| Name | datadigger JSON |
| Version |
0.11
JSON |
| download |
| home_page | None |
| Summary | The package is geared towards automating text-related tasks and is useful for data extraction, web scraping, and text file management. |
| upload_time | 2025-08-27 13:51:41 |
| maintainer | None |
| docs_url | None |
| author | Ramesh Chandra |
| requires_python | >=3.6 |
| license | None |
| keywords |
|
| VCS |
|
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# datadigger
`datadigger` is a Python package designed to simplify text processing tasks, such as extracting, manipulating, and saving text data from various sources. It includes utility functions for working with text, handling files (e.g., reading/writing CSV), interacting with HTML elements via BeautifulSoup, and performing operations like string standardization, element extraction with CSS selectors, and more.
---
## ✨ Key Features
- 📝 **String manipulation**: Clean, standardize, and sanitize text.
- 📂 **File handling**: Read/write CSV, TXT, and other files with optional headers and delimiters.
- 🌐 **HTML parsing**: Extract text or attributes using **CSS selectors** or **XPath**.
- 📦 **JSON utilities**: Access deeply nested values and normalize data.
- 🧹 **Flexible error handling**: Graceful behavior with missing/invalid inputs.
---
## 📦 Installation
Install via **pip**:
```bash
pip install datadigger
# ================================================================
1. Create a Directory
from datadigger import create_directory
# Creates a directory if it doesn't already exist.
# Example 1: Creating a new directory
create_directory("new_folder")
# Example 2: Creating nested directories
create_directory("parent_folder/sub_folder")
# ================================================================
2. Standardize a String
from datadigger import standardized_string
# This function standardizes the input string by removing escape sequences like \n, \t, and \r, removing HTML tags, collapsing multiple spaces, and trimming leading/trailing spaces.
# Example 1: Standardize a string with newlines, tabs, and HTML tags
input_string_1 = "<html><body> Hello \nWorld! \tThis is a test. </body></html>"
print("Standardized String 1:", standardized_string(input_string_1))
# Example 2: Input string with multiple spaces and line breaks
input_string_2 = " This is a \n\n string with spaces and \t tabs. "
print("Standardized String 2:", standardized_string(input_string_2))
# Example 3: Pass an empty string
input_string_3 = ""
print("Standardized String 3:", standardized_string(input_string_3))
# Example 4: Pass None (invalid input)
input_string_4 = None
print("Standardized String 4:", standardized_string(input_string_4))
================================================================
3. Remove Common Elements
from datadigger import remove_common_elements
# Example 1: Lists
print(remove_common_elements([1, 2, 3, 4, 5], [3, 4, 6]))
# Output: [1, 2, 5]
# Example 2: Set + Tuple
print(remove_common_elements({1, 2, 3, 4, 5}, (3, 4, 6)))
# Output: {1, 2, 5}
# Example 3: Missing arguments
print(remove_common_elements([1, 2], None))
# Output: "Value not passed for: remove_by"
print(remove_common_elements(None, None))
# Output: "Value not passed for: remove_in, remove_by"
================================================================
4. Save to CSV
from datadigger import save_to_csv
list_data = [[1, 'Alice', 23], [2, 'Bob', 30], [3, 'Charlie', 25]]
column_header_list = ['ID', 'Name', 'Age']
output_file_path = 'output_data.csv'
# Default separator (comma)
save_to_csv(list_data, column_header_list, output_file_path)
# Tab separator
save_to_csv(list_data, column_header_list, output_file_path, sep="\t")
# Semicolon separator
save_to_csv(list_data, column_header_list, output_file_path, sep=";")
Output (default, sep=","):
ID,Name,Age
1,Alice,23
2,Bob,30
3,Charlie,25
Output (sep="\t"):
ID Name Age
1 Alice 23
2 Bob 30
3 Charlie 25
================================================================
5. Read CSV
from datadigger import read_csv
csv_file_path = 'data.csv'
get_value_by_col_name = 'URL'
filter_col_name = 'Category'
include_filter_col_values = ['Tech']
result = read_csv(csv_file_path, get_value_by_col_name, filter_col_name, include_filter_col_values)
print(result)
Sample CSV
Category,URL
Tech,https://tech1.com
Tech,https://tech2.com
Science,https://science1.com
Result
['https://tech1.com', 'https://tech2.com']
================================================================
6. Extract JSON Content
from datadigger import get_json_content
json_data = {"user": {"name": "John", "age": 30}}
keys = ["user", "name"]
print(get_json_content(json_data, keys))
# Output: "John"
================================================================
7. Extract with CSS Selectors
from bs4 import BeautifulSoup
from datadigger import get_selector_content
html_content = """
<html>
<body>
<div class="example">Example Text</div>
<a href="https://example.com">Link</a>
</body>
</html>
"""
soup_obj = BeautifulSoup(html_content, "html.parser")
print(get_selector_content(soup_obj=soup_obj, css_selector_ele=".example"))
# [<div class="example">Example Text</div>]
print(get_selector_content(soup_obj=soup_obj, css_selector=".example"))
# "Example Text"
print(get_selector_content(soup_obj=soup_obj, css_selector="a", attr="href"))
# "https://example.com"
print(get_selector_content(soup_obj))
# "Example Text Link"
================================================================
8. Extract with XPath
from datadigger import get_xpath_content
from lxml import etree
html_content = """
<html>
<body>
<div>
<h1>Welcome to My Website</h1>
<p class="description">This is a paragraph.</p>
<a href="http://example.com" id="example-link">Click here</a>
</div>
</body>
</html>
"""
tree = etree.HTML(html_content)
print(get_xpath_content(tree, xpath="//h1"))
# "Welcome to My Website"
print(get_xpath_content(tree, xpath="//a[@id='example-link']", attr="href"))
# "http://example.com"
print(get_xpath_content(tree, xpath="//a", attr="id"))
# "example-link"
================================================================
9. Save & Read Files
from datadigger import save_file, read_file
# Save file
save_file("output", "This is a new file.", "example.txt")
save_file("output", "Appending content.", "example.txt", mode="a")
save_file("output", "Special characters: äöüß", "example_latin1.txt", encoding="latin-1")
# Read file
content = read_file("output/example.txt")
print(content)
Raw data
{
"_id": null,
"home_page": null,
"name": "datadigger",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.6",
"maintainer_email": null,
"keywords": null,
"author": "Ramesh Chandra",
"author_email": "rameshsofter@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/f8/ca/a3d880d3bcea12f79628bacd9195ecf5cc2ffbb510ce9c748e53de9ec4e3/datadigger-0.11.tar.gz",
"platform": null,
"description": "# datadigger\r\n\r\n`datadigger` is a Python package designed to simplify text processing tasks, such as extracting, manipulating, and saving text data from various sources. It includes utility functions for working with text, handling files (e.g., reading/writing CSV), interacting with HTML elements via BeautifulSoup, and performing operations like string standardization, element extraction with CSS selectors, and more. \r\n\r\n---\r\n\r\n## \u2728 Key Features\r\n\r\n- \ud83d\udcdd **String manipulation**: Clean, standardize, and sanitize text. \r\n- \ud83d\udcc2 **File handling**: Read/write CSV, TXT, and other files with optional headers and delimiters. \r\n- \ud83c\udf10 **HTML parsing**: Extract text or attributes using **CSS selectors** or **XPath**. \r\n- \ud83d\udce6 **JSON utilities**: Access deeply nested values and normalize data. \r\n- \ud83e\uddf9 **Flexible error handling**: Graceful behavior with missing/invalid inputs. \r\n\r\n---\r\n\r\n## \ud83d\udce6 Installation\r\n\r\nInstall via **pip**:\r\n\r\n```bash\r\npip install datadigger\r\n\r\n\r\n# ================================================================\r\n1. Create a Directory\r\n\r\nfrom datadigger import create_directory\r\n# Creates a directory if it doesn't already exist.\r\n\r\n\r\n# Example 1: Creating a new directory\r\ncreate_directory(\"new_folder\")\r\n\r\n# Example 2: Creating nested directories\r\ncreate_directory(\"parent_folder/sub_folder\")\r\n\r\n# ================================================================\r\n2. Standardize a String\r\n\r\nfrom datadigger import standardized_string\r\n# This function standardizes the input string by removing escape sequences like \\n, \\t, and \\r, removing HTML tags, collapsing multiple spaces, and trimming leading/trailing spaces.\r\n\r\n\r\n# Example 1: Standardize a string with newlines, tabs, and HTML tags\r\ninput_string_1 = \"<html><body> Hello \\nWorld! \\tThis is a test. </body></html>\"\r\nprint(\"Standardized String 1:\", standardized_string(input_string_1))\r\n\r\n# Example 2: Input string with multiple spaces and line breaks\r\ninput_string_2 = \" This is a \\n\\n string with spaces and \\t tabs. \"\r\nprint(\"Standardized String 2:\", standardized_string(input_string_2))\r\n\r\n# Example 3: Pass an empty string\r\ninput_string_3 = \"\"\r\nprint(\"Standardized String 3:\", standardized_string(input_string_3))\r\n\r\n# Example 4: Pass None (invalid input)\r\ninput_string_4 = None\r\nprint(\"Standardized String 4:\", standardized_string(input_string_4))\r\n\r\n================================================================\r\n3. Remove Common Elements\r\n\r\nfrom datadigger import remove_common_elements\r\n\r\n# Example 1: Lists\r\nprint(remove_common_elements([1, 2, 3, 4, 5], [3, 4, 6]))\r\n# Output: [1, 2, 5]\r\n\r\n# Example 2: Set + Tuple\r\nprint(remove_common_elements({1, 2, 3, 4, 5}, (3, 4, 6)))\r\n# Output: {1, 2, 5}\r\n\r\n# Example 3: Missing arguments\r\nprint(remove_common_elements([1, 2], None))\r\n# Output: \"Value not passed for: remove_by\"\r\n\r\nprint(remove_common_elements(None, None))\r\n# Output: \"Value not passed for: remove_in, remove_by\"\r\n\r\n\r\n================================================================\r\n4. Save to CSV\r\n\r\nfrom datadigger import save_to_csv\r\n\r\nlist_data = [[1, 'Alice', 23], [2, 'Bob', 30], [3, 'Charlie', 25]]\r\ncolumn_header_list = ['ID', 'Name', 'Age']\r\noutput_file_path = 'output_data.csv'\r\n\r\n# Default separator (comma)\r\nsave_to_csv(list_data, column_header_list, output_file_path)\r\n\r\n# Tab separator\r\nsave_to_csv(list_data, column_header_list, output_file_path, sep=\"\\t\")\r\n\r\n# Semicolon separator\r\nsave_to_csv(list_data, column_header_list, output_file_path, sep=\";\")\r\n\r\nOutput (default, sep=\",\"):\r\nID,Name,Age\r\n1,Alice,23\r\n2,Bob,30\r\n3,Charlie,25\r\n\r\nOutput (sep=\"\\t\"):\r\nID Name Age\r\n1 Alice 23\r\n2 Bob 30\r\n3 Charlie 25\r\n\r\n\r\n\r\n================================================================\r\n5. Read CSV\r\n\r\nfrom datadigger import read_csv\r\n\r\ncsv_file_path = 'data.csv'\r\nget_value_by_col_name = 'URL'\r\nfilter_col_name = 'Category'\r\ninclude_filter_col_values = ['Tech']\r\n\r\nresult = read_csv(csv_file_path, get_value_by_col_name, filter_col_name, include_filter_col_values)\r\nprint(result)\r\n\r\nSample CSV\r\n\r\nCategory,URL\r\nTech,https://tech1.com\r\nTech,https://tech2.com\r\nScience,https://science1.com\r\n\r\nResult\r\n\r\n['https://tech1.com', 'https://tech2.com']\r\n\r\n================================================================\r\n6. Extract JSON Content\r\n\r\nfrom datadigger import get_json_content\r\n\r\njson_data = {\"user\": {\"name\": \"John\", \"age\": 30}}\r\nkeys = [\"user\", \"name\"]\r\n\r\nprint(get_json_content(json_data, keys))\r\n# Output: \"John\"\r\n\r\n================================================================\r\n7. Extract with CSS Selectors\r\n\r\nfrom bs4 import BeautifulSoup\r\nfrom datadigger import get_selector_content\r\n\r\nhtml_content = \"\"\"\r\n<html>\r\n <body>\r\n <div class=\"example\">Example Text</div>\r\n <a href=\"https://example.com\">Link</a>\r\n </body>\r\n</html>\r\n\"\"\"\r\nsoup_obj = BeautifulSoup(html_content, \"html.parser\")\r\n\r\nprint(get_selector_content(soup_obj=soup_obj, css_selector_ele=\".example\"))\r\n# [<div class=\"example\">Example Text</div>]\r\n\r\nprint(get_selector_content(soup_obj=soup_obj, css_selector=\".example\"))\r\n# \"Example Text\"\r\n\r\nprint(get_selector_content(soup_obj=soup_obj, css_selector=\"a\", attr=\"href\"))\r\n# \"https://example.com\"\r\n\r\nprint(get_selector_content(soup_obj))\r\n# \"Example Text Link\"\r\n\r\n\r\n================================================================\r\n8. Extract with XPath\r\n\r\nfrom datadigger import get_xpath_content\r\nfrom lxml import etree\r\n\r\nhtml_content = \"\"\"\r\n<html>\r\n <body>\r\n <div>\r\n <h1>Welcome to My Website</h1>\r\n <p class=\"description\">This is a paragraph.</p>\r\n <a href=\"http://example.com\" id=\"example-link\">Click here</a>\r\n </div>\r\n </body>\r\n</html>\r\n\"\"\"\r\n\r\ntree = etree.HTML(html_content)\r\n\r\nprint(get_xpath_content(tree, xpath=\"//h1\"))\r\n# \"Welcome to My Website\"\r\n\r\nprint(get_xpath_content(tree, xpath=\"//a[@id='example-link']\", attr=\"href\"))\r\n# \"http://example.com\"\r\n\r\nprint(get_xpath_content(tree, xpath=\"//a\", attr=\"id\"))\r\n# \"example-link\"\r\n\r\n\r\n================================================================\r\n9. Save & Read Files\r\n\r\nfrom datadigger import save_file, read_file\r\n\r\n# Save file\r\nsave_file(\"output\", \"This is a new file.\", \"example.txt\") \r\nsave_file(\"output\", \"Appending content.\", \"example.txt\", mode=\"a\") \r\nsave_file(\"output\", \"Special characters: \u00e4\u00f6\u00fc\u00df\", \"example_latin1.txt\", encoding=\"latin-1\") \r\n\r\n# Read file\r\ncontent = read_file(\"output/example.txt\")\r\nprint(content)\r\n\r\n\r\n\r\n",
"bugtrack_url": null,
"license": null,
"summary": "The package is geared towards automating text-related tasks and is useful for data extraction, web scraping, and text file management.",
"version": "0.11",
"project_urls": null,
"split_keywords": [],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "6842240ec899e3c8f5aa305dfcb9f08178866c227fde02ad6631e4ca78da0969",
"md5": "f7bff424060439c04bcd3477b84ad2d2",
"sha256": "718ab5b22f4bc3530d970bd6c0ac6516c30615fcf78f4d26ebf3caf2009004aa"
},
"downloads": -1,
"filename": "datadigger-0.11-py3-none-any.whl",
"has_sig": false,
"md5_digest": "f7bff424060439c04bcd3477b84ad2d2",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.6",
"size": 11741,
"upload_time": "2025-08-27T13:51:40",
"upload_time_iso_8601": "2025-08-27T13:51:40.371188Z",
"url": "https://files.pythonhosted.org/packages/68/42/240ec899e3c8f5aa305dfcb9f08178866c227fde02ad6631e4ca78da0969/datadigger-0.11-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "f8caa3d880d3bcea12f79628bacd9195ecf5cc2ffbb510ce9c748e53de9ec4e3",
"md5": "de263d12be258b1163c2a920dc3e6e89",
"sha256": "47dab4fbd7d6031973d33595b0eecdd9fe78f3e5c1034bf4aad1703ece7199c8"
},
"downloads": -1,
"filename": "datadigger-0.11.tar.gz",
"has_sig": false,
"md5_digest": "de263d12be258b1163c2a920dc3e6e89",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.6",
"size": 13555,
"upload_time": "2025-08-27T13:51:41",
"upload_time_iso_8601": "2025-08-27T13:51:41.378764Z",
"url": "https://files.pythonhosted.org/packages/f8/ca/a3d880d3bcea12f79628bacd9195ecf5cc2ffbb510ce9c748e53de9ec4e3/datadigger-0.11.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-08-27 13:51:41",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "datadigger"
}
