chrono24Scraper/WatchOffer.py at main · CodeOfRob/chrono24Scraper · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
from datetime import datetime

import bs4
from requests_html import HTMLSession


class WatchOffer:

    def __init__(self, url: str, title: str, price: int, currency: str):
        self.timestamp = datetime.now()
        self.url = url
        self.title = title
        self.currency = currency
        self.price = price

        self.condition = None
        self.productionyear = None
        self.has_original_box = None
        self.has_original_papers = None
        self.location = None
        self.description = None

        self.fetch_details()

    def fetch_details(self):
        print("fetching:", self.url)
        session = HTMLSession()
        doc = session.get(self.url)
        doc.html.render(timeout=60)

        page_content = bs4.BeautifulSoup(doc.html.raw_html, "lxml")
        # print(page_content)
        main_section = page_content.find("main")
        specs_section = main_section.find("section", {"id":"jq-specifications"})

        tables = specs_section.find_all("table")

        specs = tables[0]
        desc = tables[1]

        spec_rows = specs.find_all("tr")
        for row in spec_rows:
            if "Zustand" in row.text:
                cols = row.find_all("td")
                self.condition = cols[1].find("a").text.strip()

            elif "Lieferumfang" in row.text:
                cols = row.find_all("td")
                content = cols[1].text.strip().lower()
                elements = content.split(",")

                for element in elements:
                    cond = True if "mit" in element else False

                    if "original-box" in element:
                        self.has_original_box = cond
                    elif "original-papiere" in element:
                        self.has_original_papers = cond
                    else:
                        print("error while parsing box and papers")

            elif "Herstellungsjahr" in row.text:
                cols = row.find_all("td")
                self.productionyear = cols[1].text.strip()

            elif "Standort" in row.text:
                cols = row.find_all("td")
                self.location = cols[1].text.strip()


        desc_rows = desc.find_all("tr")
        if len(desc_rows)>=2:
            self.description = desc_rows[1].text.strip()