Merge de9b811 into 3680f4f

.gitignore

@@ -8,6 +8,7 @@ __pycache__/
 # Distribution / packaging
 .Python
 env/
+.venv
 build/
 develop-eggs/
 dist/
@@ -57,3 +58,6 @@ target/
 
 # Vim stuff
 .ropeproject/
+
+# Pycharm settings
+.idea

.travis.yml

@@ -6,9 +6,13 @@ matrix:
 python:
   - "2.7"
   - "3.6"
+  - "3.7"
+  - "3.8"
+  - "pypy"
+  - "pypy3.6-7.3.1"
 install:
   - "pip install ."
   - "pip install -r requirements_dev.txt"
-script: py.test --cov haralyzer tests/
+script: py.test --cov haralyzer tests/ -vv
 after_success:
   - coveralls

README.rst

@@ -19,9 +19,11 @@ A Python Framework For Using HAR Files To Analyze Web Pages.
 Overview
 --------
 
-The haralyzer module contains two classes for analyzing web pages based
+The haralyzer module contains three classes for analyzing web pages based
 on a HAR file. ``HarParser()`` represents a full file (which might have
-multiple pages), and ``HarPage()`` represents a single page from said file.
+multiple pages). ``HarPage()`` represents a single page from said file.
+``HarEntry()`` represents an entry in a ``HarPage()``, and there are are multiple entries per page.
+Each ``HarEntry`` has a request and response that contains items such as the headers, status code, timings, etc
 
 ``HarParser`` has a couple of helpful methods for analyzing single entries
 from a HAR file, but most of the pertinent functions are inside of the page
@@ -119,6 +121,102 @@ to a page, an additional page will be created with an ID of `unknown`. This
 not have attributes for things like time to first byte or page load, and will
 return `None`.
 
+HarEntry
+++++++++
+
+The ``HarEntry()`` object contains useful information for each request. The main purpose is to have easy of use as it has a lot of attributes.
+Each entry also contains a ``Request()`` and ``Response()`` which are styled off of the requests library.::
+
+    import json
+    from haralyzer import HarPage
+
+    with open("humanssuck.net.har", 'r') as f:
+        har_page = HarPage('page_3', har_data=json.loads(f.read()))
+
+    ### GET BASIC INFO
+    print(har_page.hostname)
+    # 'humanssuck.net'
+    print(har_page.url)
+    # 'http://humanssuck.net/'
+
+    ### GET LIST OF ENTRIES
+    print(har_page.entries)
+    # [HarEntry for http://humanssuck.net/, HarEntry for http://humanssuck.net/test.css, ...]
+
+    ### WORKING WITH ENTRIES
+    single_entry = har_page.entries[0]
+
+    ### REQUEST HEADERS
+    print(single_entry.request.headers)
+    # [{'name': 'Host', 'value': 'humanssuck.net'}, {'name': 'User-Agent', 'value': 'Mozilla/5.0 (X11; Linux i686 on x86_64; rv:25.0) Gecko/20100101 Firefox/25.0'}, ...]
+
+    ### RESPONSE HEADERS
+    print(single_entry.response.headers)
+    # [{'name': 'Server', 'value': 'nginx'}, {'name': 'Date', 'value': 'Mon, 23 Feb 2015 03:28:12 GMT'}, ...]
+
+    ### RESPONSE CODE
+    print(single_entry.response.status)
+    # 200
+
+    # GET THE VALUE OF A REQUEST OR RESPONSE HEADER
+    print(single_entry.request.get_header_value("accept"))
+    # text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8
+
+    # ALL ATTRIBUTES OF A ENTRY
+
+    single_entry.cache -> Dictionary of cached content
+    single_entry.cookies -> List of combined cookies for request and response
+    single_entry.headers -> List of combined headers for request and response
+    single_entry.pageref -> String of the pageref
+    single_entry.port -> Integer of the port number for the server
+    single_entry.request -> Request object
+    single_entry.response -> Response object
+    single_entry.secure -> Bool if secure is set
+    single_entry.serverAddress -> String of the server IP
+    single_entry.startTime -> Datetime of the start time
+    single_entry.time -> Integer of total time for entry
+    single_entry.timings -> Dictionary of the timings for a request
+    single_entry.url -> String of the request url
+
+    # ALL ATTRIBUTES OF A REQUEST
+
+    single_entry.request.accept -> String of the ``Accept`` header
+    single_entry.request.bodySize -> Integer of the body size for the request
+    single_entry.request.cacheControl -> String of the ``Cache-Control`` header
+    single_entry.request.cookies -> List of cookies
+    single_entry.request.encoding -> String of the ``Accept-Encoding`` header
+    single_entry.request.headers -> List of headers
+    single_entry.request.headersSize -> Integer of the size of the headers
+    single_entry.request.host -> String of the ``Host`` header
+    single_entry.request.httpVersion -> String of the http version used
+    single_entry.request.language -> String of the ``Accept-Language`` header
+    single_entry.request.method -> String of the HTTP method used
+    single_entry.request.queryString -> List of query string used
+    single_entry.request.url -> String of the URL
+    single_entry.request.userAgent -> String of the User-Agent
+
+    # ALL ATTRIBUTES OF A RESPONSE
+    single_entry.response.bodySize -> Integer of the body size for the response
+    single_entry.response.cacheControl -> String of the ``Cache-Control`` header
+    single_entry.response.contentSecurityPolicy -> String of the `Content-Security-Policy`` header
+    single_entry.response.contentSize -> Integer of the content size
+    single_entry.response.contentType -> String of the ``content-type`` header
+    single_entry.response.date -> String of the ``date`` header
+    single_entry.response.headers -> List of headers
+    single_entry.response.headersSize -> Integer of the size of the headers
+    single_entry.response.httpVersion -> String of the http version used
+    single_entry.response.lastModified -> String of the ``last-modified`` header
+    single_entry.response.mimeType -> String of the mimeType of the content
+    single_entry.response.redirectURL -> String of the redirect URL or None
+    single_entry.response.status -> Integer of th HTTP status code
+    single_entry.response.statusText -> String of HTTP status
+    single_entry.response.text -> String of content received
+
+    ** You are still able to access items like a dictionary.
+    print(single_entry["connection"])
+    # "80"
+
+
 MultiHarParser
 ++++++++++++++
 

haralyzer/__init__.py

@@ -1,7 +1,10 @@
 """
 Module for analyzing web pages using HAR files
 """
-from .assets import HarParser, HarPage
+from .assets import HarParser, HarPage, HarEntry
 
 
 from .multihar import MultiHarParser
+
+
+__all__ = ["HarPage", "HarParser", "MultiHarParser", "HarEntry"]