работа с парсингом

Author: Sinrez

diving_in_python/file2.py

@@ -0,0 +1,47 @@
+from os.path import exists
+from tempfile import gettempdir
+from os.path import join
+
+
+class File:
+    add_helper = 0
+
+    def __init__(self, path_to_file):
+        if not exists(path_to_file):
+            open(path_to_file, "w").close()
+        self.path_to_file = path_to_file
+
+    def __str__(self):
+        return self.path_to_file
+
+    def __iter__(self):
+        self.current = 0
+        with open(self.path_to_file, "r") as f:
+            self.lines = f.readlines()
+        return self
+
+    def __next__(self):
+        if len(self.lines) == self.current:
+            raise StopIteration
+        line = self.lines[self.current]
+        self.current += 1
+        return line
+
+    def __add__(self, obj):
+        File.add_helper += 1
+        new_obj = File(join(gettempdir(), str(self.add_helper)))
+        new_obj.write(self.read() + obj.read())
+        return new_obj
+
+    def read(self):
+        with open(self.path_to_file, "r") as f:
+            return f.read()
+
+    def write(self, data):
+        with open(self.path_to_file, "w") as f:
+            f.write(data)
+            print(len(data))
+
+
+if __name__ == "__main__":
+    pass

diving_in_python/file_class.py

@@ -1,44 +1,30 @@
-import os
-import tempfile
-import datetime
+import os.path, tempfile
 
 
 class File:
+    """Интерфейс для работы с файлами"""
 
     def __init__(self, file_path):
         self.file_path = file_path
-        self.cur_position = 0
 
-        if not os.path.exists(file_path):
-            with open(file_path, 'w'):
-                pass
-
-    def write(self, content):
+    def write(self, data):
         with open(self.file_path, 'w') as f:
-            f.write(content)
+            f.write(data)
 
     def read(self):
-        with open(self.file_path, 'r') as f:
+        with open(self.file_path) as f:
             return f.read()
 
-    def __add__(self, other):
-        new_path = os.path.join(tempfile.gettempdir(), datetime.datetime.today().strftime("%Y%m%d%H%M%S"))
-        new_file = File(new_path)
-        new_file.write(self.read() + other.read())
-        return new_file
+    def __add__(self, obj):
+        file_name = '-'.join([self.file_path, obj.file_path])
+        new_file_path = os.path.join(tempfile.gettempdir(), str(hash(file_name)))
+        new_obj = File(new_file_path)
+        new_obj.write(self.read() + obj.read())
 
-    def __iter__(self):
-        return self
-
-    def __next__(self):
-        with open(self.file_path, 'r') as f:
-            f.seek(self.cur_position)
-            line = f.readline()
-            if not line:
-                self.cur_position = 0
-                raise StopIteration('EOF')
-            self.cur_position = f.tell()
-            return line
+        return new_obj
 
     def __str__(self):
-        return self.file_path
+        return self.file_path
+
+    def __iter__(self):
+        return open(self.file_path, 'r')

heartbeat_market/usd_spread.sqlite

@@ -0,0 +1,8 @@
+from urllib.request import urlopen
+from io import StringIO
+import csv
+data = urlopen('http://pythonscraping.com/files/MontyPythonAlbums.csv').read().decode('ascii', 'ignore')
+dataFile = StringIO(data)
+csvReader = csv.reader(dataFile)
+for row in csvReader:
+       print(row)

parsing/book_parsing/6.py

@@ -0,0 +1,9 @@
+from urllib.request import urlopen
+from io import StringIO
+import csv
+data = urlopen('http://pythonscraping.com/files/MontyPythonAlbums.csv').read().decode('ascii', 'ignore')
+dataFile = StringIO(data)
+dictReader = csv.DictReader(dataFile)
+print(dictReader.fieldnames)
+for row in dictReader:
+    print(row)