[shopifx] natively support a few more sites (closes #2089)

- chelseacrew.com
- michaels.com.au
- modcloth.com
- pinupgirlclothing.com
- raidlondon.com (loveraid.com)
- unique-vintage.com
This commit is contained in:
Mike Fährmann
2022-05-10 15:49:36 +02:00
parent 60f4d59b1e
commit feb470d19a
2 changed files with 88 additions and 12 deletions

View File

@@ -43,22 +43,46 @@ class ShopifyExtractor(BaseExtractor):
BASE_PATTERN = ShopifyExtractor.update({
"chelseacrew": {
"root": "https://chelseacrew.com",
"pattern": r"(?:www\.)?chelseacrew\.com",
},
"fashionnova": {
"root": "https://www.fashionnova.com",
"pattern": r"(?:www\.)?fashionnova\.com",
},
"loungeunderwear": {
"root": "https://loungeunderwear.com",
"pattern": r"(?:[a-z]+\.)?loungeunderwear\.com",
},
"michaelscameras": {
"root": "https://michaels.com.au",
"pattern": r"michaels\.com\.au",
},
"modcloth": {
"root": "https://modcloth.com",
"pattern": r"modcloth\.com",
},
"omgmiamiswimwear": {
"root": "https://www.omgmiamiswimwear.com",
"pattern": r"(?:www\.)?omgmiamiswimwear\.com",
},
"pinupgirlclothing": {
"root": "https://pinupgirlclothing.com",
"pattern": r"pinupgirlclothing\.com",
},
"raidlondon": {
"root": "https://www.raidlondon.com",
"pattern": r"(?:www\.)?raidlondon\.com",
},
"unique-vintage": {
"root": "https://www.unique-vintage.com",
"pattern": r"(?:www\.)?unique\-vintage\.com",
},
"windsorstore": {
"root": "https://www.windsorstore.com",
"pattern": r"(?:www\.)?windsorstore\.com",
},
"loungeunderwear": {
"root": "https://loungeunderwear.com",
"pattern": r"(?:[a-z]+\.)?loungeunderwear\.com",
},
})
@@ -68,15 +92,21 @@ class ShopifyCollectionExtractor(ShopifyExtractor):
directory_fmt = ("{category}", "{collection[title]}")
pattern = BASE_PATTERN + r"(/collections/[\w-]+)/?(?:$|[?#])"
test = (
("https://chelseacrew.com/collections/flats"),
("https://www.fashionnova.com/collections/mini-dresses", {
"range": "1-20",
"count": 20,
}),
("https://www.fashionnova.com/collections/mini-dresses/?page=1"),
("https://www.fashionnova.com/collections/mini-dresses#1"),
("https://www.omgmiamiswimwear.com/collections/fajas"),
("https://www.windsorstore.com/collections/dresses-ball-gowns"),
("https://loungeunderwear.com/collections/apparel"),
("https://michaels.com.au/collections/microphones"),
("https://modcloth.com/collections/shoes"),
("https://www.omgmiamiswimwear.com/collections/fajas"),
("https://pinupgirlclothing.com/collections/evening"),
("https://www.raidlondon.com/collections/flats"),
("https://www.unique-vintage.com/collections/flapper-1920s"),
("https://www.windsorstore.com/collections/dresses-ball-gowns"),
)
def metadata(self):
@@ -101,18 +131,28 @@ class ShopifyProductExtractor(ShopifyExtractor):
directory_fmt = ("{category}", "Products")
pattern = BASE_PATTERN + r"((?:/collections/[\w-]+)?/products/[\w-]+)"
test = (
("https://chelseacrew.com/collections/flats/products/dora"),
("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"),
("https://de.loungeunderwear.com/products/ribbed-crop-top-black"),
("https://michaels.com.au/collections/audio/products"
"/boya-by-wm4-pro-k5-2-4ghz-mic-android-1-1-101281"),
("https://modcloth.com/collections/shoes/products/heidii-brn"),
("https://www.omgmiamiswimwear.com/products/la-medusa-maxi-dress", {
"pattern": r"https://cdn\.shopify\.com/s/files/1/1819/6171/",
"count": 5,
}),
("https://www.fashionnova.com/collections/flats/products/name"),
("https://pinupgirlclothing.com/collections/evening/products"
"/clarice-coat-dress-in-olive-green-poly-crepe-laura-byrnes-design"),
("https://www.raidlondon.com/collections/flats/products"
"/raid-addyson-chunky-flat-shoe-in-white"),
("https://www.unique-vintage.com/collections/flapper-1920s/products"
"/unique-vintage-plus-size-black-silver-beaded-troyes-flapper-dress"),
("https://www.windsorstore.com/collections/accessories-belts/products"
"/rhine-buckle-dbl-o-ring-pu-strap-belt-073010158001"),
("https://de.loungeunderwear.com/products/ribbed-crop-top-black"),
)
def products(self):