From f0e1221ee790b308cae09bb773de7f18c5000107 Mon Sep 17 00:00:00 2001 From: boris Date: Mon, 14 Jan 2019 14:25:09 -0700 Subject: [PATCH 01/10] remove 'u' prefix from strings --- tests.py | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/tests.py b/tests.py index 548c9c7..9953af6 100644 --- a/tests.py +++ b/tests.py @@ -3,17 +3,17 @@ class TestSummarize(TestCase): def testText(self): - article_title = u'Framework for Partitioning and Execution of Data Stream Applications in Mobile Cloud Computing' - article_text = u'The contribution of cloud computing and mobile computing technologies lead to the newly emerging mobile cloud com- puting paradigm. Three major approaches have been pro- posed for mobile cloud applications: 1) extending the access to cloud services to mobile devices; 2) enabling mobile de- vices to work collaboratively as cloud resource providers; 3) augmenting the execution of mobile applications on portable devices using cloud resources. In this paper, we focus on the third approach in supporting mobile data stream applica- tions. More specifically, we study how to optimize the com- putation partitioning of a data stream application between mobile and cloud to achieve maximum speed/throughput in processing the streaming data. To the best of our knowledge, it is the first work to study the partitioning problem for mobile data stream applica- tions, where the optimization is placed on achieving high throughput of processing the streaming data rather than minimizing the makespan of executions as in other appli- cations. We first propose a framework to provide runtime support for the dynamic computation partitioning and exe- cution of the application. Different from existing works, the framework not only allows the dynamic partitioning for a single user but also supports the sharing of computation in- stances among multiple users in the cloud to achieve efficient utilization of the underlying cloud resources. Meanwhile, the framework has better scalability because it is designed on the elastic cloud fabrics. Based on the framework, we design a genetic algorithm for optimal computation parti- tion. Both numerical evaluation and real world experiment have been performed, and the results show that the par- titioned application can achieve at least two times better performance in terms of throughput than the application without partitioning.' + article_title = 'Framework for Partitioning and Execution of Data Stream Applications in Mobile Cloud Computing' + article_text = 'The contribution of cloud computing and mobile computing technologies lead to the newly emerging mobile cloud com- puting paradigm. Three major approaches have been pro- posed for mobile cloud applications: 1) extending the access to cloud services to mobile devices; 2) enabling mobile de- vices to work collaboratively as cloud resource providers; 3) augmenting the execution of mobile applications on portable devices using cloud resources. In this paper, we focus on the third approach in supporting mobile data stream applica- tions. More specifically, we study how to optimize the com- putation partitioning of a data stream application between mobile and cloud to achieve maximum speed/throughput in processing the streaming data. To the best of our knowledge, it is the first work to study the partitioning problem for mobile data stream applica- tions, where the optimization is placed on achieving high throughput of processing the streaming data rather than minimizing the makespan of executions as in other appli- cations. We first propose a framework to provide runtime support for the dynamic computation partitioning and exe- cution of the application. Different from existing works, the framework not only allows the dynamic partitioning for a single user but also supports the sharing of computation in- stances among multiple users in the cloud to achieve efficient utilization of the underlying cloud resources. Meanwhile, the framework has better scalability because it is designed on the elastic cloud fabrics. Based on the framework, we design a genetic algorithm for optimal computation parti- tion. Both numerical evaluation and real world experiment have been performed, and the results show that the par- titioned application can achieve at least two times better performance in terms of throughput than the application without partitioning.' - summarised_article_text = [u'The contribution of cloud computing and mobile computing technologies lead to the newly emerging mobile cloud com- puting paradigm.', u'Three major approaches have been pro- posed for mobile cloud applications: 1) extending the access to cloud services to mobile devices; 2) enabling mobile de- vices to work collaboratively as cloud resource providers; 3) augmenting the execution of mobile applications on portable devices using cloud resources.', u'In this paper, we focus on the third approach in supporting mobile data stream applica- tions.', u'More specifically, we study how to optimize the com- putation partitioning of a data stream application between mobile and cloud to achieve maximum speed/throughput in processing the streaming data.', u'We first propose a framework to provide runtime support for the dynamic computation partitioning and exe- cution of the application.'] + summarised_article_text = ['The contribution of cloud computing and mobile computing technologies lead to the newly emerging mobile cloud com- puting paradigm.', 'Three major approaches have been pro- posed for mobile cloud applications: 1) extending the access to cloud services to mobile devices; 2) enabling mobile de- vices to work collaboratively as cloud resource providers; 3) augmenting the execution of mobile applications on portable devices using cloud resources.', 'In this paper, we focus on the third approach in supporting mobile data stream applica- tions.', 'More specifically, we study how to optimize the com- putation partitioning of a data stream application between mobile and cloud to achieve maximum speed/throughput in processing the streaming data.', 'We first propose a framework to provide runtime support for the dynamic computation partitioning and exe- cution of the application.'] self.assertEqual(Summarize(article_title, article_text), summarised_article_text) def testURLs(self): - urls = (u'http://www.huffingtonpost.com/2013/11/22/twitter-forward-secrecy_n_4326599.html', - u'http://www.bbc.co.uk/news/world-europe-30035666', - u'http://www.bbc.co.uk/news/magazine-29631332') + urls = ('http://www.huffingtonpost.com/2013/11/22/twitter-forward-secrecy_n_4326599.html', + 'http://www.bbc.co.uk/news/world-europe-30035666', + 'http://www.bbc.co.uk/news/magazine-29631332') #just make sure it doesn't crash for url in urls: From 6cd3f1e82f021abdef23838e1e210ccee97e991f Mon Sep 17 00:00:00 2001 From: boris Date: Mon, 14 Jan 2019 14:27:03 -0700 Subject: [PATCH 02/10] ran 2to3 on pyteaser.py --- pyteaser.py | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/pyteaser.py b/pyteaser.py index 5f5bca9..9d69c91 100644 --- a/pyteaser.py +++ b/pyteaser.py @@ -69,14 +69,14 @@ def SummarizeUrl(url): try: article = grab_link(url) except IOError: - print 'IOError' + print('IOError') return None if not (article and article.cleaned_text and article.title): return None - summaries = Summarize(unicode(article.title), - unicode(article.cleaned_text)) + summaries = Summarize(str(article.title), + str(article.cleaned_text)) return summaries @@ -104,7 +104,7 @@ def grab_link(inurl): article = Goose().extract(url=inurl) return article except ValueError: - print 'Goose failed to extract article from url' + print('Goose failed to extract article from url') return None return None @@ -170,7 +170,7 @@ def split_words(text): text = regex_sub(r'[^\w ]', '', text, flags=REGEX_UNICODE) # strip special chars return [x.strip('.').lower() for x in text.split()] except TypeError: - print "Error while splitting characters" + print("Error while splitting characters") return None @@ -204,9 +204,9 @@ def split_sentences(text): second to last line adds this item to the s_iter list and the last line returns the full list. ''' - sentences = regex_split(u'(? Date: Mon, 14 Jan 2019 14:53:04 -0700 Subject: [PATCH 03/10] regex doesn't need a UNICODE flag --- pyteaser.py | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/pyteaser.py b/pyteaser.py index 9d69c91..1c523ed 100644 --- a/pyteaser.py +++ b/pyteaser.py @@ -1,7 +1,6 @@ -# coding=utf-8 from collections import Counter from math import fabs -from re import split as regex_split, sub as regex_sub, UNICODE as REGEX_UNICODE +import re stopWords = set([ "-", " ", ",", ".", "a", "e", "i", "o", "u", "t", "about", "above", @@ -167,7 +166,7 @@ def dbs(words, keywords): def split_words(text): #split a string into array of words try: - text = regex_sub(r'[^\w ]', '', text, flags=REGEX_UNICODE) # strip special chars + text = re.sub(r'[^\w ]', '', text) # strip special chars return [x.strip('.').lower() for x in text.split()] except TypeError: print("Error while splitting characters") @@ -204,7 +203,7 @@ def split_sentences(text): second to last line adds this item to the s_iter list and the last line returns the full list. ''' - sentences = regex_split('(? Date: Mon, 14 Jan 2019 14:57:31 -0700 Subject: [PATCH 04/10] don't ship goose, install it as a dependency --- goose/LICENSE.txt | 202 ----- goose/README.rst.txt | 217 ----- goose/__init__.py | 86 -- goose/article.py | 96 --- goose/cleaners.py | 242 ------ goose/configuration.py | 116 --- goose/crawler.py | 148 ---- goose/extractors.py | 527 ------------ goose/images/__init__.py | 0 goose/images/extractors.py | 425 ---------- goose/images/image.py | 97 --- goose/images/utils.py | 120 --- goose/network.py | 53 -- goose/outputformatters.py | 128 --- goose/parsers.py | 244 ------ goose/resources/images/known-image-css.txt | 9 - goose/resources/text/stopwords-ar.txt | 162 ---- goose/resources/text/stopwords-de.txt | 894 --------------------- goose/resources/text/stopwords-en.txt | 546 ------------- goose/resources/text/stopwords-es.txt | 310 ------- goose/resources/text/stopwords-fr.txt | 220 ----- goose/resources/text/stopwords-it.txt | 287 ------- goose/resources/text/stopwords-ru.txt | 406 ---------- goose/resources/text/stopwords-sv.txt | 547 ------------- goose/resources/text/stopwords-zh.txt | 125 --- goose/text.py | 164 ---- goose/utils/__init__.py | 155 ---- goose/utils/encoding.py | 132 --- goose/version.py | 25 - goose/videos/__init__.py | 0 goose/videos/extractors.py | 144 ---- goose/videos/videos.py | 48 -- pyteaser.py | 2 +- setup.py | 2 +- 34 files changed, 2 insertions(+), 6877 deletions(-) delete mode 100644 goose/LICENSE.txt delete mode 100644 goose/README.rst.txt delete mode 100644 goose/__init__.py delete mode 100644 goose/article.py delete mode 100644 goose/cleaners.py delete mode 100644 goose/configuration.py delete mode 100644 goose/crawler.py delete mode 100644 goose/extractors.py delete mode 100644 goose/images/__init__.py delete mode 100644 goose/images/extractors.py delete mode 100644 goose/images/image.py delete mode 100644 goose/images/utils.py delete mode 100644 goose/network.py delete mode 100644 goose/outputformatters.py delete mode 100644 goose/parsers.py delete mode 100644 goose/resources/images/known-image-css.txt delete mode 100644 goose/resources/text/stopwords-ar.txt delete mode 100644 goose/resources/text/stopwords-de.txt delete mode 100644 goose/resources/text/stopwords-en.txt delete mode 100644 goose/resources/text/stopwords-es.txt delete mode 100644 goose/resources/text/stopwords-fr.txt delete mode 100644 goose/resources/text/stopwords-it.txt delete mode 100644 goose/resources/text/stopwords-ru.txt delete mode 100644 goose/resources/text/stopwords-sv.txt delete mode 100644 goose/resources/text/stopwords-zh.txt delete mode 100644 goose/text.py delete mode 100644 goose/utils/__init__.py delete mode 100644 goose/utils/encoding.py delete mode 100644 goose/version.py delete mode 100644 goose/videos/__init__.py delete mode 100644 goose/videos/extractors.py delete mode 100644 goose/videos/videos.py diff --git a/goose/LICENSE.txt b/goose/LICENSE.txt deleted file mode 100644 index 65ee1c1..0000000 --- a/goose/LICENSE.txt +++ /dev/null @@ -1,202 +0,0 @@ - - Apache License - Version 2.0, January 2004 - http://www.apache.org/licenses/ - -TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION - -1. Definitions. - - "License" shall mean the terms and conditions for use, reproduction, - and distribution as defined by Sections 1 through 9 of this document. - - "Licensor" shall mean the copyright owner or entity authorized by - the copyright owner that is granting the License. - - "Legal Entity" shall mean the union of the acting entity and all - other entities that control, are controlled by, or are under common - control with that entity. For the purposes of this definition, - "control" means (i) the power, direct or indirect, to cause the - direction or management of such entity, whether by contract or - otherwise, or (ii) ownership of fifty percent (50%) or more of the - outstanding shares, or (iii) beneficial ownership of such entity. - - "You" (or "Your") shall mean an individual or Legal Entity - exercising permissions granted by this License. - - "Source" form shall mean the preferred form for making modifications, - including but not limited to software source code, documentation - source, and configuration files. - - "Object" form shall mean any form resulting from mechanical - transformation or translation of a Source form, including but - not limited to compiled object code, generated documentation, - and conversions to other media types. - - "Work" shall mean the work of authorship, whether in Source or - Object form, made available under the License, as indicated by a - copyright notice that is included in or attached to the work - (an example is provided in the Appendix below). - - "Derivative Works" shall mean any work, whether in Source or Object - form, that is based on (or derived from) the Work and for which the - editorial revisions, annotations, elaborations, or other modifications - represent, as a whole, an original work of authorship. For the purposes - of this License, Derivative Works shall not include works that remain - separable from, or merely link (or bind by name) to the interfaces of, - the Work and Derivative Works thereof. - - "Contribution" shall mean any work of authorship, including - the original version of the Work and any modifications or additions - to that Work or Derivative Works thereof, that is intentionally - submitted to Licensor for inclusion in the Work by the copyright owner - or by an individual or Legal Entity authorized to submit on behalf of - the copyright owner. For the purposes of this definition, "submitted" - means any form of electronic, verbal, or written communication sent - to the Licensor or its representatives, including but not limited to - communication on electronic mailing lists, source code control systems, - and issue tracking systems that are managed by, or on behalf of, the - Licensor for the purpose of discussing and improving the Work, but - excluding communication that is conspicuously marked or otherwise - designated in writing by the copyright owner as "Not a Contribution." - - "Contributor" shall mean Licensor and any individual or Legal Entity - on behalf of whom a Contribution has been received by Licensor and - subsequently incorporated within the Work. - -2. Grant of Copyright License. Subject to the terms and conditions of - this License, each Contributor hereby grants to You a perpetual, - worldwide, non-exclusive, no-charge, royalty-free, irrevocable - copyright license to reproduce, prepare Derivative Works of, - publicly display, publicly perform, sublicense, and distribute the - Work and such Derivative Works in Source or Object form. - -3. Grant of Patent License. Subject to the terms and conditions of - this License, each Contributor hereby grants to You a perpetual, - worldwide, non-exclusive, no-charge, royalty-free, irrevocable - (except as stated in this section) patent license to make, have made, - use, offer to sell, sell, import, and otherwise transfer the Work, - where such license applies only to those patent claims licensable - by such Contributor that are necessarily infringed by their - Contribution(s) alone or by combination of their Contribution(s) - with the Work to which such Contribution(s) was submitted. If You - institute patent litigation against any entity (including a - cross-claim or counterclaim in a lawsuit) alleging that the Work - or a Contribution incorporated within the Work constitutes direct - or contributory patent infringement, then any patent licenses - granted to You under this License for that Work shall terminate - as of the date such litigation is filed. - -4. Redistribution. You may reproduce and distribute copies of the - Work or Derivative Works thereof in any medium, with or without - modifications, and in Source or Object form, provided that You - meet the following conditions: - - (a) You must give any other recipients of the Work or - Derivative Works a copy of this License; and - - (b) You must cause any modified files to carry prominent notices - stating that You changed the files; and - - (c) You must retain, in the Source form of any Derivative Works - that You distribute, all copyright, patent, trademark, and - attribution notices from the Source form of the Work, - excluding those notices that do not pertain to any part of - the Derivative Works; and - - (d) If the Work includes a "NOTICE" text file as part of its - distribution, then any Derivative Works that You distribute must - include a readable copy of the attribution notices contained - within such NOTICE file, excluding those notices that do not - pertain to any part of the Derivative Works, in at least one - of the following places: within a NOTICE text file distributed - as part of the Derivative Works; within the Source form or - documentation, if provided along with the Derivative Works; or, - within a display generated by the Derivative Works, if and - wherever such third-party notices normally appear. The contents - of the NOTICE file are for informational purposes only and - do not modify the License. You may add Your own attribution - notices within Derivative Works that You distribute, alongside - or as an addendum to the NOTICE text from the Work, provided - that such additional attribution notices cannot be construed - as modifying the License. - - You may add Your own copyright statement to Your modifications and - may provide additional or different license terms and conditions - for use, reproduction, or distribution of Your modifications, or - for any such Derivative Works as a whole, provided Your use, - reproduction, and distribution of the Work otherwise complies with - the conditions stated in this License. - -5. Submission of Contributions. Unless You explicitly state otherwise, - any Contribution intentionally submitted for inclusion in the Work - by You to the Licensor shall be under the terms and conditions of - this License, without any additional terms or conditions. - Notwithstanding the above, nothing herein shall supersede or modify - the terms of any separate license agreement you may have executed - with Licensor regarding such Contributions. - -6. Trademarks. This License does not grant permission to use the trade - names, trademarks, service marks, or product names of the Licensor, - except as required for reasonable and customary use in describing the - origin of the Work and reproducing the content of the NOTICE file. - -7. Disclaimer of Warranty. Unless required by applicable law or - agreed to in writing, Licensor provides the Work (and each - Contributor provides its Contributions) on an "AS IS" BASIS, - WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or - implied, including, without limitation, any warranties or conditions - of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A - PARTICULAR PURPOSE. You are solely responsible for determining the - appropriateness of using or redistributing the Work and assume any - risks associated with Your exercise of permissions under this License. - -8. Limitation of Liability. In no event and under no legal theory, - whether in tort (including negligence), contract, or otherwise, - unless required by applicable law (such as deliberate and grossly - negligent acts) or agreed to in writing, shall any Contributor be - liable to You for damages, including any direct, indirect, special, - incidental, or consequential damages of any character arising as a - result of this License or out of the use or inability to use the - Work (including but not limited to damages for loss of goodwill, - work stoppage, computer failure or malfunction, or any and all - other commercial damages or losses), even if such Contributor - has been advised of the possibility of such damages. - -9. Accepting Warranty or Additional Liability. While redistributing - the Work or Derivative Works thereof, You may choose to offer, - and charge a fee for, acceptance of support, warranty, indemnity, - or other liability obligations and/or rights consistent with this - License. However, in accepting such obligations, You may act only - on Your own behalf and on Your sole responsibility, not on behalf - of any other Contributor, and only if You agree to indemnify, - defend, and hold each Contributor harmless for any liability - incurred by, or claims asserted against, such Contributor by reason - of your accepting any such warranty or additional liability. - -END OF TERMS AND CONDITIONS - -APPENDIX: How to apply the Apache License to your work. - - To apply the Apache License to your work, attach the following - boilerplate notice, with the fields enclosed by brackets "[]" - replaced with your own identifying information. (Don't include - the brackets!) The text should be enclosed in the appropriate - comment syntax for the file format. We also recommend that a - file or class name and description of purpose be included on the - same "printed page" as the copyright notice for easier - identification within third-party archives. - -Copyright [yyyy] [name of copyright owner] - -Licensed under the Apache License, Version 2.0 (the "License"); -you may not use this file except in compliance with the License. -You may obtain a copy of the License at - - http://www.apache.org/licenses/LICENSE-2.0 - -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. \ No newline at end of file diff --git a/goose/README.rst.txt b/goose/README.rst.txt deleted file mode 100644 index fe45992..0000000 --- a/goose/README.rst.txt +++ /dev/null @@ -1,217 +0,0 @@ -Python-Goose - Article Extractor |Build Status| -=============================================== - -Intro ------ - -Goose was originally an article extractor written in Java that has most -recently (aug2011) converted to a `scala project `_. - -This is a complete rewrite in python. The aim of the software is is to -take any news article or article type web page and not only extract what -is the main body of the article but also all meta data and most probable -image candidate. - -Goose will try to extract the following information: - -- Main text of an article -- Main image of article -- Any Youtube/Vimeo movies embedded in article -- Meta Description -- Meta tags - -The python version was rewrite by: - -- Xavier Grangier - -Licensing ---------- - -If you find Goose useful or have issues please drop me a line, I'd love -to hear how you're using it or what features should be improved - -Goose is licensed by Gravity.com under the Apache 2.0 license, see the -LICENSE file for more details - -Setup ------ - -:: - - mkvirtualenv --no-site-packages goose - git clone https://github.com/grangier/python-goose.git - cd python-goose - pip install -r requirements.txt - python setup.py install - -Take it for a spin ------------------- - -:: - - >>> from goose import Goose - >>> url = 'http://edition.cnn.com/2012/02/22/world/europe/uk-occupy-london/index.html?hpt=ieu_c2' - >>> g = Goose() - >>> article = g.extract(url=url) - >>> article.title - u'Occupy London loses eviction fight' - >>> article.meta_description - "Occupy London protesters who have been camped outside the landmark St. Paul's Cathedral for the past four months lost their court bid to avoid eviction Wednesday in a decision made by London's Court of Appeal." - >>> article.cleaned_text[:150] - (CNN) -- Occupy London protesters who have been camped outside the landmark St. Paul's Cathedral for the past four months lost their court bid to avoi - >>> article.top_image.src - http://i2.cdn.turner.com/cnn/dam/assets/111017024308-occupy-london-st-paul-s-cathedral-story-top.jpg - -Configuration -------------- - -There is two way to pass configuration to goose. The first one is to -pass to goose a Configuration() object. The second one is to pass a -configuration dict - -For instance, if you want to change the userAgent used by Goose juste -pass : - -:: - - >>> g = Goose({'browser_user_agent': 'Mozilla'}) - -Switching parser : Goose can now be use with lxml html parser or lxml -soup parser. By default the html parser is used. If you want to use the -soup parser passe it in the configuration dict : - -:: - - >>> g = Goose({'browser_user_agent': 'Mozilla', 'parser_class':'soup'}) - -Goose is now language aware ---------------------------- - -For exemple scrapping a spanish content page with correct meta language -tags - -:: - - >>> from goose import Goose - >>> url = 'http://sociedad.elpais.com/sociedad/2012/10/27/actualidad/1351332873_157836.html' - >>> g = Goose() - >>> article = g.extract(url=url) - >>> article.title - u'Las listas de espera se agravan' - >>> article.cleaned_text[:150] - u'Los recortes pasan factura a los pacientes. De diciembre de 2010 a junio de 2012 las listas de espera para operarse aumentaron un 125%. Hay m\xe1s ciudad' - -Some pages don't have correct meta language tags, you can force it using -configuration : - -:: - - >>> from goose import Goose - >>> url = 'http://www.elmundo.es/elmundo/2012/10/28/espana/1351388909.html' - >>> g = Goose({'use_meta_language': False, 'target_language':'es'}) - >>> article = g.extract(url=url) - >>> article.cleaned_text[:150] - u'Importante golpe a la banda terrorista ETA en Francia. La Guardia Civil ha detenido en un hotel de Macon, a 70 kil\xf3metros de Lyon, a Izaskun Lesaka y ' - -Passing {'use\_meta\_language': False, 'target\_language':'es'} will -force as configuration will force the spanish language - - -Video extraction ----------------- - -:: - - >>> import goose - >>> url = 'http://www.liberation.fr/politiques/2013/08/12/journee-de-jeux-pour-ayrault-dans-les-jardins-de-matignon_924350' - >>> g = goose.Goose({'target_language':'fr'}) - >>> article = g.extract(url=url) - >>> article.movies - [] - >>> article.movies[0].src - 'http://sa.kewego.com/embed/vp/?language_code=fr&playerKey=1764a824c13c&configKey=dcc707ec373f&suffix=&sig=9bc77afb496s&autostart=false' - >>> article.movies[0].embed_code - '