scry/main.py at master · konserw/scry · 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
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
import csv
import re
import time
from pathlib import Path

import requests
from bs4 import BeautifulSoup
from pathos.multiprocessing import ProcessPool


class Collection:
    def __init__(self, collection_id, name):
        self.collection_id = collection_id
        self.name = name
        self._search_url = f"https://mtgcollectionbuilder.com/collections/{collection_id}/search"
        self.found = []

    def search_card(self, card):
        strings = []
        page = requests.post(self._search_url, data={"cardNameSearch": card})
        soup = BeautifulSoup(page.content, 'html.parser')
        # return soup.select('tr.success')
        for r in soup.select('tr.success'):
            tds = r.select("td")
            name = tds[0].text.strip()
            img_url = r.td.a["data-img"]
            row = f'<tr><td><a class="thumbnail" href="{tds[0].a["href"]}" target="_blank" rel="noopener noreferrer">{name}<span><img src="{img_url}" /></span></a></td>{tds[1]}{tds[2]}{tds[3]}{tds[4]}</tr>'
            strings.append(row)
        return strings

    def search_card_list(self, search_list):
        print(f"Searching in {self.name}:", end="")
        #        self.found += self.search_card(search_list[0])
        #        return
        pool = ProcessPool(nodes=16)
        results = pool.amap(self.search_card, search_list)
        while not results.ready():
            time.sleep(0.5)
            print(".", end='')

        for r in results.get():
            self.found += r
        print(" Done!")

    def get_html(self):
        ret = f"""
<h1><a href="https://mtgcollectionbuilder.com/collections/{self.collection_id}">{self.name} collection</a></h1>
<table class="styled-table">
    <thead>
    <tr>
        <th class="header">Name</th>
        <th class="header">Qt.</th>
        <th class="header">Foil Qt.</th>
        <th class="header">Set</th>
        <th class="header">Low $</th>
    </tr>
    </thead>
    <tbody>
    {'\n'.join(self.found)}
    </tbody>
</table>
        """
        return ret


def process_file(path):
    out = set()
    regex = re.compile(r"(?:\d+ )?([^(]*)(?:\(.*\))?(?: .*)?")
    lines = path.read_text().splitlines()
    for line in lines:
        if not line or line[0] == "#":
            continue
        match = regex.match(line)
        if match:
            out.add(match.group(1).strip())
    return out


def save_report(collections, report_name="report.html"):
    print(f"\nSaving report to {report_name}")
    html_report = """
<html>
<head>
<link rel="stylesheet" href="thumbs.css">
<link rel="stylesheet" href="table.css">
</head>
<body>
"""
    for collection in collections:
        html_report += collection.get_html()
    html_report += "\n</body></html>"

    (Path.cwd() / report_name).write_text(html_report)


def main(report_name="report.html", single_list=None, single_collection=None):
    search_list = set()
    if single_list:
        search_list = process_file(Path.cwd() / single_list)
    else:
        for path in Path.cwd().glob("*.txt"):
            print(f"reading from {path}")
            search_list.update(process_file(path))

    collections = []
    if single_collection:
        collections.append(single_collection)
    else:
        friends_path = Path.cwd() / "friends.csv"
        friends_list = friends_path.read_text().splitlines()
        reader = csv.reader(friends_list[1:], delimiter=',')
        for row in reader:
            collections.append(Collection(row[1], row[0]))

    for collection in collections:
        collection.search_card_list(search_list)
    save_report(collections, report_name)


if __name__ == '__main__':
    # moje = Collection("49772", "moje")
    main("krak.html", "krak.txt")