Makefile tox

.gitignore

@@ -8,12 +8,13 @@ wechatsogou/ocr
 sprider
 wechatsogou.egg-info
 dist
-demo/yu_save.py
-demo/wechatsogou
 demo
 log.txt
 web
 wechatid.txt
 .DS_Store
 test/config.py
-.python-version
+.python-version
+*.pyc
+.tox/
+build/

.travis.yml

@@ -1,7 +1,9 @@
 language: python
 
 python:
-- 3.6
+  - "2.7.12"
+  - "3.5.3"
+  - "3.6.1"
 
 cache:
   directories:
@@ -13,10 +15,18 @@ env:
     - PIP_FIND_LINKS=file://$HOME/.cache/pip/wheels
 
 install:
+  - pip install tox tox-travis flake8
   - pip install -r requirements.txt
 
 before_script:
   - export PYTHONPATH=$PYTHONPATH:$(pwd)
 
 script:
-  - python -m nose -vs
+  - make flake8
+  - make dry_publish
+  - tox
+
+notifications:
+  email:
+    on_success: never
+    on_failure: never

MANIFEST.in

@@ -1,10 +1,2 @@
 include LICENSE
-include README.rst
-include MANIFEST.in
-recursive-include * Makefile
-recursive-include * make.bat
-recursive-include test *
-recursive-include demo *
-recursive-exclude * __pycache__
-recursive-exclude screenshot *
-
+graft docs

Makefile

@@ -0,0 +1,23 @@
+.PHONY: rst dry_publish
+
+docdir = docs
+rst:
+	if [ -a $(docdir)/README.rst ]; then rm $(docdir)/README.rst; fi;
+	pandoc --from=markdown --to=rst --output=$(docdir)/README.rst README.md
+	if [ -a $(docdir)/HISTORY.rst ]; then rm $(docdir)/HISTORY.rst; fi;
+	pandoc --from=markdown --to=rst --output=$(docdir)/HISTORY.rst CHANGELOG.md
+	python setup.py check --restructuredtext
+
+dry_publish:
+	rm -rf dist/ build/
+	python setup.py sdist bdist_wheel
+
+flake8:
+	flake8 --ignore=E501,F401,E128,E402,E731,F821 wechatsogou
+
+tox:
+	pyenv local 2.7.12 3.5.3 3.6.1
+	tox
+
+clean:
+	@rm -rf build/ wechatsogou.egg-info/ dist/

docs/HISTORY.rst

@@ -0,0 +1,111 @@
+Change Log
+==========
+
+`Unreleased <https://github.com/Chyroc/WechatSogou/tree/HEAD>`__
+----------------------------------------------------------------
+
+`Full
+Changelog <https://github.com/Chyroc/WechatSogou/compare/v2.0.3...HEAD>`__
+
+**Closed issues:**
+
+-  微信搜索公众号结果模版改变了
+   `#51 <https://github.com/Chyroc/WechatSogou/issues/51>`__
+-  ImportError: cannot import name config
+   `#40 <https://github.com/Chyroc/WechatSogou/issues/40>`__
+
+`v2.0.3 <https://github.com/Chyroc/WechatSogou/tree/v2.0.3>`__ (2016-12-18)
+---------------------------------------------------------------------------
+
+**Closed issues:**
+
+-  引入模块的时候报错
+   `#33 <https://github.com/Chyroc/WechatSogou/issues/33>`__
+-  导入文件后有bug
+   `#31 <https://github.com/Chyroc/WechatSogou/issues/31>`__
+-  请问如何设置代理
+   `#27 <https://github.com/Chyroc/WechatSogou/issues/27>`__
+-  请问最近搜狗返回的Html内容是改了吗？最近抓内容出错。
+   `#25 <https://github.com/Chyroc/WechatSogou/issues/25>`__
+-  结果模版更新了
+   `#24 <https://github.com/Chyroc/WechatSogou/issues/24>`__
+-  文章标题带引号（"，&quot）的情况解析报错
+   `#23 <https://github.com/Chyroc/WechatSogou/issues/23>`__
+-  请问，我运行test.py时为何没报错却没得到任何结果？
+   `#21 <https://github.com/Chyroc/WechatSogou/issues/21>`__
+-  如何获得公众号的id和名称？
+   `#20 <https://github.com/Chyroc/WechatSogou/issues/20>`__
+-  search\_gzh\_info无法取得内容
+   `#18 <https://github.com/Chyroc/WechatSogou/issues/18>`__
+-  原始文章url `#17 <https://github.com/Chyroc/WechatSogou/issues/17>`__
+-  请问在Linux下可以使用吗？我运行了一下出现如下问题，还望指教
+   `#16 <https://github.com/Chyroc/WechatSogou/issues/16>`__
+-  log怎么使用？
+   `#15 <https://github.com/Chyroc/WechatSogou/issues/15>`__
+-  抓取数据有时成功，有时失败
+   `#14 <https://github.com/Chyroc/WechatSogou/issues/14>`__
+-  验证码打开失败问题原因是：
+   `#13 <https://github.com/Chyroc/WechatSogou/issues/13>`__
+-  验证码输入后失败
+   `#12 <https://github.com/Chyroc/WechatSogou/issues/12>`__
+-  获得的文章链接，如果打开需要验证码输入才跳转
+   `#11 <https://github.com/Chyroc/WechatSogou/issues/11>`__
+-  获取文章只能10篇？
+   `#10 <https://github.com/Chyroc/WechatSogou/issues/10>`__
+-  搜狗平台问题 `#9 <https://github.com/Chyroc/WechatSogou/issues/9>`__
+-  deal\_article\_comment(text=text)并不能获得用户的评论内容
+   `#8 <https://github.com/Chyroc/WechatSogou/issues/8>`__
+-  py2.7 什么时候支持？
+   `#7 <https://github.com/Chyroc/WechatSogou/issues/7>`__
+-  PIL is not support Python3
+   `#6 <https://github.com/Chyroc/WechatSogou/issues/6>`__
+-  演示代码wechats.get\_gzh\_article\_by\_url\_dict(wechat\_info['url'])提示list
+   index out of range
+   `#5 <https://github.com/Chyroc/WechatSogou/issues/5>`__
+-  如何使用代理 `#2 <https://github.com/Chyroc/WechatSogou/issues/2>`__
+-  使用的是 python3 吗？
+   `#1 <https://github.com/Chyroc/WechatSogou/issues/1>`__
+
+**Merged pull requests:**
+
+-  fix for ci `#50 <https://github.com/Chyroc/WechatSogou/pull/50>`__
+   (`Chyroc <https://github.com/Chyroc>`__)
+-  add readme.rst
+   `#48 <https://github.com/Chyroc/WechatSogou/pull/48>`__
+   (`Chyroc <https://github.com/Chyroc>`__)
+-  添加安装说明 `#47 <https://github.com/Chyroc/WechatSogou/pull/47>`__
+   (`Chyroc <https://github.com/Chyroc>`__)
+-  upload to pypi
+   `#46 <https://github.com/Chyroc/WechatSogou/pull/46>`__
+   (`Chyroc <https://github.com/Chyroc>`__)
+-  add `#45 <https://github.com/Chyroc/WechatSogou/pull/45>`__
+   (`Chyroc <https://github.com/Chyroc>`__)
+-  Add/api test `#44 <https://github.com/Chyroc/WechatSogou/pull/44>`__
+   (`Chyroc <https://github.com/Chyroc>`__)
+-  Fix/re ocr for get gzh article by url text
+   `#43 <https://github.com/Chyroc/WechatSogou/pull/43>`__
+   (`Chyroc <https://github.com/Chyroc>`__)
+-  修复首页热门获取单页
+   `#42 <https://github.com/Chyroc/WechatSogou/pull/42>`__
+   (`Chyroc <https://github.com/Chyroc>`__)
+-  Fix/search article info
+   `#41 <https://github.com/Chyroc/WechatSogou/pull/41>`__
+   (`Chyroc <https://github.com/Chyroc>`__)
+-  Add/readme zanshu
+   `#39 <https://github.com/Chyroc/WechatSogou/pull/39>`__
+   (`Chyroc <https://github.com/Chyroc>`__)
+-  Fix/test ruokuai
+   `#38 <https://github.com/Chyroc/WechatSogou/pull/38>`__
+   (`Chyroc <https://github.com/Chyroc>`__)
+-  Feature/test ruokuai
+   `#37 <https://github.com/Chyroc/WechatSogou/pull/37>`__
+   (`Chyroc <https://github.com/Chyroc>`__)
+-  Feature/update version
+   `#35 <https://github.com/Chyroc/WechatSogou/pull/35>`__
+   (`Chyroc <https://github.com/Chyroc>`__)
+-  add requirements.txt
+   `#34 <https://github.com/Chyroc/WechatSogou/pull/34>`__
+   (`Chyroc <https://github.com/Chyroc>`__)
+
+\* *This Change Log was automatically generated by
+`github\_changelog\_generator <https://github.com/skywinder/Github-Changelog-Generator>`__*

README.rst → docs/README.rst

@@ -1,7 +1,7 @@
 基于搜狗微信搜索的微信公众号爬虫接口
 ====================================
 
-|py27| |py35|
+|Build Status| |PyPI version| |py36|
 
 项目简介
 ========
@@ -17,6 +17,7 @@
 
 赞助作者
 ========
+
 甲鱼说，咖啡是灵魂的饮料，买点咖啡
 
 谢谢：
@@ -421,6 +422,9 @@ TODO
 
 --------------
 
-.. |py27| image:: https://camo.githubusercontent.com/392a32588691a8418368a51ff33a12d41f11f0a9/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f707974686f6e2d322e372d6666363962342e737667
-.. |py35| image:: https://camo.githubusercontent.com/633acad03f4dbbaa8cca6bee5902207fd3b27a34/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f707974686f6e2d332e352d7265642e737667
-
+.. |Build Status| image:: https://travis-ci.org/Chyroc/WechatSogou.svg?branch=master
+   :target: https://github.com/Chyroc/WechatSogou
+.. |PyPI version| image:: https://badge.fury.io/py/wechatsogou.svg
+   :target: https://github.com/Chyroc/WechatSogou
+.. |py36| image:: https://img.shields.io/pypi/pyversions/wechatsogou.svg
+   :target: https://github.com/Chyroc/WechatSogou

requirements.txt

@@ -1,10 +1,7 @@
-Flask==0.12.2
+future==0.16.0
 lxml==3.7.3
-MarkupSafe==1.0
-nose==1.3.7
 Pillow==4.1.1
 requests==2.14.2
 six==1.10.0
 Werkzeug==0.12.2
 xlrd==1.0.0
-zope.interface==4.4.1

setup.cfg

@@ -0,0 +1,2 @@
+[bdist_wheel]
+universal = 1

setup.py

@@ -1,35 +1,43 @@
-# -*- coding: utf-8 -*-
+import codecs
+from setuptools import setup
 
-from setuptools import setup, find_packages
-from codecs import open
-from os import path
 import wechatsogou
 
-here = path.abspath(path.dirname(__file__))
-
-with open(path.join(here, 'README.rst'), encoding='utf-8') as f:
-    long_description = f.read()
+readme = codecs.open('docs/README.rst', encoding='utf-8').read()
+history = codecs.open('docs/HISTORY.rst', encoding='utf-8').read()
 
 setup(
     name='wechatsogou',
-
     version=wechatsogou.__version__,
-
-    description='api for wechat mp with sogou.',
-    long_description=long_description,
-
-    url='https://github.com/Chyroc/WechatSogou',
-
-    author='Chyroc Chen',
+    description='Api for wechat mp with sogou',
+    long_description=u'\n\n'.join([readme, history]),
+    author='Chyroc',
     author_email='[email protected]',
-
-    license='MIT',
-
-    keywords='python web wechat sogou api weixin',
-
-    packages=find_packages(),
-
-    install_requires=['requests'],
-
-    extras_require={},
-)
+    url='https://github.com/Chyroc/WechatSogou',
+    packages=[
+        'wechatsogou',
+    ],
+    setup_requires=[
+        # minimum version to use environment markers
+        'setuptools>=20.6.8',
+    ],
+    install_requires=[
+        'future', 'lxml', 'Pillow', 'requests', 'six', 'Werkzeug', 'xlrd'
+    ],
+    include_package_data=True,
+    license='MIT License',
+    classifiers=[
+        'Intended Audience :: Developers',
+        'License :: OSI Approved :: MIT License',
+        'Operating System :: MacOS :: MacOS X',
+        'Operating System :: Microsoft :: Windows',
+        'Operating System :: POSIX',
+        'Programming Language :: Python',
+        'Programming Language :: Python :: 2.7.12',
+        'Programming Language :: Python :: 3.5.3',
+        'Programming Language :: Python :: 3.6.1',
+        'Topic :: Software Development :: Libraries :: Python Modules',
+        'Programming Language :: Python :: Implementation :: PyPy',
+        'Programming Language :: Python :: Implementation :: CPython',
+    ],
+)

test/TestTools.py

@@ -1,3 +1,5 @@
+# -*- coding: utf-8 -*-
+
 import unittest
 from nose.tools import assert_raises, assert_equal
 

test/__init__.py

@@ -0,0 +1 @@
+# -*- coding: utf-8 -*-

tox.ini

@@ -0,0 +1,15 @@
+[tox]
+envlist = py27,py35,py36
+
+[testenv]
+deps=
+    setuptools==34.3.1
+    requests
+    lxml
+    future
+    Pillow
+    Werkzeug
+    nose
+commands =
+    #python setup.py test
+    python -m nose -vs

wechatsogou/api.py

@@ -1,7 +1,6 @@
 # -*- coding: utf-8 -*-
 
 import re
-import time
 import logging
 
 import requests
@@ -338,9 +337,8 @@ def deal_article_comment(self, **kwargs):
         sg_data = re.findall(u'window.sg_data={(.*?)}', text, re.S)
         sg_data = '{' + sg_data[0].replace(u'\r\n', '').replace(' ', '') + '}'
         sg_data = re.findall(u'{src:"(.*?)",ver:"(.*?)",timestamp:"(.*?)",signature:"(.*?)"}', sg_data)[0]
-        comment_req_url = 'http://mp.weixin.qq.com/mp/getcomment?src=' + sg_data[0] + '&ver=' + sg_data[
-            1] + '&timestamp=' + sg_data[2] + '&signature=' + sg_data[
-                              3] + '&uin=&key=&pass_ticket=&wxtoken=&devicetype=&clientversion=0&x5=0'
+        comment_req_url = 'http://mp.weixin.qq.com/mp/getcomment?src={}&ver={}&timestamp={}&signature={}&uin=&key=&pass_ticket=&wxtoken=&devicetype=&clientversion=0&x5=0'.format(
+            *sg_data)
         comment_text = self._get(comment_req_url, 'get', host='mp.weixin.qq.com', referer='http://mp.weixin.qq.com')
         comment_dict = eval(comment_text)
         ret = comment_dict['base_resp']['ret']

wechatsogou/basic.py

@@ -4,7 +4,7 @@
 import time
 import random
 import logging
-from builtins import input
+from future.builtins.misc import input
 
 import requests
 from lxml import etree
@@ -22,13 +22,11 @@
 try:
     import StringIO
 
-
     def readimg(content):
         return Image.open(StringIO.StringIO(content))
 except ImportError:
     import tempfile
 
-
     def readimg(content):
         f = tempfile.TemporaryFile()
         f.write(content)

wechatsogou/config.py

@@ -3,4 +3,3 @@
 # 缓存配置
 cache_dir = 'cache'
 cache_session_name = 'requests_wechatsogou_session'
-

wechatsogou/exceptions.py

@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 
+
 class WechatSogouException(Exception):
     """基于搜狗搜索的的微信公众号爬虫接口  异常基类
     """