├── .gitignore ├── LICENSE ├── README.rst ├── docs ├── Makefile ├── api.rst ├── conf.py ├── index.rst ├── make.bat └── settings.rst ├── example ├── example │ ├── __init__.py │ ├── items.py │ ├── pipelines.py │ ├── settings.py │ └── spiders │ │ ├── __init__.py │ │ └── custom_kafka_spider.py └── scrapy.cfg ├── requirements.txt ├── scrapy_kafka ├── __init__.py ├── pipelines.py └── spiders.py └── setup.py /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | 5 | # C extensions 6 | *.so 7 | 8 | # Distribution / packaging 9 | .Python 10 | env/ 11 | bin/ 12 | build/ 13 | develop-eggs/ 14 | dist/ 15 | eggs/ 16 | lib/ 17 | lib64/ 18 | parts/ 19 | sdist/ 20 | var/ 21 | _build 22 | *.egg-info/ 23 | .installed.cfg 24 | *.egg 25 | 26 | # Installer logs 27 | pip-log.txt 28 | pip-delete-this-directory.txt 29 | 30 | # Unit test / coverage reports 31 | htmlcov/ 32 | .tox/ 33 | .coverage 34 | .cache 35 | nosetests.xml 36 | coverage.xml 37 | 38 | # Translations 39 | *.mo 40 | 41 | # Mr Developer 42 | .mr.developer.cfg 43 | .project 44 | .pydevproject 45 | 46 | # Rope 47 | .ropeproject 48 | 49 | # Django stuff: 50 | *.log 51 | *.pot 52 | 53 | # Sphinx documentation 54 | docs/_build/ 55 | 56 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "{}" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright {yyyy} {name of copyright owner} 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. -------------------------------------------------------------------------------- /README.rst: -------------------------------------------------------------------------------- 1 | scrapy-kafka 2 | ============ 3 | 4 | Kafka-based components for Scrapy. There are 2 components: 5 | 6 | - A custom ``Spider`` that waits for URLs to crawl via a Kafka topic. When there are no more messages to read for the topic, the ``Spider`` just stays idle. 7 | - A custom ``ItemPipeline`` component that stores a JSON-ified ``Item`` back into another Kafka topic. 8 | 9 | Please see the `example`_ directory for how to use this. 10 | 11 | .. _example: https://github.com/dfdeshom/scrapy-kafka/tree/master/example 12 | 13 | Contributors 14 | ------------- 15 | Contributors to `scrapy-kafka`, listed alphabetically: 16 | 17 | * Matthew Daniel `@mdaniel`_ 18 | * Didier Deshommes `@dfdeshom`_ 19 | 20 | .. _@mdaniel: https://github.com/mdaniel 21 | .. _@dfdeshom: https://github.com/dfdeshom 22 | -------------------------------------------------------------------------------- /docs/Makefile: -------------------------------------------------------------------------------- 1 | # Makefile for Sphinx documentation 2 | # 3 | 4 | # You can set these variables from the command line. 5 | SPHINXOPTS = 6 | SPHINXBUILD = sphinx-build 7 | PAPER = 8 | BUILDDIR = _build 9 | 10 | # User-friendly check for sphinx-build 11 | ifeq ($(shell which $(SPHINXBUILD) >/dev/null 2>&1; echo $$?), 1) 12 | $(error The '$(SPHINXBUILD)' command was not found. Make sure you have Sphinx installed, then set the SPHINXBUILD environment variable to point to the full path of the '$(SPHINXBUILD)' executable. Alternatively you can add the directory with the executable to your PATH. If you don't have Sphinx installed, grab it from http://sphinx-doc.org/) 13 | endif 14 | 15 | # Internal variables. 16 | PAPEROPT_a4 = -D latex_paper_size=a4 17 | PAPEROPT_letter = -D latex_paper_size=letter 18 | ALLSPHINXOPTS = -d $(BUILDDIR)/doctrees $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) . 19 | # the i18n builder cannot share the environment and doctrees with the others 20 | I18NSPHINXOPTS = $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) . 21 | 22 | .PHONY: help clean html dirhtml singlehtml pickle json htmlhelp qthelp devhelp epub latex latexpdf text man changes linkcheck doctest gettext 23 | 24 | help: 25 | @echo "Please use \`make ' where is one of" 26 | @echo " html to make standalone HTML files" 27 | @echo " dirhtml to make HTML files named index.html in directories" 28 | @echo " singlehtml to make a single large HTML file" 29 | @echo " pickle to make pickle files" 30 | @echo " json to make JSON files" 31 | @echo " htmlhelp to make HTML files and a HTML help project" 32 | @echo " qthelp to make HTML files and a qthelp project" 33 | @echo " devhelp to make HTML files and a Devhelp project" 34 | @echo " epub to make an epub" 35 | @echo " latex to make LaTeX files, you can set PAPER=a4 or PAPER=letter" 36 | @echo " latexpdf to make LaTeX files and run them through pdflatex" 37 | @echo " latexpdfja to make LaTeX files and run them through platex/dvipdfmx" 38 | @echo " text to make text files" 39 | @echo " man to make manual pages" 40 | @echo " texinfo to make Texinfo files" 41 | @echo " info to make Texinfo files and run them through makeinfo" 42 | @echo " gettext to make PO message catalogs" 43 | @echo " changes to make an overview of all changed/added/deprecated items" 44 | @echo " xml to make Docutils-native XML files" 45 | @echo " pseudoxml to make pseudoxml-XML files for display purposes" 46 | @echo " linkcheck to check all external links for integrity" 47 | @echo " doctest to run all doctests embedded in the documentation (if enabled)" 48 | 49 | clean: 50 | rm -rf $(BUILDDIR)/* 51 | 52 | html: 53 | $(SPHINXBUILD) -b html $(ALLSPHINXOPTS) $(BUILDDIR)/html 54 | @echo 55 | @echo "Build finished. The HTML pages are in $(BUILDDIR)/html." 56 | 57 | dirhtml: 58 | $(SPHINXBUILD) -b dirhtml $(ALLSPHINXOPTS) $(BUILDDIR)/dirhtml 59 | @echo 60 | @echo "Build finished. The HTML pages are in $(BUILDDIR)/dirhtml." 61 | 62 | singlehtml: 63 | $(SPHINXBUILD) -b singlehtml $(ALLSPHINXOPTS) $(BUILDDIR)/singlehtml 64 | @echo 65 | @echo "Build finished. The HTML page is in $(BUILDDIR)/singlehtml." 66 | 67 | pickle: 68 | $(SPHINXBUILD) -b pickle $(ALLSPHINXOPTS) $(BUILDDIR)/pickle 69 | @echo 70 | @echo "Build finished; now you can process the pickle files." 71 | 72 | json: 73 | $(SPHINXBUILD) -b json $(ALLSPHINXOPTS) $(BUILDDIR)/json 74 | @echo 75 | @echo "Build finished; now you can process the JSON files." 76 | 77 | htmlhelp: 78 | $(SPHINXBUILD) -b htmlhelp $(ALLSPHINXOPTS) $(BUILDDIR)/htmlhelp 79 | @echo 80 | @echo "Build finished; now you can run HTML Help Workshop with the" \ 81 | ".hhp project file in $(BUILDDIR)/htmlhelp." 82 | 83 | qthelp: 84 | $(SPHINXBUILD) -b qthelp $(ALLSPHINXOPTS) $(BUILDDIR)/qthelp 85 | @echo 86 | @echo "Build finished; now you can run "qcollectiongenerator" with the" \ 87 | ".qhcp project file in $(BUILDDIR)/qthelp, like this:" 88 | @echo "# qcollectiongenerator $(BUILDDIR)/qthelp/scrapy-kafka.qhcp" 89 | @echo "To view the help file:" 90 | @echo "# assistant -collectionFile $(BUILDDIR)/qthelp/scrapy-kafka.qhc" 91 | 92 | devhelp: 93 | $(SPHINXBUILD) -b devhelp $(ALLSPHINXOPTS) $(BUILDDIR)/devhelp 94 | @echo 95 | @echo "Build finished." 96 | @echo "To view the help file:" 97 | @echo "# mkdir -p $$HOME/.local/share/devhelp/scrapy-kafka" 98 | @echo "# ln -s $(BUILDDIR)/devhelp $$HOME/.local/share/devhelp/scrapy-kafka" 99 | @echo "# devhelp" 100 | 101 | epub: 102 | $(SPHINXBUILD) -b epub $(ALLSPHINXOPTS) $(BUILDDIR)/epub 103 | @echo 104 | @echo "Build finished. The epub file is in $(BUILDDIR)/epub." 105 | 106 | latex: 107 | $(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex 108 | @echo 109 | @echo "Build finished; the LaTeX files are in $(BUILDDIR)/latex." 110 | @echo "Run \`make' in that directory to run these through (pdf)latex" \ 111 | "(use \`make latexpdf' here to do that automatically)." 112 | 113 | latexpdf: 114 | $(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex 115 | @echo "Running LaTeX files through pdflatex..." 116 | $(MAKE) -C $(BUILDDIR)/latex all-pdf 117 | @echo "pdflatex finished; the PDF files are in $(BUILDDIR)/latex." 118 | 119 | latexpdfja: 120 | $(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex 121 | @echo "Running LaTeX files through platex and dvipdfmx..." 122 | $(MAKE) -C $(BUILDDIR)/latex all-pdf-ja 123 | @echo "pdflatex finished; the PDF files are in $(BUILDDIR)/latex." 124 | 125 | text: 126 | $(SPHINXBUILD) -b text $(ALLSPHINXOPTS) $(BUILDDIR)/text 127 | @echo 128 | @echo "Build finished. The text files are in $(BUILDDIR)/text." 129 | 130 | man: 131 | $(SPHINXBUILD) -b man $(ALLSPHINXOPTS) $(BUILDDIR)/man 132 | @echo 133 | @echo "Build finished. The manual pages are in $(BUILDDIR)/man." 134 | 135 | texinfo: 136 | $(SPHINXBUILD) -b texinfo $(ALLSPHINXOPTS) $(BUILDDIR)/texinfo 137 | @echo 138 | @echo "Build finished. The Texinfo files are in $(BUILDDIR)/texinfo." 139 | @echo "Run \`make' in that directory to run these through makeinfo" \ 140 | "(use \`make info' here to do that automatically)." 141 | 142 | info: 143 | $(SPHINXBUILD) -b texinfo $(ALLSPHINXOPTS) $(BUILDDIR)/texinfo 144 | @echo "Running Texinfo files through makeinfo..." 145 | make -C $(BUILDDIR)/texinfo info 146 | @echo "makeinfo finished; the Info files are in $(BUILDDIR)/texinfo." 147 | 148 | gettext: 149 | $(SPHINXBUILD) -b gettext $(I18NSPHINXOPTS) $(BUILDDIR)/locale 150 | @echo 151 | @echo "Build finished. The message catalogs are in $(BUILDDIR)/locale." 152 | 153 | changes: 154 | $(SPHINXBUILD) -b changes $(ALLSPHINXOPTS) $(BUILDDIR)/changes 155 | @echo 156 | @echo "The overview file is in $(BUILDDIR)/changes." 157 | 158 | linkcheck: 159 | $(SPHINXBUILD) -b linkcheck $(ALLSPHINXOPTS) $(BUILDDIR)/linkcheck 160 | @echo 161 | @echo "Link check complete; look for any errors in the above output " \ 162 | "or in $(BUILDDIR)/linkcheck/output.txt." 163 | 164 | doctest: 165 | $(SPHINXBUILD) -b doctest $(ALLSPHINXOPTS) $(BUILDDIR)/doctest 166 | @echo "Testing of doctests in the sources finished, look at the " \ 167 | "results in $(BUILDDIR)/doctest/output.txt." 168 | 169 | xml: 170 | $(SPHINXBUILD) -b xml $(ALLSPHINXOPTS) $(BUILDDIR)/xml 171 | @echo 172 | @echo "Build finished. The XML files are in $(BUILDDIR)/xml." 173 | 174 | pseudoxml: 175 | $(SPHINXBUILD) -b pseudoxml $(ALLSPHINXOPTS) $(BUILDDIR)/pseudoxml 176 | @echo 177 | @echo "Build finished. The pseudo-XML files are in $(BUILDDIR)/pseudoxml." 178 | -------------------------------------------------------------------------------- /docs/api.rst: -------------------------------------------------------------------------------- 1 | API 2 | === 3 | 4 | KafkaPipeline object 5 | -------------------- 6 | .. automodule:: scrapy_kafka.pipelines 7 | :members: 8 | :inherited-members: 9 | 10 | ListeningKafkaSpider object 11 | --------------------------- 12 | .. autoclass:: scrapy_kafka.spiders.ListeningKafkaSpider 13 | :members: 14 | :inherited-members: 15 | -------------------------------------------------------------------------------- /docs/conf.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | # 3 | # scrapy-kafka documentation build configuration file, created by 4 | # sphinx-quickstart on Mon Aug 11 13:03:54 2014. 5 | # 6 | # This file is execfile()d with the current directory set to its 7 | # containing dir. 8 | # 9 | # Note that not all possible configuration values are present in this 10 | # autogenerated file. 11 | # 12 | # All configuration values have a default; values that are commented out 13 | # serve to show the default. 14 | 15 | import sys 16 | import os 17 | 18 | # If extensions (or modules to document with autodoc) are in another directory, 19 | # add these directories to sys.path here. If the directory is relative to the 20 | # documentation root, use os.path.abspath to make it absolute, like shown here. 21 | #sys.path.insert(0, os.path.abspath('.')) 22 | 23 | # -- General configuration ------------------------------------------------ 24 | 25 | # If your documentation needs a minimal Sphinx version, state it here. 26 | #needs_sphinx = '1.0' 27 | 28 | # Add any Sphinx extension module names here, as strings. They can be 29 | # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom 30 | # ones. 31 | extensions = [ 32 | 'sphinx.ext.autodoc', 33 | 'sphinx.ext.intersphinx', 34 | ] 35 | 36 | # Add any paths that contain templates here, relative to this directory. 37 | templates_path = ['_templates'] 38 | 39 | # The suffix of source filenames. 40 | source_suffix = '.rst' 41 | 42 | # The encoding of source files. 43 | #source_encoding = 'utf-8-sig' 44 | 45 | # The master toctree document. 46 | master_doc = 'index' 47 | 48 | # General information about the project. 49 | project = u'scrapy-kafka' 50 | copyright = u'2014, Didier Deshommes' 51 | 52 | # The version info for the project you're documenting, acts as replacement for 53 | # |version| and |release|, also used in various other places throughout the 54 | # built documents. 55 | # 56 | # The short X.Y version. 57 | version = '0.1.1' 58 | # The full version, including alpha/beta/rc tags. 59 | release = '0.1.1' 60 | 61 | # The language for content autogenerated by Sphinx. Refer to documentation 62 | # for a list of supported languages. 63 | #language = None 64 | 65 | # There are two options for replacing |today|: either, you set today to some 66 | # non-false value, then it is used: 67 | #today = '' 68 | # Else, today_fmt is used as the format for a strftime call. 69 | #today_fmt = '%B %d, %Y' 70 | 71 | # List of patterns, relative to source directory, that match files and 72 | # directories to ignore when looking for source files. 73 | exclude_patterns = ['_build'] 74 | 75 | # The reST default role (used for this markup: `text`) to use for all 76 | # documents. 77 | #default_role = None 78 | 79 | # If true, '()' will be appended to :func: etc. cross-reference text. 80 | #add_function_parentheses = True 81 | 82 | # If true, the current module name will be prepended to all description 83 | # unit titles (such as .. function::). 84 | #add_module_names = True 85 | 86 | # If true, sectionauthor and moduleauthor directives will be shown in the 87 | # output. They are ignored by default. 88 | #show_authors = False 89 | 90 | # The name of the Pygments (syntax highlighting) style to use. 91 | pygments_style = 'sphinx' 92 | 93 | # A list of ignored prefixes for module index sorting. 94 | #modindex_common_prefix = [] 95 | 96 | # If true, keep warnings as "system message" paragraphs in the built documents. 97 | #keep_warnings = False 98 | 99 | 100 | # -- Options for HTML output ---------------------------------------------- 101 | 102 | # The theme to use for HTML and HTML Help pages. See the documentation for 103 | # a list of builtin themes. 104 | html_theme = 'default' 105 | 106 | # Theme options are theme-specific and customize the look and feel of a theme 107 | # further. For a list of options available for each theme, see the 108 | # documentation. 109 | #html_theme_options = {} 110 | 111 | # Add any paths that contain custom themes here, relative to this directory. 112 | #html_theme_path = [] 113 | 114 | # The name for this set of Sphinx documents. If None, it defaults to 115 | # " v documentation". 116 | #html_title = None 117 | 118 | # A shorter title for the navigation bar. Default is the same as html_title. 119 | #html_short_title = None 120 | 121 | # The name of an image file (relative to this directory) to place at the top 122 | # of the sidebar. 123 | #html_logo = None 124 | 125 | # The name of an image file (within the static path) to use as favicon of the 126 | # docs. This file should be a Windows icon file (.ico) being 16x16 or 32x32 127 | # pixels large. 128 | #html_favicon = None 129 | 130 | # Add any paths that contain custom static files (such as style sheets) here, 131 | # relative to this directory. They are copied after the builtin static files, 132 | # so a file named "default.css" will overwrite the builtin "default.css". 133 | html_static_path = ['_static'] 134 | 135 | # Add any extra paths that contain custom files (such as robots.txt or 136 | # .htaccess) here, relative to this directory. These files are copied 137 | # directly to the root of the documentation. 138 | #html_extra_path = [] 139 | 140 | # If not '', a 'Last updated on:' timestamp is inserted at every page bottom, 141 | # using the given strftime format. 142 | #html_last_updated_fmt = '%b %d, %Y' 143 | 144 | # If true, SmartyPants will be used to convert quotes and dashes to 145 | # typographically correct entities. 146 | #html_use_smartypants = True 147 | 148 | # Custom sidebar templates, maps document names to template names. 149 | #html_sidebars = {} 150 | 151 | # Additional templates that should be rendered to pages, maps page names to 152 | # template names. 153 | #html_additional_pages = {} 154 | 155 | # If false, no module index is generated. 156 | #html_domain_indices = True 157 | 158 | # If false, no index is generated. 159 | #html_use_index = True 160 | 161 | # If true, the index is split into individual pages for each letter. 162 | #html_split_index = False 163 | 164 | # If true, links to the reST sources are added to the pages. 165 | #html_show_sourcelink = True 166 | 167 | # If true, "Created using Sphinx" is shown in the HTML footer. Default is True. 168 | #html_show_sphinx = True 169 | 170 | # If true, "(C) Copyright ..." is shown in the HTML footer. Default is True. 171 | #html_show_copyright = True 172 | 173 | # If true, an OpenSearch description file will be output, and all pages will 174 | # contain a tag referring to it. The value of this option must be the 175 | # base URL from which the finished HTML is served. 176 | #html_use_opensearch = '' 177 | 178 | # This is the file name suffix for HTML files (e.g. ".xhtml"). 179 | #html_file_suffix = None 180 | 181 | # Output file base name for HTML help builder. 182 | htmlhelp_basename = 'scrapy-kafkadoc' 183 | 184 | 185 | # -- Options for LaTeX output --------------------------------------------- 186 | 187 | latex_elements = { 188 | # The paper size ('letterpaper' or 'a4paper'). 189 | #'papersize': 'letterpaper', 190 | 191 | # The font size ('10pt', '11pt' or '12pt'). 192 | #'pointsize': '10pt', 193 | 194 | # Additional stuff for the LaTeX preamble. 195 | #'preamble': '', 196 | } 197 | 198 | # Grouping the document tree into LaTeX files. List of tuples 199 | # (source start file, target name, title, 200 | # author, documentclass [howto, manual, or own class]). 201 | latex_documents = [ 202 | ('index', 'scrapy-kafka.tex', u'scrapy-kafka Documentation', 203 | u'Didier Deshommes', 'manual'), 204 | ] 205 | 206 | # The name of an image file (relative to this directory) to place at the top of 207 | # the title page. 208 | #latex_logo = None 209 | 210 | # For "manual" documents, if this is true, then toplevel headings are parts, 211 | # not chapters. 212 | #latex_use_parts = False 213 | 214 | # If true, show page references after internal links. 215 | #latex_show_pagerefs = False 216 | 217 | # If true, show URL addresses after external links. 218 | #latex_show_urls = False 219 | 220 | # Documents to append as an appendix to all manuals. 221 | #latex_appendices = [] 222 | 223 | # If false, no module index is generated. 224 | #latex_domain_indices = True 225 | 226 | 227 | # -- Options for manual page output --------------------------------------- 228 | 229 | # One entry per manual page. List of tuples 230 | # (source start file, name, description, authors, manual section). 231 | man_pages = [ 232 | ('index', 'scrapy-kafka', u'scrapy-kafka Documentation', 233 | [u'Didier Deshommes'], 1) 234 | ] 235 | 236 | # If true, show URL addresses after external links. 237 | #man_show_urls = False 238 | 239 | 240 | # -- Options for Texinfo output ------------------------------------------- 241 | 242 | # Grouping the document tree into Texinfo files. List of tuples 243 | # (source start file, target name, title, author, 244 | # dir menu entry, description, category) 245 | texinfo_documents = [ 246 | ('index', 'scrapy-kafka', u'scrapy-kafka Documentation', 247 | u'Didier Deshommes', 'scrapy-kafka', 'One line description of project.', 248 | 'Miscellaneous'), 249 | ] 250 | 251 | # Documents to append as an appendix to all manuals. 252 | #texinfo_appendices = [] 253 | 254 | # If false, no module index is generated. 255 | #texinfo_domain_indices = True 256 | 257 | # How to display URL addresses: 'footnote', 'no', or 'inline'. 258 | #texinfo_show_urls = 'footnote' 259 | 260 | # If true, do not generate a @detailmenu in the "Top" node's menu. 261 | #texinfo_no_detailmenu = False 262 | 263 | 264 | # Example configuration for intersphinx: refer to the Python standard library. 265 | intersphinx_mapping = {'http://docs.python.org/': None} 266 | -------------------------------------------------------------------------------- /docs/index.rst: -------------------------------------------------------------------------------- 1 | .. scrapy-kafka documentation master file, created by 2 | sphinx-quickstart on Mon Aug 11 13:03:54 2014. 3 | You can adapt this file completely to your liking, but it should at least 4 | contain the root `toctree` directive. 5 | 6 | Welcome to scrapy-kafka 7 | ========================= 8 | 9 | Kafka-based components for Scrapy, to allow Spiders to read their next URL 10 | from a Kafka topic and an `ItemPipeline` to store the JSON-ified `Item` back 11 | into a Kafka topic. 12 | 13 | Contents: 14 | 15 | .. toctree:: 16 | :maxdepth: 2 17 | 18 | 19 | API reference 20 | -------------- 21 | .. toctree:: 22 | :maxdepth: 2 23 | 24 | api 25 | settings 26 | 27 | Indices and tables 28 | ================== 29 | 30 | * :ref:`genindex` 31 | * :ref:`modindex` 32 | * :ref:`search` 33 | 34 | -------------------------------------------------------------------------------- /docs/make.bat: -------------------------------------------------------------------------------- 1 | @ECHO OFF 2 | 3 | REM Command file for Sphinx documentation 4 | 5 | if "%SPHINXBUILD%" == "" ( 6 | set SPHINXBUILD=sphinx-build 7 | ) 8 | set BUILDDIR=_build 9 | set ALLSPHINXOPTS=-d %BUILDDIR%/doctrees %SPHINXOPTS% . 10 | set I18NSPHINXOPTS=%SPHINXOPTS% . 11 | if NOT "%PAPER%" == "" ( 12 | set ALLSPHINXOPTS=-D latex_paper_size=%PAPER% %ALLSPHINXOPTS% 13 | set I18NSPHINXOPTS=-D latex_paper_size=%PAPER% %I18NSPHINXOPTS% 14 | ) 15 | 16 | if "%1" == "" goto help 17 | 18 | if "%1" == "help" ( 19 | :help 20 | echo.Please use `make ^` where ^ is one of 21 | echo. html to make standalone HTML files 22 | echo. dirhtml to make HTML files named index.html in directories 23 | echo. singlehtml to make a single large HTML file 24 | echo. pickle to make pickle files 25 | echo. json to make JSON files 26 | echo. htmlhelp to make HTML files and a HTML help project 27 | echo. qthelp to make HTML files and a qthelp project 28 | echo. devhelp to make HTML files and a Devhelp project 29 | echo. epub to make an epub 30 | echo. latex to make LaTeX files, you can set PAPER=a4 or PAPER=letter 31 | echo. text to make text files 32 | echo. man to make manual pages 33 | echo. texinfo to make Texinfo files 34 | echo. gettext to make PO message catalogs 35 | echo. changes to make an overview over all changed/added/deprecated items 36 | echo. xml to make Docutils-native XML files 37 | echo. pseudoxml to make pseudoxml-XML files for display purposes 38 | echo. linkcheck to check all external links for integrity 39 | echo. doctest to run all doctests embedded in the documentation if enabled 40 | goto end 41 | ) 42 | 43 | if "%1" == "clean" ( 44 | for /d %%i in (%BUILDDIR%\*) do rmdir /q /s %%i 45 | del /q /s %BUILDDIR%\* 46 | goto end 47 | ) 48 | 49 | 50 | %SPHINXBUILD% 2> nul 51 | if errorlevel 9009 ( 52 | echo. 53 | echo.The 'sphinx-build' command was not found. Make sure you have Sphinx 54 | echo.installed, then set the SPHINXBUILD environment variable to point 55 | echo.to the full path of the 'sphinx-build' executable. Alternatively you 56 | echo.may add the Sphinx directory to PATH. 57 | echo. 58 | echo.If you don't have Sphinx installed, grab it from 59 | echo.http://sphinx-doc.org/ 60 | exit /b 1 61 | ) 62 | 63 | if "%1" == "html" ( 64 | %SPHINXBUILD% -b html %ALLSPHINXOPTS% %BUILDDIR%/html 65 | if errorlevel 1 exit /b 1 66 | echo. 67 | echo.Build finished. The HTML pages are in %BUILDDIR%/html. 68 | goto end 69 | ) 70 | 71 | if "%1" == "dirhtml" ( 72 | %SPHINXBUILD% -b dirhtml %ALLSPHINXOPTS% %BUILDDIR%/dirhtml 73 | if errorlevel 1 exit /b 1 74 | echo. 75 | echo.Build finished. The HTML pages are in %BUILDDIR%/dirhtml. 76 | goto end 77 | ) 78 | 79 | if "%1" == "singlehtml" ( 80 | %SPHINXBUILD% -b singlehtml %ALLSPHINXOPTS% %BUILDDIR%/singlehtml 81 | if errorlevel 1 exit /b 1 82 | echo. 83 | echo.Build finished. The HTML pages are in %BUILDDIR%/singlehtml. 84 | goto end 85 | ) 86 | 87 | if "%1" == "pickle" ( 88 | %SPHINXBUILD% -b pickle %ALLSPHINXOPTS% %BUILDDIR%/pickle 89 | if errorlevel 1 exit /b 1 90 | echo. 91 | echo.Build finished; now you can process the pickle files. 92 | goto end 93 | ) 94 | 95 | if "%1" == "json" ( 96 | %SPHINXBUILD% -b json %ALLSPHINXOPTS% %BUILDDIR%/json 97 | if errorlevel 1 exit /b 1 98 | echo. 99 | echo.Build finished; now you can process the JSON files. 100 | goto end 101 | ) 102 | 103 | if "%1" == "htmlhelp" ( 104 | %SPHINXBUILD% -b htmlhelp %ALLSPHINXOPTS% %BUILDDIR%/htmlhelp 105 | if errorlevel 1 exit /b 1 106 | echo. 107 | echo.Build finished; now you can run HTML Help Workshop with the ^ 108 | .hhp project file in %BUILDDIR%/htmlhelp. 109 | goto end 110 | ) 111 | 112 | if "%1" == "qthelp" ( 113 | %SPHINXBUILD% -b qthelp %ALLSPHINXOPTS% %BUILDDIR%/qthelp 114 | if errorlevel 1 exit /b 1 115 | echo. 116 | echo.Build finished; now you can run "qcollectiongenerator" with the ^ 117 | .qhcp project file in %BUILDDIR%/qthelp, like this: 118 | echo.^> qcollectiongenerator %BUILDDIR%\qthelp\scrapy-kafka.qhcp 119 | echo.To view the help file: 120 | echo.^> assistant -collectionFile %BUILDDIR%\qthelp\scrapy-kafka.ghc 121 | goto end 122 | ) 123 | 124 | if "%1" == "devhelp" ( 125 | %SPHINXBUILD% -b devhelp %ALLSPHINXOPTS% %BUILDDIR%/devhelp 126 | if errorlevel 1 exit /b 1 127 | echo. 128 | echo.Build finished. 129 | goto end 130 | ) 131 | 132 | if "%1" == "epub" ( 133 | %SPHINXBUILD% -b epub %ALLSPHINXOPTS% %BUILDDIR%/epub 134 | if errorlevel 1 exit /b 1 135 | echo. 136 | echo.Build finished. The epub file is in %BUILDDIR%/epub. 137 | goto end 138 | ) 139 | 140 | if "%1" == "latex" ( 141 | %SPHINXBUILD% -b latex %ALLSPHINXOPTS% %BUILDDIR%/latex 142 | if errorlevel 1 exit /b 1 143 | echo. 144 | echo.Build finished; the LaTeX files are in %BUILDDIR%/latex. 145 | goto end 146 | ) 147 | 148 | if "%1" == "latexpdf" ( 149 | %SPHINXBUILD% -b latex %ALLSPHINXOPTS% %BUILDDIR%/latex 150 | cd %BUILDDIR%/latex 151 | make all-pdf 152 | cd %BUILDDIR%/.. 153 | echo. 154 | echo.Build finished; the PDF files are in %BUILDDIR%/latex. 155 | goto end 156 | ) 157 | 158 | if "%1" == "latexpdfja" ( 159 | %SPHINXBUILD% -b latex %ALLSPHINXOPTS% %BUILDDIR%/latex 160 | cd %BUILDDIR%/latex 161 | make all-pdf-ja 162 | cd %BUILDDIR%/.. 163 | echo. 164 | echo.Build finished; the PDF files are in %BUILDDIR%/latex. 165 | goto end 166 | ) 167 | 168 | if "%1" == "text" ( 169 | %SPHINXBUILD% -b text %ALLSPHINXOPTS% %BUILDDIR%/text 170 | if errorlevel 1 exit /b 1 171 | echo. 172 | echo.Build finished. The text files are in %BUILDDIR%/text. 173 | goto end 174 | ) 175 | 176 | if "%1" == "man" ( 177 | %SPHINXBUILD% -b man %ALLSPHINXOPTS% %BUILDDIR%/man 178 | if errorlevel 1 exit /b 1 179 | echo. 180 | echo.Build finished. The manual pages are in %BUILDDIR%/man. 181 | goto end 182 | ) 183 | 184 | if "%1" == "texinfo" ( 185 | %SPHINXBUILD% -b texinfo %ALLSPHINXOPTS% %BUILDDIR%/texinfo 186 | if errorlevel 1 exit /b 1 187 | echo. 188 | echo.Build finished. The Texinfo files are in %BUILDDIR%/texinfo. 189 | goto end 190 | ) 191 | 192 | if "%1" == "gettext" ( 193 | %SPHINXBUILD% -b gettext %I18NSPHINXOPTS% %BUILDDIR%/locale 194 | if errorlevel 1 exit /b 1 195 | echo. 196 | echo.Build finished. The message catalogs are in %BUILDDIR%/locale. 197 | goto end 198 | ) 199 | 200 | if "%1" == "changes" ( 201 | %SPHINXBUILD% -b changes %ALLSPHINXOPTS% %BUILDDIR%/changes 202 | if errorlevel 1 exit /b 1 203 | echo. 204 | echo.The overview file is in %BUILDDIR%/changes. 205 | goto end 206 | ) 207 | 208 | if "%1" == "linkcheck" ( 209 | %SPHINXBUILD% -b linkcheck %ALLSPHINXOPTS% %BUILDDIR%/linkcheck 210 | if errorlevel 1 exit /b 1 211 | echo. 212 | echo.Link check complete; look for any errors in the above output ^ 213 | or in %BUILDDIR%/linkcheck/output.txt. 214 | goto end 215 | ) 216 | 217 | if "%1" == "doctest" ( 218 | %SPHINXBUILD% -b doctest %ALLSPHINXOPTS% %BUILDDIR%/doctest 219 | if errorlevel 1 exit /b 1 220 | echo. 221 | echo.Testing of doctests in the sources finished, look at the ^ 222 | results in %BUILDDIR%/doctest/output.txt. 223 | goto end 224 | ) 225 | 226 | if "%1" == "xml" ( 227 | %SPHINXBUILD% -b xml %ALLSPHINXOPTS% %BUILDDIR%/xml 228 | if errorlevel 1 exit /b 1 229 | echo. 230 | echo.Build finished. The XML files are in %BUILDDIR%/xml. 231 | goto end 232 | ) 233 | 234 | if "%1" == "pseudoxml" ( 235 | %SPHINXBUILD% -b pseudoxml %ALLSPHINXOPTS% %BUILDDIR%/pseudoxml 236 | if errorlevel 1 exit /b 1 237 | echo. 238 | echo.Build finished. The pseudo-XML files are in %BUILDDIR%/pseudoxml. 239 | goto end 240 | ) 241 | 242 | :end 243 | -------------------------------------------------------------------------------- /docs/settings.rst: -------------------------------------------------------------------------------- 1 | ======== 2 | Settings 3 | ======== 4 | 5 | 6 | SCRAPY_KAFKA_HOSTS 7 | ------------------- 8 | 9 | Default: `['localhost:9092']` 10 | 11 | The Kafka hosts. 12 | 13 | 14 | SCRAPY_KAFKA_ITEM_PIPELINE_TOPIC 15 | ---------------------------------- 16 | 17 | Default: `scrapy_kafka_item` 18 | 19 | The Kafka topic to post processed items from the pipeline to. 20 | 21 | 22 | SCRAPY_KAFKA_SPIDER_CONSUMER_GROUP 23 | ----------------------------------- 24 | 25 | Default : `scrapy-kafka` 26 | 27 | The Kafka consumer group a :class:`~scrapy_kafka.spiders.ListeningKafkaSpider` belongs to. 28 | 29 | 30 | 31 | -------------------------------------------------------------------------------- /example/example/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dfdeshom/scrapy-kafka/a1e401f8dc96c67801d80d3da612db60b6f1fc80/example/example/__init__.py -------------------------------------------------------------------------------- /example/example/items.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | 3 | # Define here the models for your scraped items 4 | # 5 | # See documentation in: 6 | # http://doc.scrapy.org/en/latest/topics/items.html 7 | 8 | import scrapy 9 | 10 | 11 | class DmozItem(scrapy.Item): 12 | title = scrapy.Field() 13 | link = scrapy.Field() 14 | desc = scrapy.Field() 15 | -------------------------------------------------------------------------------- /example/example/pipelines.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | 3 | # Define your item pipelines here 4 | # 5 | # Don't forget to add your pipeline to the ITEM_PIPELINES setting 6 | # See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html 7 | 8 | 9 | class ExamplePipeline(object): 10 | def process_item(self, item, spider): 11 | return item 12 | -------------------------------------------------------------------------------- /example/example/settings.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | 3 | # Scrapy settings for example project 4 | # 5 | # For simplicity, this file contains only the most important settings by 6 | # default. All the other settings are documented here: 7 | # 8 | # http://doc.scrapy.org/en/latest/topics/settings.html 9 | # 10 | 11 | BOT_NAME = 'example' 12 | 13 | SPIDER_MODULES = ['example.spiders'] 14 | NEWSPIDER_MODULE = SPIDER_MODULES[0] 15 | ITEM_PIPELINES = { 16 | 'example.pipelines.ExamplePipeline': 102, 17 | 'scrapy_kafka.pipelines.KafkaPipeline': 103, 18 | } 19 | 20 | # scrapy-kafka settings 21 | SCRAPY_KAFKA_HOSTS = ['localhost:9092'] 22 | SCRAPY_KAFKA_SPIDER_CONSUMER_GROUP = 'scrapy-kafka' 23 | 24 | # Crawl responsibly by identifying yourself (and your website) on the user-agent 25 | # USER_AGENT = 'example (+http://www.yourdomain.com)' 26 | -------------------------------------------------------------------------------- /example/example/spiders/__init__.py: -------------------------------------------------------------------------------- 1 | # This package will contain the spiders of your Scrapy project 2 | # 3 | # Please refer to the documentation for information on how to create and manage 4 | # your spiders. 5 | -------------------------------------------------------------------------------- /example/example/spiders/custom_kafka_spider.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | from scrapy_kafka.spiders import ListeningKafkaSpider 3 | from ..items import DmozItem 4 | 5 | 6 | class CustomKafkaSpider(ListeningKafkaSpider): 7 | name = "dmoz_kafka" 8 | allowed_domains = ["dmoz.org"] 9 | 10 | def parse(self, response): 11 | for sel in response.xpath('//ul/li'): 12 | item = DmozItem() 13 | item['title'] = sel.xpath('a/text()').extract() 14 | item['link'] = sel.xpath('a/@href').extract() 15 | item['desc'] = sel.xpath('text()').extract() 16 | yield item 17 | -------------------------------------------------------------------------------- /example/scrapy.cfg: -------------------------------------------------------------------------------- 1 | # Automatically created by: scrapy startproject 2 | # 3 | # For more information about the [deploy] section see: 4 | # http://doc.scrapy.org/en/latest/topics/scrapyd.html 5 | 6 | [settings] 7 | default = example.settings 8 | 9 | [deploy] 10 | #url = http://localhost:6800/ 11 | project = example 12 | -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | Scrapy >= 0.24.2 2 | kafka-python >= 0.9.1 3 | -------------------------------------------------------------------------------- /scrapy_kafka/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dfdeshom/scrapy-kafka/a1e401f8dc96c67801d80d3da612db60b6f1fc80/scrapy_kafka/__init__.py -------------------------------------------------------------------------------- /scrapy_kafka/pipelines.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | from scrapy.utils.serialize import ScrapyJSONEncoder 3 | 4 | from kafka.client import KafkaClient 5 | from kafka.producer import SimpleProducer 6 | 7 | 8 | class KafkaPipeline(object): 9 | 10 | """ 11 | Publishes a serialized item into a Kafka topic 12 | 13 | :param producer: The Kafka producer 14 | :type producer: kafka.producer.Producer 15 | 16 | :param topic: The Kafka topic being used 17 | :type topic: str or unicode 18 | 19 | """ 20 | 21 | def __init__(self, producer, topic): 22 | """ 23 | :type producer: kafka.producer.Producer 24 | :type topic: str or unicode 25 | """ 26 | self.producer = producer 27 | self.topic = topic 28 | 29 | self.encoder = ScrapyJSONEncoder() 30 | 31 | def process_item(self, item, spider): 32 | """ 33 | Overriden method to process the item 34 | 35 | :param item: Item being passed 36 | :type item: scrapy.item.Item 37 | 38 | :param spider: The current spider being used 39 | :type spider: scrapy.spider.Spider 40 | """ 41 | # put spider name in item 42 | item = dict(item) 43 | item['spider'] = spider.name 44 | msg = self.encoder.encode(item) 45 | self.producer.send_messages(self.topic, msg) 46 | 47 | @classmethod 48 | def from_settings(cls, settings): 49 | """ 50 | :param settings: the current Scrapy settings 51 | :type settings: scrapy.settings.Settings 52 | 53 | :rtype: A :class:`~KafkaPipeline` instance 54 | """ 55 | k_hosts = settings.get('SCRAPY_KAFKA_HOSTS', ['localhost:9092']) 56 | topic = settings.get('SCRAPY_KAFKA_ITEM_PIPELINE_TOPIC', 'scrapy_kafka_item') 57 | kafka = KafkaClient(k_hosts) 58 | conn = SimpleProducer(kafka) 59 | return cls(conn, topic) 60 | -------------------------------------------------------------------------------- /scrapy_kafka/spiders.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | from scrapy import signals 3 | from scrapy.exceptions import DontCloseSpider 4 | from scrapy.spiders import Spider 5 | 6 | from kafka.client import KafkaClient 7 | from kafka.consumer import SimpleConsumer 8 | 9 | 10 | class KafkaSpiderMixin(object): 11 | 12 | """ 13 | Mixin class to implement reading urls from a kafka queue. 14 | 15 | :type kafka_topic: str 16 | """ 17 | kafka_topic = None 18 | 19 | def process_kafka_message(self, message): 20 | """" 21 | Tell this spider how to extract urls from a kafka message 22 | 23 | :param message: A Kafka message object 24 | :type message: kafka.common.OffsetAndMessage 25 | :rtype: str or None 26 | """ 27 | if not message: 28 | return None 29 | 30 | return message.message.value 31 | 32 | def setup_kafka(self, settings): 33 | """Setup redis connection and idle signal. 34 | 35 | This should be called after the spider has set its crawler object. 36 | 37 | :param settings: The current Scrapy settings being used 38 | :type settings: scrapy.settings.Settings 39 | """ 40 | if not hasattr(self, 'topic') or not self.topic: 41 | self.topic = '%s-starturls' % self.name 42 | 43 | hosts = settings.get('SCRAPY_KAFKA_HOSTS', ['localhost:9092']) 44 | consumer_group = settings.get('SCRAPY_KAFKA_SPIDER_CONSUMER_GROUP', 'scrapy-kafka') 45 | _kafka = KafkaClient(hosts) 46 | # wait at most 1sec for more messages. Otherwise continue 47 | self.consumer = SimpleConsumer(_kafka, consumer_group, self.topic, 48 | auto_commit=True, iter_timeout=1.0) 49 | # idle signal is called when the spider has no requests left, 50 | # that's when we will schedule new requests from kafka topic 51 | self.crawler.signals.connect(self.spider_idle, signal=signals.spider_idle) 52 | self.crawler.signals.connect(self.item_scraped, signal=signals.item_scraped) 53 | self.log("Reading URLs from kafka topic '%s'" % self.kafka_topic) 54 | 55 | def next_request(self): 56 | """ 57 | Returns a request to be scheduled. 58 | 59 | :rtype: str or None 60 | """ 61 | message = self.consumer.get_message(True) 62 | url = self.process_kafka_message(message) 63 | if not url: 64 | return None 65 | return self.make_requests_from_url(url) 66 | 67 | def schedule_next_request(self): 68 | """Schedules a request if available""" 69 | req = self.next_request() 70 | if req: 71 | self.crawler.engine.crawl(req, spider=self) 72 | 73 | def spider_idle(self): 74 | """Schedules a request if available, otherwise waits.""" 75 | self.schedule_next_request() 76 | raise DontCloseSpider 77 | 78 | def item_scraped(self, *args, **kwargs): 79 | """Avoids waiting for the spider to idle before scheduling the next request""" 80 | self.schedule_next_request() 81 | 82 | 83 | class ListeningKafkaSpider(KafkaSpiderMixin, Spider): 84 | 85 | """ 86 | Spider that reads urls from a kafka topic when idle. 87 | 88 | This spider will exit only if stopped, otherwise it keeps 89 | listening to messages on the given topic 90 | 91 | Specify the topic to listen to by setting the spider's `kafka_topic`. 92 | 93 | Messages are assumed to be URLS, one by message. To do custom 94 | processing of kafka messages, override the spider's `process_kafka_message` 95 | method 96 | """ 97 | 98 | def _set_crawler(self, crawler): 99 | """ 100 | :type crawler: scrapy.crawler.Crawler 101 | """ 102 | super(ListeningKafkaSpider, self)._set_crawler(crawler) 103 | self.setup_kafka(crawler.settings) 104 | -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- 1 | import os 2 | from pkg_resources import parse_requirements 3 | from setuptools import setup 4 | 5 | MY_DIR = os.path.dirname(__file__) 6 | LONG_DESC = open(os.path.join(MY_DIR, 'README.rst')).read() 7 | req_fh = open(os.path.join(MY_DIR, 'requirements.txt')) 8 | install_requirements = [str(r) for r in parse_requirements(req_fh)] 9 | req_fh.close() 10 | 11 | setup(name='scrapy-kafka', 12 | version='0.1.1', 13 | description='Kafka-based components for Scrapy', 14 | long_description=LONG_DESC, 15 | author='Didier Deshommes', 16 | author_email='dfdeshom@gmail.com', 17 | url='https://github.com/dfdeshom/scrapy-kafka', 18 | packages=['scrapy_kafka'], 19 | license='BSD', 20 | install_requires=install_requirements, 21 | extras_require={ 22 | "docs": ['sphinx'], 23 | }, 24 | dependency_links=[ 25 | 'https://github.com/mumrah/kafka-python/archive/v0.9.1.tar.gz#egg=kafka-python-0.9.1', 26 | ], 27 | classifiers=[ 28 | 'Programming Language :: Python', 29 | 'Development Status :: 4 - Beta', 30 | 'Intended Audience :: Developers', 31 | ]) 32 | --------------------------------------------------------------------------------