Created
September 28, 2017 04:25
-
-
Save faisalburhanudin/62ba352e24db7e16816070f4572c3c9c to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| from typing import List | |
| import lxml.html | |
| import requests | |
| from flask import Flask, request, jsonify | |
| app = Flask(__name__) | |
| @app.route("/detail") | |
| def get_url(): | |
| url = request.args.get("url") | |
| session = requests.Session() | |
| detail_page = session.get(url) | |
| detail_tree = lxml.html.fromstring(detail_page.content) | |
| title = detail_tree.xpath("//h1[@class='product-name']/text()") | |
| title = str(title[0]) if title else "" | |
| rate = detail_tree.xpath("//span[@class='percent-num']/text()") | |
| rate = float(rate[0]) if rate else 0 | |
| orders = detail_tree.xpath("//span[@class='order-num']/text()") | |
| orders = int(str(orders[0]).replace(" orders", "")) if orders else "" | |
| price = detail_tree.xpath("//span[@itemprop='price']/text()") | |
| price = float(price[0]) if price else 0 | |
| low_price = detail_tree.xpath("//span[@itemprop='lowPrice']/text()") | |
| low_price = float(low_price[0]) if low_price else 0 | |
| high_price = detail_tree.xpath("//span[@itemprop='highPrice']/text()") | |
| high_price = float(high_price[0]) if high_price else 0 | |
| feedback_url = detail_tree.xpath("//div[@class='ui-tab-pane']/iframe/@thesrc") | |
| feedback_url = "https:" + str(feedback_url[0]) if feedback_url else "" | |
| feeds = feedback(session, feedback_url) if feedback_url else [] | |
| response = { | |
| "title": title, | |
| "rate": rate, | |
| "orders": orders, | |
| "price": price, | |
| "low_price": low_price, | |
| "high_price": high_price, | |
| "feedback": feeds | |
| } | |
| return jsonify(response) | |
| def feedback(session, iframe_src: str) -> List: | |
| feed_page1 = session.get(iframe_src) | |
| feed_page1_tree = lxml.html.fromstring(feed_page1.content) | |
| page = map(lambda x: int(x), feed_page1_tree.xpath("//a[@class='ui-goto-page']/@pageno")) | |
| urls = [] | |
| for i in page: | |
| u = iframe_src + "&page=%i" | |
| urls.append(u % i) | |
| feeds = [] | |
| for u in urls: | |
| feedback_page = requests.get(u) | |
| feedback_tree = lxml.html.fromstring(feedback_page.content) | |
| items = feedback_tree.xpath("//div[@class='feedback-item clearfix']") | |
| for item in items: | |
| text = item.xpath("div/div/dl/dt/span/text()") | |
| feeds.append({ | |
| "rate": str(item.xpath("div/div/span/span/@style")[0]).replace("width:", "").replace("%", ""), | |
| "text": str(text[0]) if text else "", | |
| "create_on": str(item.xpath("div/div/dl/dd[@class='r-time']/text()")[0]) | |
| }) | |
| return feeds | |
| app.run() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment