Port referer-parser to python.

Author: donspaulding

MANIFEST.in

@@ -0,0 +1 @@
+include README.md

README.md

@@ -0,0 +1,59 @@
+# referer-parser Python library
+
+This is the Python implementation of [referer-parser] [referer-parser], the library for extracting search marketing data from referer _(sic)_ URLs.
+
+The implementation uses the shared 'database' of known search engine referers found in [`search.yml`] [search-yml].
+
+## Installation
+
+    pip install referer_parser
+
+## Usage
+
+Create a new instance of a Referer object by passing in the url you want to parse:
+
+```python
+from referer_parser import Referer
+
+referer_url = 'http://www.google.com/search?q=gateway+oracle+cards+denise+linn&hl=en&client=safari'
+
+r = Referer(referer_url)
+```
+
+The `r` variable now holds a Referer instance.  The important attributes are:
+
+```python
+print(r.known)              # True
+print(r.referer)            # 'Google'
+print(r.search_parameter)   # 'q'     
+print(r.search_term)        # 'gateway oracle cards denise linn'
+print(r.uri)                # ParseResult(scheme='http', netloc='www.google.com', path='/search', params='', query='q=gateway+oracle+cards+denise+linn&hl=en&client=safari', fragment='')
+```
+
+The `uri` attribute is an instance of ParseResult from the standard libraries `urlparse` module.
+
+## Contributing
+
+1. Fork it
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create new Pull Request
+
+## Copyright and license
+
+The referer-parser Python library is copyright 2012 Don Spaulding.
+
+Licensed under the [Apache License, Version 2.0] [license] (the "License");
+you may not use this software except in compliance with the License.
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+
+[referer-parser]: https://github.com/snowplow/referer-parser
+[search-yml]: https://github.com/snowplow/referer-parser/blob/master/search.yml
+
+[license]: http://www.apache.org/licenses/LICENSE-2.0

build_json.py

@@ -0,0 +1,12 @@
+#!/usr/bin/env python
+import json
+
+import yaml
+
+def build_json():
+    searches = yaml.load(open('./data/search.yml'))
+    with open('./data/search.json', 'w') as fp:
+        json.dump(searches, fp)
+
+if __name__ == "__main__":
+    build_json()

data/search.json

@@ -0,0 +1,27 @@
+import json
+from urlparse import urlparse, parse_qsl
+
+
+REFERERS = {}
+for ref, config in json.load(open('./data/search.json')).iteritems():
+    for domain in config['domains']:
+        REFERERS[domain] = {
+            'name': ref,
+            'params': map(unicode.lower, config['parameters']),
+        }
+
+
+class Referer(object):
+    def __init__(self, url):
+        self.uri = urlparse(url)
+        host = self.uri.netloc.split(':', 1)[0]
+        self.known = False if host not in REFERERS else True
+        self.referer = None
+        self.search_parameter = ''
+        self.search_term = ''
+        if self.known:
+            self.referer = REFERERS[host]['name']
+            for param, val in parse_qsl(self.uri.query):
+                if param.lower() in REFERERS[host]['params']:
+                    self.search_parameter = param
+                    self.search_term = val

referer_parser.py

@@ -0,0 +1,14 @@
+import os
+from setuptools import setup, find_packages
+
+setup_pth = os.path.dirname(__file__)
+readme_pth = os.path.join(setup_pth, 'README.md')
+
+setup(
+    name='referer-parser',
+    version="0.0.3",
+    long_description=open(readme_pth).read(),
+    packages=find_packages(),
+    include_package_data=True,
+    zip_safe=False,
+)