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
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
|
# -*- coding: utf-8 -*-
# Copyright 2019-2020 Mike Fährmann
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License version 2 as
# published by the Free Software Foundation.
"""Extractors for Shopify instances"""
from .common import Extractor, Message, generate_extractors
from .. import text
import re
class ShopifyExtractor(Extractor):
"""Base class for Shopify extractors"""
basecategory = "shopify"
filename_fmt = "{product[title]}_{num:>02}_{id}.{extension}"
archive_fmt = "{id}"
def __init__(self, match):
Extractor.__init__(self, match)
self.item_url = self.root + match.group(1)
def request(self, url, **kwargs):
kwargs["retries"] = float("inf")
return Extractor.request(self, url, **kwargs)
def items(self):
data = self.metadata()
yield Message.Version, 1
yield Message.Directory, data
headers = {"X-Requested-With": "XMLHttpRequest"}
for url in self.products():
response = self.request(
url + ".json", headers=headers, fatal=False)
if response.status_code >= 400:
self.log.warning('Skipping %s ("%s: %s")',
url, response.status_code, response.reason)
continue
product = response.json()["product"]
del product["image"]
for num, image in enumerate(product.pop("images"), 1):
text.nameext_from_url(image["src"], image)
image.update(data)
image["product"] = product
image["num"] = num
yield Message.Url, image["src"], image
def metadata(self):
"""Return general metadata"""
return {}
def products(self):
"""Return an iterable with all relevant product URLs"""
class ShopifyCollectionExtractor(ShopifyExtractor):
"""Base class for collection extractors for Shopify based sites"""
subcategory = "collection"
directory_fmt = ("{category}", "{collection[title]}")
pattern_fmt = r"(/collections/[\w-]+)/?(?:\?([^#]+))?(?:$|#)"
def __init__(self, match):
ShopifyExtractor.__init__(self, match)
self.params = match.group(2)
def metadata(self):
return self.request(self.item_url + ".json").json()
def products(self):
params = text.parse_query(self.params)
params["page"] = text.parse_int(params.get("page"), 1)
fetch = True
last = None
for pattern in (
r"/collections/[\w-]+/products/[\w-]+",
r"href=[\"'](/products/[\w-]+)",
):
search_re = re.compile(pattern)
while True:
if fetch:
page = self.request(self.item_url, params=params).text
urls = search_re.findall(page)
if len(urls) < 3:
if last:
return
fetch = False
break
fetch = True
for path in urls:
if last == path:
continue
last = path
yield self.root + path
params["page"] += 1
class ShopifyProductExtractor(ShopifyExtractor):
"""Base class for product extractors for Shopify based sites"""
subcategory = "product"
directory_fmt = ("{category}", "Products")
pattern_fmt = r"((?:/collections/[\w-]+)?/products/[\w-]+)"
def products(self):
return (self.item_url,)
EXTRACTORS = {
"fashionnova": {
"root": "https://www.fashionnova.com",
"pattern": r"(?:www\.)?fashionnova\.com",
"test-product": (
("https://www.fashionnova.com/products/essential-slide-red", {
"pattern": r"https?://cdn\d*\.shopify.com/",
"count": 3,
}),
("https://www.fashionnova.com/collections/flats/products/name"),
),
"test-collection": (
("https://www.fashionnova.com/collections/mini-dresses", {
"range": "1-20",
"count": 20,
"archive": False,
}),
("https://www.fashionnova.com/collections/mini-dresses/?page=1"),
("https://www.fashionnova.com/collections/mini-dresses#1"),
),
},
}
generate_extractors(EXTRACTORS, globals(), (
ShopifyProductExtractor,
ShopifyCollectionExtractor,
))
|
