Python-сообщество

data['Product Composition'] = '93% Polyamide 7% Elastane Lining: 100% Polyester</p><p>Dress Length: 90 cm'
    data['Product Attributes;'] = ': Boat Neck, Long Sleeve, Midi, Zip, Concealed, Laced, Side Lining Type: Full Lining'

import lxml.html
import requests
import pprint
def get_doc(url):
    try:
        req = requests.get(url)
    except requests.exceptions.ConnectionError as exc:
        print('A Connection error occurred. ', exc)
    else:
        doc_html = req.text
        doc_obj = lxml.html.document_fromstring(doc_html)        
        return doc_html, doc_obj
req = get_doc('http://en.modagram.com/women/open-back-velvet-dress-claret/detail/37803/168598')
doc_html, doc_obj = req
        
details = {}
base_details_query = doc_obj.xpath('//section[@id="ProductInfo"]/div[contains(concat(" ", normalize-space(@class), " "), " TabItem ")]')
if len(base_details_query):
    base_details_query = base_details_query[0].xpath('//p/strong')
    if len(base_details_query):
         for dict_title in base_details_query:
            p = dict_title.getparent()
            print(dict_title, dict_title.text, p, p.text, '-----')
            desc = []
            while p is not None and not p.xpath('.//strong'):
                desc.append(p.text)
                p = p.getnext()
            details[dict_title.text] = " ".join(desc)
    pprint.pprint(details)