CSV newline bug on Windows, but is OK on Archlinux and Mac

chapter5/1-getPageMedia.py

@@ -39,5 +39,5 @@ def getDownloadPath(baseUrl, absoluteUrl, downloadDirectory):
     fileUrl = getAbsoluteURL(baseUrl, download["src"])
     if fileUrl is not None:
         print(fileUrl)
-
-urlretrieve(fileUrl, getDownloadPath(baseUrl, fileUrl, downloadDirectory))
+        fileUrl = fileUrl.split('?')[0]
+        urlretrieve(fileUrl, getDownloadPath(baseUrl, fileUrl, downloadDirectory))

chapter5/2-createCsv.py

@@ -1,11 +1,13 @@
 import csv
-#from os import open
+import os
 
-csvFile = open("../files/test.csv", 'w+')
+filename = "../files/test.csv"
+os.makedirs(os.path.dirname(filename), exist_ok=True)
+csvFile = open(filename, 'w', newline='')
 try:
     writer = csv.writer(csvFile)
     writer.writerow(('number', 'number plus 2', 'number times 2'))
     for i in range(10):
-        writer.writerow( (i, i+2, i*2))
+        writer.writerow((i, i+2, i*2))
 finally:
     csvFile.close()

chapter5/3-scrapeCsv.py

@@ -4,17 +4,17 @@
 
 html = urlopen("http://en.wikipedia.org/wiki/Comparison_of_text_editors")
 bsObj = BeautifulSoup(html)
-#The main comparison table is currently the first table on the page
-table = bsObj.findAll("table",{"class":"wikitable"})[0]
+# The main comparison table is currently the first table on the page
+table = bsObj.findAll("table", {"class": "wikitable"})[0]
 rows = table.findAll("tr")
 
-csvFile = open("files/editors.csv", 'wt')
+csvFile = open("../files/editors.csv", 'w', encoding='utf-8', newline='')
 writer = csv.writer(csvFile)
 try:
-	for row in rows:
-		csvRow = []
-		for cell in row.findAll(['td', 'th']):
-			csvRow.append(cell.get_text())
-			writer.writerow(csvRow)
+    for row in rows:
+        csvRow = []
+        for cell in row.findAll(['td', 'th']):
+            csvRow.append(cell.get_text())
+        writer.writerow(csvRow)
 finally:
-    csvFile.close()
+    csvFile.close()

chapter5/5-storeWikiLinks.py

@@ -1,5 +1,6 @@
 from urllib.request import urlopen
 from bs4 import BeautifulSoup
+import re
 import datetime
 import random
 import pymysql
@@ -30,4 +31,4 @@ def getLinks(articleUrl):
          links = getLinks(newArticle)
 finally:
     cur.close()
-    conn.close()
+    conn.close()