821576816965952-1.jpg', 'host': None, 'imageURL': 'http://assets.myntassets.com/assets/images/productimage/2019/12/20/0c15e03c-863b-4a4a-9bb7-709a733fd4821576816965952-1.jpg', 'annotation': []}, {'src': 'http://assets.myntassets.com/h_($height),q_($qualityPercentage),w_($width)/v1/assets/images/productimage/2019/12/20/69bfa4e0-1ac4-4adf-b84e-4815ff60e8831576816966007-2.jpg', 'secureSrc': 'https://assets.myntassets.com/h_($height),q_($qualityPercentage),w_($width)/v1/assets/images/productimage/2019/12/20/69bfa4e0-1ac4-4adf-b84e-4815ff60e8831576816966007-2.jpg', 'host': None, 'imageURL': 'http://assets.myntassets.com/assets/images/productimage/2019/12/20/69bfa4e0-1ac4-4adf-b84e-4815ff60e8831576816966007-2.jpg', 'annotation': []}, {'src': 'http://assets.myntassets.com/h_($height),q_($qualityPercentage),w_($width)/v1/assets/images/productimage/2019/12/20/d2fd0ca0-1643-43ae-a0fc-fb1309580e151576816966049-3.jpg', 'secureSrc': 'https://assets.myntassets.com/h_($height),q_($qualityPercentage),w_($width)/v1/assets/images/productimage/2019/12/20/d2fd0ca0-1643-43ae-a0fc-fb1309580e151576816966049-3.jpg', 'host': None, 'imageURL': 'http://assets.myntassets.com/assets/images/productimage/2019/12/20/d2fd0ca0-1643-43ae-a0fc-fb1309580e151576816966049-3.jpg', 'annotation': []}, {'src': 'http://assets.myntassets.com/h_($height),q_($qualityPercentage),w_($width)/v1/assets/images/productimage/2019/12/20/0edae428-b9c0-4755-9127-0961d872b78a1576816966095-4.jpg', 'secureSrc': 'https://assets.myntassets.com/h_($height),q_($qualityPercentage),w_($width)/v1/assets/images/productimage/2019/12/20/0edae428-b9c0-4755-9127-0961d872b78a1576816966095-4.jpg', 'host': None, 'imageURL': 'http://assets.myntassets.com/assets/images/productimage/2019/12/20/0edae428-b9c0-4755-9127-0961d872b78a1576816966095-4.jpg', 'annotation': []}, {'src': 'http://assets.myntassets.com/h_($height),q_($qualityPercentage),w_($width)/v1/assets/images/productimage/2019/12/20/c59c7677-2bbd-4dbe-9b02-7c321c29cb701576816966142-5.jpg', 'secureSrc': 'https://assets.myntassets.com/h_($height),q_($qualityPercentage),w_($width)/v1/assets/images/productimage/2019/12/20/c59c7677-2bbd-4dbe-9b02-7c321c29cb701576816966142-5.jpg', 'host': None, 'imageURL': 'http://assets.myntassets.com/assets/images/productimage/2019/12/20/c59c7677-2bbd-4dbe-9b02-7c321c29cb701576816966142-5.jpg', 'annotation': []}]}, {'name': 'animatedImage', 'images': []}]}, 'sbpEnabled': False, 'sizechart': {'sizeChartUrl': None, 'sizeRepresentationUrl': 'http://assets.myntassets.com/assets/images/sizechart/2016/12/12/11481538267795-footwear.png'}, 'sizeRecoLazy': {'actionType': 'lazy', 'action': '/product/11203218/size/recommendation', 'sizeProfileAction': '/user/size-profiles?gender=male&articleType=Sports%20Shoes'}, 'analytics': {'articleType': 'Sports Shoes', 'subCategory': 'Shoes', 'masterCategory': 'Footwear', 'gender': 'Men', 'brand': 'Puma', 'colourHexCode': None}, 'crossLinks': [{'title': 'More Sports Shoes by Puma', 'url': 'sports-shoes?f=Brand:Puma::Gender:men'}, {'title': 'More Blue Sports Shoes', 'url': 'sports-shoes?f=Color:Blue_0074D9::Gender:men'}, {'title': 'More Sports Shoes', 'url': 'sports-shoes?f=Gender:men'}], 'relatedStyles': None, 'disclaimerTitle': '', 'productDetails': [{'type': None, 'content': None, 'title': 'Product Details', 'description': "<b>FEATURES + BENEFITS</b><br>HYBRID: PUMA's combination of two of its best technologies: IGNITE foam and NRGY beads<br>IGNITE: PUMA's foam midsole and branded heel cage supports and stabilises by locking the heel onto the platform<br>NRGY: PUMA's foam midsole offers superior cushion from heel to toe so you can power through your run<br>Heel-to-toe drop: 12mm<br><br><b>Product Design Details</b><ul><li>A pair of blue &amp; brown running sports shoes, has regular styling, lace-up detail</li><li>Low boot silhouette</li><li>Lightweight synthetic upper</li><li>Overlays to secure the heel</li><li>Classic tongue</li><li>Lace-up closure</li><li>Rubber outsole for traction and durability</li><li>PUMA Wordmark at the tongue</li><li>PUMA Cat Logo at heel</li><li>Warranty: 3 months</li><li>Warranty provided by brand/manufacturer</li></ul><br><b>PRODUCT STORY</b><br>Change the name of the game with the HYBRID Fuego running sneakers. This bold colour-blocked shoe pairs a HYBRID foam midsole and a grippy rubber outsole for the ultimate in comfort and stability while still maintaining a stylish edge."}, {'type': None, 'content': None, 'title': 'MATERIAL & CARE', 'description': 'Textile<br>Wipe with a clean, dry cloth to remove dust'}], 'preOrder': None, 'sizeChartDisclaimerText': '', 'tags': None, 'articleAttributes': {'Ankle Height': 'Regular', 'Arch Type': 'Medium', 'Cleats': 'No Cleats', 'Cushioning': 'Medium', 'Distance': 'Medium', 'Fastening': 'Lace-Ups', 'Material': 'Textile', 'Outsole Type': 'Marking', 'Pronation for Running Shoes': 'Neutral', 'Running Type': 'Road Running', 'Sole Material': 'Rubber', 'Sport': 'Running', 'Surface Type': 'Outdoor', 'Technology': 'NA', 'Warranty': '3 months'}, 'systemAttributes': [], 'ratings': None, 'urgency': [{'value': '0', 'type': 'PURCHASED', 'ptile': 0}, {'value': '0', 'type': 'CART', 'ptile': 0}, {'value': '0', 'type': 'WISHLIST', 'ptile': 0}, {'value': '0', 'type': 'PDP', 'ptile': 0}], 'catalogAttributes': {'catalogDate': '1576751286000', 'season': 'summer', 'year': '2020'}, 'productContentGroupEntries': [{'title': '', 'type': 'DETAILS', 'attributes': [{'attributeName': 'Product Details', 'attributeType': 'STRING', 'value': "<b>FEATURES + BENEFITS</b><br>HYBRID: PUMA's combination of two of its best technologies: IGNITE foam and NRGY beads<br>IGNITE: PUMA's foam midsole and branded heel cage supports and stabilises by locking the heel onto the platform<br>NRGY: PUMA's foam midsole offers superior cushion from heel to toe so you can power through your run<br>Heel-to-toe drop: 12mm<br><br><b>Product Design Details</b><ul><li>A pair of blue &amp; brown running sports shoes, has regular styling, lace-up detail</li><li>Low boot silhouette</li><li>Lightweight synthetic upper</li><li>Overlays to secure the heel</li><li>Classic tongue</li><li>Lace-up closure</li><li>Rubber outsole for traction and durability</li><li>PUMA Wordmark at the tongue</li><li>PUMA Cat Logo at heel</li><li>Warranty: 3 months</li><li>Warranty provided by brand/manufacturer</li></ul><br><b>PRODUCT STORY</b><br>Change the name of the game with the HYBRID Fuego running sneakers. This bold colour-blocked shoe pairs a HYBRID foam midsole and a grippy rubber outsole for the ultimate in comfort and stability while still maintaining a stylish edge."}, {'attributeName': 'Material & Care', 'attributeType': 'STRING', 'value': 'Textile<br>Wipe with a clean, dry cloth to remove dust'}, {'attributeName': 'Style Note', 'attributeType': 'STRING', 'value': "You'll look and feel super stylish in these trendsetting sports shoes by Puma.  Match this blue pair with track pants and a sleeveless sports T-shirt when heading out for a casual day with friends."}]}], 'shoppableLooks': None, 'descriptors': [{'title': 'description', 'description': "<b>FEATURES + BENEFITS</b><br>HYBRID: PUMA's combination of two of its best technologies: IGNITE foam and NRGY beads<br>IGNITE: PUMA's foam midsole and branded heel cage supports and stabilises by locking the heel onto the platform<br>NRGY: PUMA's foam midsole offers superior cushion from heel to toe so you can power through your run<br>Heel-to-toe drop: 12mm<br><br><b>Product Design Details</b><ul><li>A pair of blue &amp; brown running sports shoes, has regular styling, lace-up detail</li><li>Low boot silhouette</li><li>Lightweight synthetic upper</li><li>Overlays to secure the heel</li><li>Classic tongue</li><li>Lace-up closure</li><li>Rubber outsole for traction and durability</li><li>PUMA Wordmark at the tongue</li><li>PUMA Cat Logo at heel</li><li>Warranty: 3 months</li><li>Warranty provided by brand/manufacturer</li></ul><br><b>PRODUCT STORY</b><br>Change the name of the game with the HYBRID Fuego running sneakers. This bold colour-blocked shoe pairs a HYBRID foam midsole and a grippy rubber outsole for the ultimate in comfort and stability while still maintaining a stylish edge."}, {'title': 'style_note', 'description': "You'll look and feel super stylish in these trendsetting sports shoes by Puma.  Match this blue pair with track pants and a sleeveless sports T-shirt when heading out for a casual day with friends."}, {'title': 'materials_care_desc', 'description': 'Textile<br>Wipe with a clean, dry cloth to remove dust'}], 'flags': {'isExchangeable': True, 'isReturnable': True, 'openBoxPickupEnabled': True, 'tryAndBuyEnabled': True, 'isLarge': False, 'isHazmat': False, 'isFragile': False, 'isJewellery': False, 'outOfStock': False, 'codEnabled': True, 'globalStore': False, 'loyaltyPointsEnabled': False, 'emiEnabled': True, 'chatEnabled': False, 'measurementModeEnabled': False, 'sampleModeEnabled': False, 'disableBuyButton': False}, 'earlyBirdOffer': None, 'serviceability': {'launchDate': '', 'returnPeriod': 30, 'descriptors': ['Pay on delivery might be available', 'Easy 30 days returns and exchanges', 'Try & Buy might be available'], 'procurementTimeInDays': {'6206': 4}}, 'buyButtonSellerOrder': [{'skuId': 38724440, 'sellerPartnerId': 6206}, {'skuId': 38724442, 'sellerPartnerId': 6206}, {'skuId': 38724446, 'sellerPartnerId': 6206}, {'skuId': 38724450, 'sellerPartnerId': 6206}, {'skuId': 38724452, 'sellerPartnerId': 6206}, {'skuId': 38724444, 'sellerPartnerId': 6206}, {'skuId': 38724448, 'sellerPartnerId': 6206}], 'sellers': [{'sellerPartnerId': 6206, 'sellerName': 'Puma Sports India Pvt. Ltd.(NSCM)'}], 'sizes': [{'skuId': 38724440, 'styleId': 11203218, 'action': '/product/11203218/related/6?co=1', 'label': '6', 'available': True, 'sizeType': 'UK Size', 'originalStyle': True, 'measurements': [{'type': 'Body Measurement', 'name': 'To Fit Foot Length', 'value': '24.5', 'minValue': '24.5', 'maxValue': '24.5', 'unit': 'cm', 'displayText': '24.5cm'}], 'allSizesList': [{'scaleCode': 'uk_size', 'sizeValue': '6', 'size': 'UK Size', 'order': 1, 'prefix': 'UK'}, {'scaleCode': 'us_size', 'sizeValue': '7', 'size': 'US Size', 'order': 2, 'prefix': 'US'}, {'scaleCode': 'euro_size', 'sizeValue': '39', 'size': 'Euro Size', 'order': 3, 'prefix': 'EURO'}], 'sizeSellerData': [{'mrp': 6499, 'sellerPartnerId': 6206, 'availableCount': 32, 'sellableInventoryCount': 32, 'warehouses': ['106', '328'], 'supplyType': 'ON_HAND', 'discountId': '11203218:23363948', 'discountedPrice': 2924}]}, {'skuId': 38724442, 'styleId': 11203218, 'action': '/product/11203218/related/7?co=1', 'label': '7', 'available': True, 'sizeType': 'UK Size', 'originalStyle': True, 'measurements': [{'type': 'Body Measurement', 'name': 'To Fit Foot Length', 'value': '25.4', 'minValue': '25.4', 'maxValue': '25.4', 'unit': 'cm', 'displayText': '25.4cm'}], 'allSizesList': [{'scaleCode': 'uk_size', 'sizeValue': '7', 'size': 'UK Size', 'order': 1, 'prefix': 'UK'}, {'scaleCode': 'us_size', 'sizeValue': '8', 'size': 'US Size', 'order': 2, 'prefix': 'US'}, {'scaleCode': 'euro_size', 'sizeValue': '40.5', 'size': 'Euro Size', 'order': 3, 'prefix': 'EURO'}], 'sizeSellerData': [{'mrp': 6499, 'sellerPartnerId': 6206, 'availableCount': 86, 'sellableInventoryCount': 86, 'warehouses': ['106'], 'supplyType': 'ON_HAND', 'discountId': '11203218:23363948', 'discountedPrice': 2924}]}, {'skuId': 38724444, 'styleId': 11203218, 'action': '/product/11203218/related/8?co=1', 'label': '8', 'available': True, 'sizeType': 'UK Size', 'originalStyle': True, 'measurements': [{'type': 'Body Measurement', 'name': 'To Fit Foot Length', 'value': '26.2', 'minValue': '26.2', 'maxValue': '26.2', 'unit': 'cm', 'displayText': '26.2cm'}], 'allSizesList': [{'scaleCode': 'uk_size', 'sizeValue': '8', 'size': 'UK Size', 'order': 1, 'prefix': 'UK'}, {'scaleCode': 'us_size', 'sizeValue': '9', 'size': 'US Size', 'order': 2, 'prefix': 'US'}, {'scaleCode': 'euro_size', 'sizeValue': '42', 'size': 'Euro Size', 'order': 3, 'prefix': 'EURO'}], 'sizeSellerData': [{'mrp': 6499, 'sellerPartnerId': 6206, 'availableCount': 188, 'sellableInventoryCount': 188, 'warehouses': ['106'], 'supplyType': 'ON_HAND', 'discountId': '11203218:23363948', 'discountedPrice': 2924}]}, {'skuId': 38724446, 'styleId': 11203218, 'action': '/product/11203218/related/9?co=1', 'label': '9', 'available': True, 'sizeType': 'UK Size', 'originalStyle': True, 'measurements': [{'type': 'Body Measurement', 'name': 'To Fit Foot Length', 'value': '27.1', 'minValue': '27.1', 'maxValue': '27.1', 'unit': 'cm', 'displayText': '27.1cm'}], 'allSizesList': [{'scaleCode': 'uk_size', 'sizeValue': '9', 'size': 'UK Size', 'order': 1, 'prefix': 'UK'}, {'scaleCode': 'us_size', 'sizeValue': '10', 'size': 'US Size', 'order': 2, 'prefix': 'US'}, {'scaleCode': 'euro_size', 'sizeValue': '43', 'size': 'Euro Size', 'order': 3, 'prefix': 'EURO'}], 'sizeSellerData': [{'mrp': 6499, 'sellerPartnerId': 6206, 'availableCount': 163, 'sellableInventoryCount': 163, 'warehouses': ['106'], 'supplyType': 'ON_HAND', 'discountId': '11203218:23363948', 'discountedPrice': 2924}]}, {'skuId': 38724448, 'styleId': 11203218, 'action': '/product/11203218/related/10?co=1', 'label': '10', 'available': True, 'sizeType': 'UK Size', 'originalStyle': True, 'measurements': [{'type': 'Body Measurement', 'name': 'To Fit Foot Length', 'value': '27.9', 'minValue': '27.9', 'maxValue': '27.9', 'unit': 'cm', 'displayText': '27.9cm'}], 'allSizesList': [{'scaleCode': 'uk_size', 'sizeValue': '10', 'size': 'UK Size', 'order': 1, 'prefix': 'UK'}, {'scaleCode': 'us_size', 'sizeValue': '11', 'size': 'US Size', 'order': 2, 'prefix': 'US'}, {'scaleCode': 'euro_size', 'sizeValue': '44.5', 'size': 'Euro Size', 'order': 3, 'prefix': 'EURO'}], 'sizeSellerData': [{'mrp': 6499, 'sellerPartnerId': 6206, 'availableCount': 153, 'sellableInventoryCount': 153, 'warehouses': ['106'], 'supplyType': 'ON_HAND', 'discountId': '11203218:23363948', 'discountedPrice': 2924}]}, {'skuId': 38724450, 'styleId': 11203218, 'action': '/product/11203218/related/11?co=1', 'label': '11', 'available': True, 'sizeType': 'UK Size', 'originalStyle': True, 'measurements': [{'type': 'Body Measurement', 'name': 'To Fit Foot Length', 'value': '28.8', 'minValue': '28.8', 'maxValue': '28.8', 'unit': 'cm', 'displayText': '28.8cm'}], 'allSizesList': [{'scaleCode': 'uk_size', 'sizeValue': '11', 'size': 'UK Size', 'order': 1, 'prefix': 'UK'}, {'scaleCode': 'us_size', 'sizeValue': '12', 'size': 'US Size', 'order': 2, 'prefix': 'US'}, {'scaleCode': 'euro_size', 'sizeValue': '46', 'size': 'Euro Size', 'order': 3, 'prefix': 'EURO'}], 'sizeSellerData': [{'mrp': 6499, 'sellerPartnerId': 6206, 'availableCount': 43, 'sellableInventoryCount': 43, 'warehouses': ['106'], 'supplyType': 'ON_HAND', 'discountId': '11203218:23363948', 'discountedPrice': 2924}]}, {'skuId': 38724452, 'styleId': 11203218, 'action': '/product/11203218/related/12?co=1', 'label': '12', 'available': False, 'sizeType': 'UK Size', 'originalStyle': True, 'measurements': [{'type': 'Body Measurement', 'name': 'To Fit Foot Length', 'value': '29.6', 'minValue': '29.6', 'maxValue': '29.6', 'unit': 'cm', 'displayText': '29.6cm'}], 'allSizesList': [{'scaleCode': 'uk_size', 'sizeValue': '12', 'size': 'UK Size', 'order': 1, 'prefix': 'UK'}, {'scaleCode': 'us_size', 'sizeValue': '13', 'size': 'US Size', 'order': 2, 'prefix': 'US'}, {'scaleCode': 'euro_size', 'sizeValue': '47', 'size': 'Euro Size', 'order': 3, 'prefix': 'EURO'}], 'sizeSellerData': []}], 'discounts': [{'type': 1, 'freeItem': False, 'label': '(55% OFF)', 'discountText': '', 'timerStart': '0', 'timerEnd': '1597084200', 'discountPercent': 55, 'offer': '', 'discountId': '11203218:23363948', 'heading': None, 'description': None, 'link': None, 'freeItemImage': None}], 'offers': [{'type': 'EMI', 'title': 'EMI option available', 'description': '', 'action': '/faqs', 'image': None}], 'bundledSkus': None, 'richPdp': None, 'landingPageUrl': 'sports-shoes/puma/puma-men-blue-hybrid-fuego-running-shoes/11203218/buy'}, 'pageName': 'Pdp', 'atsa': ['Sport', 'Material', 'Fastening', 'Ankle Height', 'Outsole Type', 'Cleats', 'Pronation for Running Shoes', 'Arch Type', 'Cushioning', 'Running Type', 'Warranty', 'Distance', 'Number of Components', 'Surface Type', 'Technology']}
...