1
0
mirror of https://github.com/mikf/gallery-dl.git synced 2024-11-22 18:53:21 +01:00

[shopify] use BaseExtractor

This commit is contained in:
Mike Fährmann 2021-01-27 23:43:14 +01:00
parent 2de8ebc098
commit 231bcad614
No known key found for this signature in database
GPG Key ID: 5680CA389D365A88

View File

@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2019-2020 Mike Fährmann
# Copyright 2019-2021 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
@ -8,28 +8,23 @@
"""Extractors for Shopify instances"""
from .common import Extractor, Message, generate_extractors
from .common import BaseExtractor, Message
from .. import text
import re
class ShopifyExtractor(Extractor):
class ShopifyExtractor(BaseExtractor):
"""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)
BaseExtractor.__init__(self, match)
self.item_url = self.root + match.group(match.lastindex)
def items(self):
data = self.metadata()
yield Message.Version, 1
yield Message.Directory, data
headers = {"X-Requested-With": "XMLHttpRequest"}
@ -58,22 +53,34 @@ class ShopifyExtractor(Extractor):
"""Return an iterable with all relevant product URLs"""
BASE_PATTERN = ShopifyExtractor.update({
"fashionnova": {
"root": "https://www.fashionnova.com",
"pattern": r"(?:www\.)?fashionnova\.com",
},
})
class ShopifyCollectionExtractor(ShopifyExtractor):
"""Base class for collection extractors for Shopify based sites"""
subcategory = "collection"
directory_fmt = ("{category}", "{collection[title]}")
pattern_fmt = r"(/collections/[\w-]+)/?(?:\?([^#]+))?(?:$|#)"
def __init__(self, match):
ShopifyExtractor.__init__(self, match)
self.params = match.group(2)
pattern = BASE_PATTERN + r"(/collections/[\w-]+)/?(?:$|[?#])"
test = (
("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"),
)
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)
params = {"page": 1}
fetch = True
last = None
@ -107,36 +114,14 @@ 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-]+)"
pattern = BASE_PATTERN + r"((?:/collections/[\w-]+)?/products/[\w-]+)"
test = (
("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"),
)
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,
))