fix: reorder JSON and CSV in the other lessons as well

Author: honzajavorek

sources/academy/webscraping/scraping_basics_javascript2/09_getting_links.md

@@ -35,8 +35,8 @@ Over the course of the previous lessons, the code of our program grew to almost
 import httpx
 from bs4 import BeautifulSoup
 from decimal import Decimal
-import csv
 import json
+import csv
 
 url = "https://warehouse-theme-metal.myshopify.com/collections/sales"
 response = httpx.get(url)
@@ -153,8 +153,8 @@ Now let's put it all together:
 import httpx
 from bs4 import BeautifulSoup
 from decimal import Decimal
-import csv
 import json
+import csv
 
 def download(url):
     response = httpx.get(url)
@@ -279,8 +279,8 @@ Browsers reading the HTML know the base address and automatically resolve such l
 import httpx
 from bs4 import BeautifulSoup
 from decimal import Decimal
-import csv
 import json
+import csv
 # highlight-next-line
 from urllib.parse import urljoin
 ```

sources/academy/webscraping/scraping_basics_javascript2/10_crawling.md

@@ -20,8 +20,8 @@ Thanks to the refactoring, we have functions ready for each of the tasks, so we
 import httpx
 from bs4 import BeautifulSoup
 from decimal import Decimal
-import csv
 import json
+import csv
 from urllib.parse import urljoin
 
 def download(url):

sources/academy/webscraping/scraping_basics_javascript2/11_scraping_variants.md

@@ -193,8 +193,8 @@ Now, if we use our new function, we should finally get a program that can scrape
 import httpx
 from bs4 import BeautifulSoup
 from decimal import Decimal
-import csv
 import json
+import csv
 from urllib.parse import urljoin
 
 def download(url):

sources/academy/webscraping/scraping_basics_python/08_saving_data.md

@@ -88,7 +88,6 @@ In Python, we can read and write JSON using the [`json`](https://docs.python.org
 import httpx
 from bs4 import BeautifulSoup
 from decimal import Decimal
-import csv
 # highlight-next-line
 import json
 ```
@@ -179,13 +178,22 @@ Now that's nice, but we didn't want Alice, Bob, kickbox, or TypeScript. What we
 import httpx
 from bs4 import BeautifulSoup
 from decimal import Decimal
+import json
 # highlight-next-line
 import csv
 ```
 
 Next, let's add one more data export to end of the source code of our scraper:
 
 ```py
+def serialize(obj):
+    if isinstance(obj, Decimal):
+        return str(obj)
+    raise TypeError("Object not JSON serializable")
+
+with open("products.json", "w") as file:
+    json.dump(data, file, default=serialize)
+
 with open("products.csv", "w") as file:
     writer = csv.DictWriter(file, fieldnames=["title", "min_price", "price"])
     writer.writeheader()

sources/academy/webscraping/scraping_basics_python/09_getting_links.md

@@ -34,8 +34,8 @@ Over the course of the previous lessons, the code of our program grew to almost
 import httpx
 from bs4 import BeautifulSoup
 from decimal import Decimal
-import csv
 import json
+import csv
 
 url = "https://warehouse-theme-metal.myshopify.com/collections/sales"
 response = httpx.get(url)
@@ -65,19 +65,19 @@ for product in soup.select(".product-item"):
 
     data.append({"title": title, "min_price": min_price, "price": price})
 
-with open("products.csv", "w") as file:
-    writer = csv.DictWriter(file, fieldnames=["title", "min_price", "price"])
-    writer.writeheader()
-    for row in data:
-        writer.writerow(row)
-
 def serialize(obj):
     if isinstance(obj, Decimal):
         return str(obj)
     raise TypeError("Object not JSON serializable")
 
 with open("products.json", "w") as file:
     json.dump(data, file, default=serialize)
+
+with open("products.csv", "w") as file:
+    writer = csv.DictWriter(file, fieldnames=["title", "min_price", "price"])
+    writer.writeheader()
+    for row in data:
+        writer.writerow(row)
 ```
 
 Let's introduce several functions to make the whole thing easier to digest. First, we can turn the beginning of our program into this `download()` function, which takes a URL and returns a `BeautifulSoup` instance:
@@ -152,8 +152,8 @@ Now let's put it all together:
 import httpx
 from bs4 import BeautifulSoup
 from decimal import Decimal
-import csv
 import json
+import csv
 
 def download(url):
     response = httpx.get(url)
@@ -182,13 +182,6 @@ def parse_product(product):
 
     return {"title": title, "min_price": min_price, "price": price}
 
-def export_csv(file, data):
-    fieldnames = list(data[0].keys())
-    writer = csv.DictWriter(file, fieldnames=fieldnames)
-    writer.writeheader()
-    for row in data:
-        writer.writerow(row)
-
 def export_json(file, data):
     def serialize(obj):
         if isinstance(obj, Decimal):
@@ -197,6 +190,13 @@ def export_json(file, data):
 
     json.dump(data, file, default=serialize, indent=2)
 
+def export_csv(file, data):
+    fieldnames = list(data[0].keys())
+    writer = csv.DictWriter(file, fieldnames=fieldnames)
+    writer.writeheader()
+    for row in data:
+        writer.writerow(row)
+
 listing_url = "https://warehouse-theme-metal.myshopify.com/collections/sales"
 listing_soup = download(listing_url)
 
@@ -205,11 +205,11 @@ for product in listing_soup.select(".product-item"):
     item = parse_product(product)
     data.append(item)
 
-with open("products.csv", "w") as file:
-    export_csv(file, data)
-
 with open("products.json", "w") as file:
     export_json(file, data)
+
+with open("products.csv", "w") as file:
+    export_csv(file, data)
 ```
 
 The program is much easier to read now. With the `parse_product()` function handy, we could also replace the convoluted loop with one that only takes up four lines of code.
@@ -278,8 +278,8 @@ Browsers reading the HTML know the base address and automatically resolve such l
 import httpx
 from bs4 import BeautifulSoup
 from decimal import Decimal
-import csv
 import json
+import csv
 # highlight-next-line
 from urllib.parse import urljoin
 ```

sources/academy/webscraping/scraping_basics_python/10_crawling.md

@@ -19,8 +19,8 @@ Thanks to the refactoring, we have functions ready for each of the tasks, so we
 import httpx
 from bs4 import BeautifulSoup
 from decimal import Decimal
-import csv
 import json
+import csv
 from urllib.parse import urljoin
 
 def download(url):
@@ -52,13 +52,6 @@ def parse_product(product, base_url):
 
     return {"title": title, "min_price": min_price, "price": price, "url": url}
 
-def export_csv(file, data):
-    fieldnames = list(data[0].keys())
-    writer = csv.DictWriter(file, fieldnames=fieldnames)
-    writer.writeheader()
-    for row in data:
-        writer.writerow(row)
-
 def export_json(file, data):
     def serialize(obj):
         if isinstance(obj, Decimal):
@@ -67,6 +60,13 @@ def export_json(file, data):
 
     json.dump(data, file, default=serialize, indent=2)
 
+def export_csv(file, data):
+    fieldnames = list(data[0].keys())
+    writer = csv.DictWriter(file, fieldnames=fieldnames)
+    writer.writeheader()
+    for row in data:
+        writer.writerow(row)
+
 listing_url = "https://warehouse-theme-metal.myshopify.com/collections/sales"
 listing_soup = download(listing_url)
 
@@ -75,11 +75,11 @@ for product in listing_soup.select(".product-item"):
     item = parse_product(product, listing_url)
     data.append(item)
 
-with open("products.csv", "w") as file:
-    export_csv(file, data)
-
 with open("products.json", "w") as file:
     export_json(file, data)
+
+with open("products.csv", "w") as file:
+    export_csv(file, data)
 ```
 
 ## Extracting vendor name

sources/academy/webscraping/scraping_basics_python/11_scraping_variants.md

@@ -192,8 +192,8 @@ Now, if we use our new function, we should finally get a program that can scrape
 import httpx
 from bs4 import BeautifulSoup
 from decimal import Decimal
-import csv
 import json
+import csv
 from urllib.parse import urljoin
 
 def download(url):
@@ -235,13 +235,6 @@ def parse_variant(variant):
     )
     return {"variant_name": name, "price": price}
 
-def export_csv(file, data):
-    fieldnames = list(data[0].keys())
-    writer = csv.DictWriter(file, fieldnames=fieldnames)
-    writer.writeheader()
-    for row in data:
-        writer.writerow(row)
-
 def export_json(file, data):
     def serialize(obj):
         if isinstance(obj, Decimal):
@@ -250,6 +243,13 @@ def export_json(file, data):
 
     json.dump(data, file, default=serialize, indent=2)
 
+def export_csv(file, data):
+    fieldnames = list(data[0].keys())
+    writer = csv.DictWriter(file, fieldnames=fieldnames)
+    writer.writeheader()
+    for row in data:
+        writer.writerow(row)
+
 listing_url = "https://warehouse-theme-metal.myshopify.com/collections/sales"
 listing_soup = download(listing_url)
 
@@ -267,11 +267,11 @@ for product in listing_soup.select(".product-item"):
         item["variant_name"] = None
         data.append(item)
 
-with open("products.csv", "w") as file:
-    export_csv(file, data)
-
 with open("products.json", "w") as file:
     export_json(file, data)
+
+with open("products.csv", "w") as file:
+    export_csv(file, data)
 ```
 
 Let's run the scraper and see if all the items in the data contain prices: