PyQt5自定义控件

李魔佛 发表了文章 • 0 个评论 • 3082 次浏览 • 2020-06-13 23:14 • 来自相关话题

PyQt5包含种类丰富的控件。但能满足所有需求的控件库是不存在的。通常控件库只提供了像按钮、文本控件、滑块等最常用的控件。但如果需要某种特殊的控件,我们只能自己动手来实现。 自定义控件需要使用工具库提供的绘图工具,可能有两种方式:在已有的控件上进行拓展或从头开始创建自定义控件。
 
Burning widget(烧录控件)
这个控件可能会在Nero,K3B或其他CD/DVD烧录软件中见到。
 
# -*- coding: utf-8 -*-

"""
PyQt5 tutorial

In this example, we create a custom widget.
"""
import sys
from PyQt5.QtWidgets import (QWidget, QSlider, QApplication,
QHBoxLayout, QVBoxLayout)
from PyQt5.QtCore import QObject, Qt, pyqtSignal
from PyQt5.QtGui import QPainter, QFont, QColor, QPen


class Communicate(QObject):
updateBW = pyqtSignal(int)


class BurningWidget(QWidget):
def __init__(self):
super().__init__()

self.initUI()

def initUI(self):

self.setMinimumSize(1, 30)
self.value = 75
self.num = [75, 150, 225, 300, 375, 450, 525, 600, 675]

def setValue(self, value):

self.value = value

def paintEvent(self, e):

qp = QPainter()
qp.begin(self)
self.drawWidget(qp)
qp.end()

def drawWidget(self, qp):

font = QFont('Serif', 7, QFont.Light)
qp.setFont(font)

size = self.size()
w = size.width()
h = size.height()

step = int(round(w / 10.0))

till = int(((w / 750.0) * self.value))
full = int(((w / 750.0) * 700))

if self.value >= 700:

qp.setPen(QColor(255, 255, 255))
qp.setBrush(QColor(255, 255, 184))
qp.drawRect(0, 0, full, h)
qp.setPen(QColor(255, 175, 175))
qp.setBrush(QColor(255, 175, 175))
qp.drawRect(full, 0, till - full, h)

else:

qp.setPen(QColor(255, 255, 255))
qp.setBrush(QColor(255, 255, 184))
qp.drawRect(0, 0, till, h)

pen = QPen(QColor(20, 20, 20), 1,
Qt.SolidLine)

qp.setPen(pen)
qp.setBrush(Qt.NoBrush)
qp.drawRect(0, 0, w - 1, h - 1)

j = 0

for i in range(step, 10 * step, step):
qp.drawLine(i, 0, i, 5)
metrics = qp.fontMetrics()
fw = metrics.width(str(self.num[j]))
qp.drawText(i - fw / 2, h / 2, str(self.num[j]))
j = j + 1


class Example(QWidget):
def __init__(self):
super().__init__()

self.initUI()

def initUI(self):
sld = QSlider(Qt.Horizontal, self)
sld.setFocusPolicy(Qt.NoFocus)
sld.setRange(1, 750)
sld.setValue(75)
sld.setGeometry(30, 40, 150, 30)

self.c = Communicate()
self.wid = BurningWidget()
self.c.updateBW[int].connect(self.wid.setValue)

sld.valueChanged[int].connect(self.changeValue)
hbox = QHBoxLayout()
hbox.addWidget(self.wid)
vbox = QVBoxLayout()
vbox.addStretch(1)
vbox.addLayout(hbox)
self.setLayout(vbox)

self.setGeometry(300, 300, 390, 210)
self.setWindowTitle('Burning widget')
self.show()

def changeValue(self, value):
self.c.updateBW.emit(value)
self.wid.repaint()


if __name__ == '__main__':
app = QApplication(sys.argv)
ex = Example()
sys.exit(app.exec_())
在示例中我们使用了滑块与一个自定义控件。自定义控件受滑块控制。控件显示了媒体介质的容量和剩余空间。该控件的最小值为1,最大值为750。在值超过700时颜色变为红色。这通常意味着超刻(即实际写入光盘的容量超过刻录盘片官方标称容量的一种操作)。
 
BurningWidget控件通过QHBoxLayout与QVBoxLayout置于窗体的底部。
class BurningWidget(QWidget):

def __init__(self):
super().__init__()
 
烧录的控件,它基于QWidget
 
self.setMinimumSize(1, 30)我们改变了控件的最小大小(高度),默认值为有点小。
font = QFont('Serif', 7, QFont.Light)
qp.setFont(font)我们使用一个比默认要小的字体。
size = self.size()
w = size.width()
h = size.height()

step = int(round(w / 10.0))


till = int(((w / 750.0) * self.value))
full = int(((w / 750.0) * 700))
控件采用了动态绘制技术。窗体越大,控件也随之变大;反之亦然。这也是我们需要计算自定义控件的载体控件(即窗体)尺寸的原因。till参数定义了需要绘制的总尺寸,它根据slider控件计算得出,是整体区域的比例值。full参数定义了红色区域的绘制起点。注意在绘制时为取得较大精度而使用的浮点数运算。

实际的绘制分三个步骤。黄色或红黄矩形的绘制,然后是刻度线的绘制,最后是刻度值的绘制。
 
metrics = qp.fontMetrics()
fw = metrics.width(str(self.num[j]))
qp.drawText(i-fw/2, h/2, str(self.num[j]))我们使用字体度量来绘制文本。我们必须知道文本的宽度,以中心垂直线。
def changeValue(self, value):

self.c.updateBW.emit(value)
self.wid.repaint()当滑块发生移动时,changeValue()方法会被调用。在方法内我们触发了一个自定义的updateBW信号,其参数是当前滚动条的值。该值被用于计算Burning widget的容量值。然后对控件进行重绘。
 





  查看全部
PyQt5包含种类丰富的控件。但能满足所有需求的控件库是不存在的。通常控件库只提供了像按钮、文本控件、滑块等最常用的控件。但如果需要某种特殊的控件,我们只能自己动手来实现。 自定义控件需要使用工具库提供的绘图工具,可能有两种方式:在已有的控件上进行拓展或从头开始创建自定义控件。
 
Burning widget(烧录控件)
这个控件可能会在Nero,K3B或其他CD/DVD烧录软件中见到。
 
# -*- coding: utf-8 -*-

"""
PyQt5 tutorial

In this example, we create a custom widget.
"""
import sys
from PyQt5.QtWidgets import (QWidget, QSlider, QApplication,
QHBoxLayout, QVBoxLayout)
from PyQt5.QtCore import QObject, Qt, pyqtSignal
from PyQt5.QtGui import QPainter, QFont, QColor, QPen


class Communicate(QObject):
updateBW = pyqtSignal(int)


class BurningWidget(QWidget):
def __init__(self):
super().__init__()

self.initUI()

def initUI(self):

self.setMinimumSize(1, 30)
self.value = 75
self.num = [75, 150, 225, 300, 375, 450, 525, 600, 675]

def setValue(self, value):

self.value = value

def paintEvent(self, e):

qp = QPainter()
qp.begin(self)
self.drawWidget(qp)
qp.end()

def drawWidget(self, qp):

font = QFont('Serif', 7, QFont.Light)
qp.setFont(font)

size = self.size()
w = size.width()
h = size.height()

step = int(round(w / 10.0))

till = int(((w / 750.0) * self.value))
full = int(((w / 750.0) * 700))

if self.value >= 700:

qp.setPen(QColor(255, 255, 255))
qp.setBrush(QColor(255, 255, 184))
qp.drawRect(0, 0, full, h)
qp.setPen(QColor(255, 175, 175))
qp.setBrush(QColor(255, 175, 175))
qp.drawRect(full, 0, till - full, h)

else:

qp.setPen(QColor(255, 255, 255))
qp.setBrush(QColor(255, 255, 184))
qp.drawRect(0, 0, till, h)

pen = QPen(QColor(20, 20, 20), 1,
Qt.SolidLine)

qp.setPen(pen)
qp.setBrush(Qt.NoBrush)
qp.drawRect(0, 0, w - 1, h - 1)

j = 0

for i in range(step, 10 * step, step):
qp.drawLine(i, 0, i, 5)
metrics = qp.fontMetrics()
fw = metrics.width(str(self.num[j]))
qp.drawText(i - fw / 2, h / 2, str(self.num[j]))
j = j + 1


class Example(QWidget):
def __init__(self):
super().__init__()

self.initUI()

def initUI(self):
sld = QSlider(Qt.Horizontal, self)
sld.setFocusPolicy(Qt.NoFocus)
sld.setRange(1, 750)
sld.setValue(75)
sld.setGeometry(30, 40, 150, 30)

self.c = Communicate()
self.wid = BurningWidget()
self.c.updateBW[int].connect(self.wid.setValue)

sld.valueChanged[int].connect(self.changeValue)
hbox = QHBoxLayout()
hbox.addWidget(self.wid)
vbox = QVBoxLayout()
vbox.addStretch(1)
vbox.addLayout(hbox)
self.setLayout(vbox)

self.setGeometry(300, 300, 390, 210)
self.setWindowTitle('Burning widget')
self.show()

def changeValue(self, value):
self.c.updateBW.emit(value)
self.wid.repaint()


if __name__ == '__main__':
app = QApplication(sys.argv)
ex = Example()
sys.exit(app.exec_())

在示例中我们使用了滑块与一个自定义控件。自定义控件受滑块控制。控件显示了媒体介质的容量和剩余空间。该控件的最小值为1,最大值为750。在值超过700时颜色变为红色。这通常意味着超刻(即实际写入光盘的容量超过刻录盘片官方标称容量的一种操作)。
 
BurningWidget控件通过QHBoxLayout与QVBoxLayout置于窗体的底部。
class BurningWidget(QWidget):

def __init__(self):
super().__init__()

 
烧录的控件,它基于QWidget
 
self.setMinimumSize(1, 30)
我们改变了控件的最小大小(高度),默认值为有点小。
font = QFont('Serif', 7, QFont.Light)
qp.setFont(font)
我们使用一个比默认要小的字体。
size = self.size()
w = size.width()
h = size.height()

step = int(round(w / 10.0))


till = int(((w / 750.0) * self.value))
full = int(((w / 750.0) * 700))

控件采用了动态绘制技术。窗体越大,控件也随之变大;反之亦然。这也是我们需要计算自定义控件的载体控件(即窗体)尺寸的原因。till参数定义了需要绘制的总尺寸,它根据slider控件计算得出,是整体区域的比例值。full参数定义了红色区域的绘制起点。注意在绘制时为取得较大精度而使用的浮点数运算。

实际的绘制分三个步骤。黄色或红黄矩形的绘制,然后是刻度线的绘制,最后是刻度值的绘制。
 
metrics = qp.fontMetrics()
fw = metrics.width(str(self.num[j]))
qp.drawText(i-fw/2, h/2, str(self.num[j]))
我们使用字体度量来绘制文本。我们必须知道文本的宽度,以中心垂直线。
def changeValue(self, value):

self.c.updateBW.emit(value)
self.wid.repaint()
当滑块发生移动时,changeValue()方法会被调用。在方法内我们触发了一个自定义的updateBW信号,其参数是当前滚动条的值。该值被用于计算Burning widget的容量值。然后对控件进行重绘。
 

12345.PNG

 

Windows安装pyminizip

李魔佛 发表了文章 • 0 个评论 • 3513 次浏览 • 2020-05-31 19:06 • 来自相关话题

python3直接安装会报错:
pip install pyminizip
 电脑需要安装vc的编译库,或者在其他机子上把pyd文件拷贝到程序的当前目录。
python3直接安装会报错:
pip install pyminizip
 电脑需要安装vc的编译库,或者在其他机子上把pyd文件拷贝到程序的当前目录。

为什么我使用splash中间件得到的response.body和splash上访问的html代码不同

李魔佛 回复了问题 • 1 人关注 • 1 个回复 • 3025 次浏览 • 2020-04-29 00:19 • 来自相关话题

pyqt5 QRect在哪个类

李魔佛 发表了文章 • 0 个评论 • 2503 次浏览 • 2020-04-24 10:45 • 来自相关话题

最新的版本是在 QtCore里面的
 from PyQt5.QtCore import Qt,QRect
 
最新的版本是在 QtCore里面的
 
from PyQt5.QtCore import Qt,QRect

 

请问各位用scrapy和redis方法爬取不到数据的问题(可悬赏),求大佬看下,感激不尽

python爬虫李魔佛 回复了问题 • 2 人关注 • 1 个回复 • 7509 次浏览 • 2020-04-16 22:16 • 来自相关话题

薅“疫情公益”羊毛,黑产恶意爬取各大出版社电子书上万册

python爬虫Magiccc 发表了文章 • 0 个评论 • 2812 次浏览 • 2020-02-26 13:17 • 来自相关话题

疫情以来,所有企业都上班延期选择在线复工,在我们居家自我隔离期间,极验观察爬虫却没有消停,反而爬虫行为更加活跃且更胜往常。本周五,我们和无糖信息一起聊聊线上爬虫的“疫情”。
 
 
疫情以来,所有企业都上班延期选择在线复工,在我们居家自我隔离期间,极验观察爬虫却没有消停,反而爬虫行为更加活跃且更胜往常。本周五,我们和无糖信息一起聊聊线上爬虫的“疫情”。
 
 

爬虫发送弹幕问题

回复

python爬虫naythefirst 发起了问题 • 1 人关注 • 0 个回复 • 3252 次浏览 • 2020-02-26 11:28 • 来自相关话题

requests请求返回的json格式为bytes乱码

python爬虫李魔佛 回复了问题 • 2 人关注 • 1 个回复 • 4705 次浏览 • 2020-02-16 23:35 • 来自相关话题

为什么我这段代码得到的是空列表呢

python爬虫李魔佛 回复了问题 • 2 人关注 • 1 个回复 • 3233 次浏览 • 2020-02-09 12:47 • 来自相关话题

socketio中client的sio wait用法

李魔佛 发表了文章 • 1 个评论 • 4617 次浏览 • 2020-01-08 20:30 • 来自相关话题

用于阻塞当前的线程,后面的操作不会进行,直到服务端断开。
 
import time
import socketio

sio = socketio.Client()
start_timer = None


def send_ping():
global start_timer
start_timer = time.time()
sio.emit('ping_from_client')


@sio.event
def connect():
print('connected to server')
send_ping()


@sio.event
def pong_from_server(data):
global start_timer
latency = time.time() - start_timer
print('latency is {0:.2f} ms'.format(latency * 1000))
sio.sleep(1)
send_ping()


if __name__ == '__main__':
sio.connect('http://localhost:5000')
sio.wait()
print('next')

比如上述代码中,如果调用了sio.wait() , 那么next是不会被打印的。
 
如果注释掉后,那么next就可以正常被打印。 查看全部
用于阻塞当前的线程,后面的操作不会进行,直到服务端断开。
 
import time
import socketio

sio = socketio.Client()
start_timer = None


def send_ping():
global start_timer
start_timer = time.time()
sio.emit('ping_from_client')


@sio.event
def connect():
print('connected to server')
send_ping()


@sio.event
def pong_from_server(data):
global start_timer
latency = time.time() - start_timer
print('latency is {0:.2f} ms'.format(latency * 1000))
sio.sleep(1)
send_ping()


if __name__ == '__main__':
sio.connect('http://localhost:5000')
sio.wait()
print('next')

比如上述代码中,如果调用了sio.wait() , 那么next是不会被打印的。
 
如果注释掉后,那么next就可以正常被打印。

jieba.posseg TypeError: cannot unpack non-iterable pair object 词性分析报错

李魔佛 发表了文章 • 0 个评论 • 4076 次浏览 • 2019-11-23 10:12 • 来自相关话题

词性标注的例子出现错误 'pair' object is not iterable
 
例子:import jieba.posseg as pseg
seg_list = pseg.cut("我爱北京天安门")
for word,flag in seg_list:
print(word)
print(flag) 
 ---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-5-f105f6980f88> in <module>()
1 import jieba.posseg as pseg
2 seg_list = pseg.cut("我爱北京天安门")
----> 3 for word,flag in seg_list:
4 print(word)
5 print(flag)

TypeError: cannot unpack non-iterable pair object原因是新版本中seg_list是一个生成器,所以只能 for win seg_list然后从word中解包出来

print(w.word)

print(w.flag)

这样问题就解决了。 查看全部
词性标注的例子出现错误 'pair' object is not iterable
 
例子:
import jieba.posseg as pseg
seg_list = pseg.cut("我爱北京天安门")
for word,flag in seg_list:
print(word)
print(flag)
 
 
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-5-f105f6980f88> in <module>()
1 import jieba.posseg as pseg
2 seg_list = pseg.cut("我爱北京天安门")
----> 3 for word,flag in seg_list:
4 print(word)
5 print(flag)

TypeError: cannot unpack non-iterable pair object
原因是新版本中seg_list是一个生成器,所以只能 for win seg_list
然后从word中解包出来

print(w.word)

print(w.flag)

这样问题就解决了。

scrapy在settings中定义变量不能包含小写!

python爬虫李魔佛 发表了文章 • 0 个评论 • 2675 次浏览 • 2019-11-16 16:39 • 来自相关话题

如果变量名包含小写字母,那么你的变量会被过滤掉,在scrapy编码的其他地方都会无法被识别。
比如定义了一个叫 Redis_host = '192.168.1.1',的值
 
然后在spider中,如果你调用self.settings.get('Redis_host')
那么返回值是 None。
 
如果用REDIS_HOST定义,那么就可以正确返回它的值。
 
如果你一定要用小写,也有其他方法可正常调用。
先导入settings文件
fromt xxxx import setttings # xxx为项目名
 
host = settings.Redis_host # 直接导入一个文件的形式来调用是可以的 查看全部
如果变量名包含小写字母,那么你的变量会被过滤掉,在scrapy编码的其他地方都会无法被识别。
比如定义了一个叫 Redis_host = '192.168.1.1',的值
 
然后在spider中,如果你调用self.settings.get('Redis_host')
那么返回值是 None。
 
如果用REDIS_HOST定义,那么就可以正确返回它的值。
 
如果你一定要用小写,也有其他方法可正常调用。
先导入settings文件
fromt xxxx import setttings # xxx为项目名
 
host = settings.Redis_host # 直接导入一个文件的形式来调用是可以的

etree.strip_tags的用法

python爬虫李魔佛 发表了文章 • 0 个评论 • 3879 次浏览 • 2019-10-24 11:24 • 来自相关话题

直接从官方文档那里拿过来,发现这个函数功能还挺不错的。
它把参数中的标签从源htmlelement中删除,并且把里面的标签文本给合并进来。
 
举个例子:from lxml.html import etree
from lxml.html import fromstring, HtmlElement

test_html = '''<p><span>hello</span><span>world</span></p>'''
test_element = fromstring(test_html)
etree.strip_tags(test_element,'span') # 清除span标签
etree.tostring(test_element)
因为上述操作直接应用于test_element上的,所以test_element的值已经被修改了。
 
所以现在test_element 的值是 
b'<p>helloworld</p>'

原创文章,转载请注明出处
http://30daydo.com/article/553
  查看全部
直接从官方文档那里拿过来,发现这个函数功能还挺不错的。
它把参数中的标签从源htmlelement中删除,并且把里面的标签文本给合并进来。
 
举个例子:
from lxml.html import etree
from lxml.html import fromstring, HtmlElement

test_html = '''<p><span>hello</span><span>world</span></p>'''
test_element = fromstring(test_html)
etree.strip_tags(test_element,'span') # 清除span标签
etree.tostring(test_element)

因为上述操作直接应用于test_element上的,所以test_element的值已经被修改了。
 
所以现在test_element 的值是 
b'<p>helloworld</p>'

原创文章,转载请注明出处
http://30daydo.com/article/553
 

mumu模拟器adb无法识别

python爬虫李魔佛 发表了文章 • 0 个评论 • 4916 次浏览 • 2019-10-17 08:41 • 来自相关话题

因为端口号被mumu改了。
 
            <Forwarding name="ADB_PORT" proto="1" hostip="127.0.0.1" hostport="7555" guestport="5555"/>
 
在mumu浏览器里面可以看到这个配置信息。
 
adb connect 127.0.0.1:7555
然后adb shell 就可以了。
 
配置文件名是:myandrovm_vbox86.nemu 查看全部
因为端口号被mumu改了。
 
            <Forwarding name="ADB_PORT" proto="1" hostip="127.0.0.1" hostport="7555" guestport="5555"/>
 
在mumu浏览器里面可以看到这个配置信息。
 
adb connect 127.0.0.1:7555
然后adb shell 就可以了。
 
配置文件名是:myandrovm_vbox86.nemu

aiohttp异步下载图片

python爬虫李魔佛 发表了文章 • 0 个评论 • 4458 次浏览 • 2019-09-16 17:14 • 来自相关话题

保存图片的时候不能用自带的open函数打开文件,需要用到异步io库 aiofiles来打开url = 'http://xyhz.huizhou.gov.cn/static/js/common/jigsaw/images/{}.jpg'
headers={'User-Agent':'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'}
async def getPage(num):

async with aiohttp.ClientSession() as session:
async with session.get(url.format(num),headers=headers) as resp:
if resp.status==200:
f= await aiofiles.open('{}.jpg'.format(num),mode='wb')
await f.write(await resp.read())
await f.close()

loop = asyncio.get_event_loop()
tasks = [getPage(i) for i in range(5)]
loop.run_until_complete(asyncio.wait(tasks))
原创文章,
转载请注明出处:
http://30daydo.com/article/537
  查看全部
保存图片的时候不能用自带的open函数打开文件,需要用到异步io库 aiofiles来打开
url = 'http://xyhz.huizhou.gov.cn/static/js/common/jigsaw/images/{}.jpg'
headers={'User-Agent':'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'}
async def getPage(num):

async with aiohttp.ClientSession() as session:
async with session.get(url.format(num),headers=headers) as resp:
if resp.status==200:
f= await aiofiles.open('{}.jpg'.format(num),mode='wb')
await f.write(await resp.read())
await f.close()

loop = asyncio.get_event_loop()
tasks = [getPage(i) for i in range(5)]
loop.run_until_complete(asyncio.wait(tasks))

原创文章,
转载请注明出处:
http://30daydo.com/article/537
 

基于文本及符号密度的网页正文提取方法 python实现

李魔佛 发表了文章 • 0 个评论 • 4646 次浏览 • 2019-09-10 15:19 • 来自相关话题

基于文本及符号密度的网页正文提取方法 python实现
 项目路径https://github.com/Rockyzsu/CodePool/tree/master/GeneralNewsExtractor
完成后在本文详细介绍,
请密切关注。 查看全部
基于文本及符号密度的网页正文提取方法 python实现
 项目路径https://github.com/Rockyzsu/CodePool/tree/master/GeneralNewsExtractor
完成后在本文详细介绍,
请密切关注。

python exchange保存备份邮件

李魔佛 发表了文章 • 3 个评论 • 3398 次浏览 • 2019-09-09 10:50 • 来自相关话题

python exchange保存备份邮件
 方便自己平时备份邮件。# -*-coding=utf-8-*-

# @Time : 2019/9/9 9:25
# @File : mail_backup.py
# @Author :
import codecs
import re
import config
import os
from exchangelib import DELEGATE, Account, Credentials, Configuration, NTLM, Message, Mailbox, HTMLBody,FileAttachment,ItemAttachment
from exchangelib.protocol import BaseProtocol, NoVerifyHTTPAdapter


#此句用来消除ssl证书错误,exchange使用自签证书需加上
BaseProtocol.HTTP_ADAPTER_CLS = NoVerifyHTTPAdapter


# 输入你的域账号如example\xxx
cred = Credentials(r'example\xxx', 你的邮箱密码)

configx = Configuration(server='mail.credlink.com', credentials=cred, auth_type=NTLM)
a = Account(
primary_smtp_address='你的邮箱地址', config=configx, autodiscover=False, access_type=DELEGATE
)


for item in a.inbox.all().order_by('-datetime_received')[:100]:
print(item.subject, item.sender, item.unique_body,item.datetime_received)

name = item.subject
name = re.sub('[\/:*?"<>|]', '-', name)
local_path = os.path.join('inbox', name+'.html')
with codecs.open(local_path, 'w','utf-8') as f:
f.write(item.unique_body)

for attachment in item.attachments:
if isinstance(attachment, FileAttachment):
name = attachment.name
name = re.sub('[\/:*?"<>|]','-',name)
local_path = os.path.join('inbox', attachment.name)
with codecs.open(local_path, 'wb') as f:
f.write(attachment.content)
print('Saved attachment to', local_path)

elif isinstance(attachment, ItemAttachment):
if isinstance(attachment.item, Message):
name=attachment.item.subject
name = re.sub('[\/:*?"<>|]', '-', name)
local_path = os.path.join('inbox', 'attachment')
with codecs.open(local_path, 'w') as f:
f.write(attachment.item.body)
原创文章,
转载请注明出处
http://30daydo.com/article/534
  查看全部
python exchange保存备份邮件
 方便自己平时备份邮件。
# -*-coding=utf-8-*-

# @Time : 2019/9/9 9:25
# @File : mail_backup.py
# @Author :
import codecs
import re
import config
import os
from exchangelib import DELEGATE, Account, Credentials, Configuration, NTLM, Message, Mailbox, HTMLBody,FileAttachment,ItemAttachment
from exchangelib.protocol import BaseProtocol, NoVerifyHTTPAdapter


#此句用来消除ssl证书错误,exchange使用自签证书需加上
BaseProtocol.HTTP_ADAPTER_CLS = NoVerifyHTTPAdapter


# 输入你的域账号如example\xxx
cred = Credentials(r'example\xxx', 你的邮箱密码)

configx = Configuration(server='mail.credlink.com', credentials=cred, auth_type=NTLM)
a = Account(
primary_smtp_address='你的邮箱地址', config=configx, autodiscover=False, access_type=DELEGATE
)


for item in a.inbox.all().order_by('-datetime_received')[:100]:
print(item.subject, item.sender, item.unique_body,item.datetime_received)

name = item.subject
name = re.sub('[\/:*?"<>|]', '-', name)
local_path = os.path.join('inbox', name+'.html')
with codecs.open(local_path, 'w','utf-8') as f:
f.write(item.unique_body)

for attachment in item.attachments:
if isinstance(attachment, FileAttachment):
name = attachment.name
name = re.sub('[\/:*?"<>|]','-',name)
local_path = os.path.join('inbox', attachment.name)
with codecs.open(local_path, 'wb') as f:
f.write(attachment.content)
print('Saved attachment to', local_path)

elif isinstance(attachment, ItemAttachment):
if isinstance(attachment.item, Message):
name=attachment.item.subject
name = re.sub('[\/:*?"<>|]', '-', name)
local_path = os.path.join('inbox', 'attachment')
with codecs.open(local_path, 'w') as f:
f.write(attachment.item.body)

原创文章,
转载请注明出处
http://30daydo.com/article/534
 

性能对比 pypy vs python

李魔佛 发表了文章 • 0 个评论 • 4697 次浏览 • 2019-09-06 17:04 • 来自相关话题

性能对比 pypy vs python
 不试不知道,一试吓一跳。
如果是CPU密集型的程序,pypy3的执行速度比python要快上一百倍。
talk is cheap, show me the code!
 
代码很简单,运行加法运算:
执行2千万次
 import time

LOOP = 2*10**8

def add(x,y):
return x+y

def cpu_pressure(loop):

for i in range(loop):
result = add(i,i+1)


if __name__ == '__main__':
start = time.time()
cpu_pressure(LOOP)
print(f'time used {time.time()-start}s')
python执行:
python main.py
返回用时:time used 21.422261476516724s
 
pypy执行:
pypy main.py
返回用时:time used 0.1925642490386963s
 
差距真的很大。 查看全部
性能对比 pypy vs python
 不试不知道,一试吓一跳。
如果是CPU密集型的程序,pypy3的执行速度比python要快上一百倍。
talk is cheap, show me the code!
 
代码很简单,运行加法运算:
执行2千万次
 
import time

LOOP = 2*10**8

def add(x,y):
return x+y

def cpu_pressure(loop):

for i in range(loop):
result = add(i,i+1)


if __name__ == '__main__':
start = time.time()
cpu_pressure(LOOP)
print(f'time used {time.time()-start}s')

python执行:
python main.py
返回用时:time used 21.422261476516724s
 
pypy执行:
pypy main.py
返回用时:time used 0.1925642490386963s
 
差距真的很大。

scrapy源码分析<一>:入口函数以及是如何运行

python爬虫李魔佛 发表了文章 • 0 个评论 • 5517 次浏览 • 2019-08-31 10:47 • 来自相关话题

运行scrapy crawl example 命令的时候,就会执行我们写的爬虫程序。
下面我们从源码分析一下scrapy执行的流程:
 

执行scrapy crawl 命令时,调用的是Command类class Command(ScrapyCommand):

requires_project = True

def syntax(self):
return '[options]'

def short_desc(self):
return 'Runs all of the spiders - My Defined'

def run(self,args,opts):
print('==================')
print(type(self.crawler_process))
spider_list = self.crawler_process.spiders.list() # 找到爬虫类

for name in spider_list:
print('=================')
print(name)
self.crawler_process.crawl(name,**opts.__dict__)

self.crawler_process.start()
然后我们去看看crawler_process,这个是来自ScrapyCommand,而ScrapyCommand又是CrawlerProcess的子类,而CrawlerProcess又是CrawlerRunner的子类

在CrawlerRunner构造函数里面主要作用就是这个 def __init__(self, settings=None):
if isinstance(settings, dict) or settings is None:
settings = Settings(settings)
self.settings = settings
self.spider_loader = _get_spider_loader(settings) # 构造爬虫
self._crawlers = set()
self._active = set()
self.bootstrap_failed = False
1. 加载配置文件def _get_spider_loader(settings):

cls_path = settings.get('SPIDER_LOADER_CLASS')

# settings文件没有定义SPIDER_LOADER_CLASS,所以这里获取到的是系统的默认配置文件,
# 默认配置文件在接下来的代码块A
# SPIDER_LOADER_CLASS = 'scrapy.spiderloader.SpiderLoader'

loader_cls = load_object(cls_path)
# 这个函数就是根据路径转为类对象,也就是上面crapy.spiderloader.SpiderLoader 这个
# 字符串变成一个类对象
# 具体的load_object 对象代码见下面代码块B

return loader_cls.from_settings(settings.frozencopy())
默认配置文件defautl_settting.py# 代码块A
#......省略若干
SCHEDULER = 'scrapy.core.scheduler.Scheduler'
SCHEDULER_DISK_QUEUE = 'scrapy.squeues.PickleLifoDiskQueue'
SCHEDULER_MEMORY_QUEUE = 'scrapy.squeues.LifoMemoryQueue'
SCHEDULER_PRIORITY_QUEUE = 'scrapy.pqueues.ScrapyPriorityQueue'

SPIDER_LOADER_CLASS = 'scrapy.spiderloader.SpiderLoader' 就是这个值
SPIDER_LOADER_WARN_ONLY = False

SPIDER_MIDDLEWARES = {}

load_object的实现# 代码块B 为了方便,我把异常处理的去除
from importlib import import_module #导入第三方库

def load_object(path):
dot = path.rindex('.')
module, name = path[:dot], path[dot+1:]
# 上面把路径分为基本路径+模块名

mod = import_module(module)
obj = getattr(mod, name)
# 获取模块里面那个值

return obj

测试代码:In [33]: mod = import_module(module)

In [34]: mod
Out[34]: <module 'scrapy.spiderloader' from '/home/xda/anaconda3/lib/python3.7/site-packages/scrapy/spiderloader.py'>

In [35]: getattr(mod,name)
Out[35]: scrapy.spiderloader.SpiderLoader

In [36]: obj = getattr(mod,name)

In [37]: obj
Out[37]: scrapy.spiderloader.SpiderLoader

In [38]: type(obj)
Out[38]: type
在代码块A中,loader_cls是SpiderLoader,最后返回的的是SpiderLoader.from_settings(settings.frozencopy())
接下来看看SpiderLoader.from_settings, def from_settings(cls, settings):
return cls(settings)
返回类对象自己,所以直接看__init__函数即可class SpiderLoader(object):
"""
SpiderLoader is a class which locates and loads spiders
in a Scrapy project.
"""
def __init__(self, settings):
self.spider_modules = settings.getlist('SPIDER_MODULES')
# 获得settting中的模块名字,创建scrapy的时候就默认帮你生成了
# 你可以看看你的settings文件里面的内容就可以找到这个值,是一个list

self.warn_only = settings.getbool('SPIDER_LOADER_WARN_ONLY')
self._spiders = {}
self._found = defaultdict(list)
self._load_all_spiders() # 加载所有爬虫

核心就是这个_load_all_spiders:
走起:def _load_all_spiders(self):
for name in self.spider_modules:

for module in walk_modules(name): # 这个遍历文件夹里面的文件,然后再转化为类对象,
# 保存到字典:self._spiders = {}
self._load_spiders(module) # 模块变成spider

self._check_name_duplicates() # 去重,如果名字一样就异常

接下来看看_load_spiders
核心就是下面的。def iter_spider_classes(module):
from scrapy.spiders import Spider

for obj in six.itervalues(vars(module)): # 找到模块里面的变量,然后迭代出来
if inspect.isclass(obj) and \
issubclass(obj, Spider) and \
obj.__module__ == module.__name__ and \
getattr(obj, 'name', None): # 有name属性,继承于Spider
yield obj
这个obj就是我们平时写的spider类了。
原来分析了这么多,才找到了我们平时写的爬虫类

待续。。。。
 
原创文章
转载请注明出处
http://30daydo.com/article/530
  查看全部
运行scrapy crawl example 命令的时候,就会执行我们写的爬虫程序。
下面我们从源码分析一下scrapy执行的流程:
 

执行scrapy crawl 命令时,调用的是Command类
class Command(ScrapyCommand):

requires_project = True

def syntax(self):
return '[options]'

def short_desc(self):
return 'Runs all of the spiders - My Defined'

def run(self,args,opts):
print('==================')
print(type(self.crawler_process))
spider_list = self.crawler_process.spiders.list() # 找到爬虫类

for name in spider_list:
print('=================')
print(name)
self.crawler_process.crawl(name,**opts.__dict__)

self.crawler_process.start()

然后我们去看看crawler_process,这个是来自ScrapyCommand,而ScrapyCommand又是CrawlerProcess的子类,而CrawlerProcess又是CrawlerRunner的子类

在CrawlerRunner构造函数里面主要作用就是这个
      def __init__(self, settings=None):
if isinstance(settings, dict) or settings is None:
settings = Settings(settings)
self.settings = settings
self.spider_loader = _get_spider_loader(settings) # 构造爬虫
self._crawlers = set()
self._active = set()
self.bootstrap_failed = False

1. 加载配置文件
def _get_spider_loader(settings):

cls_path = settings.get('SPIDER_LOADER_CLASS')

# settings文件没有定义SPIDER_LOADER_CLASS,所以这里获取到的是系统的默认配置文件,
# 默认配置文件在接下来的代码块A
# SPIDER_LOADER_CLASS = 'scrapy.spiderloader.SpiderLoader'

loader_cls = load_object(cls_path)
# 这个函数就是根据路径转为类对象,也就是上面crapy.spiderloader.SpiderLoader 这个
# 字符串变成一个类对象
# 具体的load_object 对象代码见下面代码块B

return loader_cls.from_settings(settings.frozencopy())

默认配置文件defautl_settting.py
# 代码块A
#......省略若干
SCHEDULER = 'scrapy.core.scheduler.Scheduler'
SCHEDULER_DISK_QUEUE = 'scrapy.squeues.PickleLifoDiskQueue'
SCHEDULER_MEMORY_QUEUE = 'scrapy.squeues.LifoMemoryQueue'
SCHEDULER_PRIORITY_QUEUE = 'scrapy.pqueues.ScrapyPriorityQueue'

SPIDER_LOADER_CLASS = 'scrapy.spiderloader.SpiderLoader' 就是这个值
SPIDER_LOADER_WARN_ONLY = False

SPIDER_MIDDLEWARES = {}


load_object的实现
# 代码块B 为了方便,我把异常处理的去除
from importlib import import_module #导入第三方库

def load_object(path):
dot = path.rindex('.')
module, name = path[:dot], path[dot+1:]
# 上面把路径分为基本路径+模块名

mod = import_module(module)
obj = getattr(mod, name)
# 获取模块里面那个值

return obj


测试代码:
In [33]: mod = import_module(module)                                                                                                                                             

In [34]: mod
Out[34]: <module 'scrapy.spiderloader' from '/home/xda/anaconda3/lib/python3.7/site-packages/scrapy/spiderloader.py'>

In [35]: getattr(mod,name)
Out[35]: scrapy.spiderloader.SpiderLoader

In [36]: obj = getattr(mod,name)

In [37]: obj
Out[37]: scrapy.spiderloader.SpiderLoader

In [38]: type(obj)
Out[38]: type

在代码块A中,loader_cls是SpiderLoader,最后返回的的是SpiderLoader.from_settings(settings.frozencopy())
接下来看看SpiderLoader.from_settings,
    def from_settings(cls, settings):
return cls(settings)

返回类对象自己,所以直接看__init__函数即可
class SpiderLoader(object):
"""
SpiderLoader is a class which locates and loads spiders
in a Scrapy project.
"""
def __init__(self, settings):
self.spider_modules = settings.getlist('SPIDER_MODULES')
# 获得settting中的模块名字,创建scrapy的时候就默认帮你生成了
# 你可以看看你的settings文件里面的内容就可以找到这个值,是一个list

self.warn_only = settings.getbool('SPIDER_LOADER_WARN_ONLY')
self._spiders = {}
self._found = defaultdict(list)
self._load_all_spiders() # 加载所有爬虫


核心就是这个_load_all_spiders:
走起:
def _load_all_spiders(self):
for name in self.spider_modules:

for module in walk_modules(name): # 这个遍历文件夹里面的文件,然后再转化为类对象,
# 保存到字典:self._spiders = {}
self._load_spiders(module) # 模块变成spider

self._check_name_duplicates() # 去重,如果名字一样就异常


接下来看看_load_spiders
核心就是下面的。
def iter_spider_classes(module):
from scrapy.spiders import Spider

for obj in six.itervalues(vars(module)): # 找到模块里面的变量,然后迭代出来
if inspect.isclass(obj) and \
issubclass(obj, Spider) and \
obj.__module__ == module.__name__ and \
getattr(obj, 'name', None): # 有name属性,继承于Spider
yield obj

这个obj就是我们平时写的spider类了。
原来分析了这么多,才找到了我们平时写的爬虫类

待续。。。。
 
原创文章
转载请注明出处
http://30daydo.com/article/530
 

anaconda环境下无法启动jupyter notebook

李魔佛 发表了文章 • 0 个评论 • 7028 次浏览 • 2019-08-19 17:16 • 来自相关话题

运行 jupyter notebook
报错: from . import (constants, error, message, context,
ImportError: DLL load failed: 找不到指定的模块。

但是可以直接在Anaconda navigator中直接启动,所以判断是环境问题。
切换到anaconda的虚拟环境,(在菜单中进入anaconda prompt command),在当前命令行下执行 jupyter notebook就能够正常运行。
 
  查看全部
运行 jupyter notebook
报错:
    from . import (constants, error, message, context,
ImportError: DLL load failed: 找不到指定的模块。

但是可以直接在Anaconda navigator中直接启动,所以判断是环境问题。
切换到anaconda的虚拟环境,(在菜单中进入anaconda prompt command),在当前命令行下执行 jupyter notebook就能够正常运行。
 
 

random.randint的用法

李魔佛 发表了文章 • 0 个评论 • 12859 次浏览 • 2019-08-01 16:31 • 来自相关话题

random.randint的用法:
from random import randint

randint(0,1)
Out[25]: 1

randint(0,1)
Out[26]: 1

randint(0,1)
Out[27]: 1

randint(0,1)
Out[28]: 1

randint(0,1)
Out[29]: 0

randint(0,1)
Out[30]: 1
random.randint(a,b)
 
输出的整数范围包含a和b,和之间的整数
  查看全部
random.randint的用法:
from random import randint

randint(0,1)
Out[25]: 1

randint(0,1)
Out[26]: 1

randint(0,1)
Out[27]: 1

randint(0,1)
Out[28]: 1

randint(0,1)
Out[29]: 0

randint(0,1)
Out[30]: 1

random.randint(a,b)
 
输出的整数范围包含a和b,和之间的整数
 

frontera运行link_follower.py 报错:doesn't define any object named 'FIFO'

python爬虫李魔佛 发表了文章 • 0 个评论 • 3300 次浏览 • 2019-07-18 11:29 • 来自相关话题

代码如下:
from __future__ import print_function

import re

import requests

from frontera.contrib.requests.manager import RequestsFrontierManager
# from frontera.contrib.requests.manager import RequestsFrontierManager
from frontera import Settings

from six.moves.urllib.parse import urljoin


SETTINGS = Settings()
SETTINGS.BACKEND = 'frontera.contrib.backends.memory.FIFO'
# SETTINGS.BACKEND = 'frontera.contrib.backends.memory.MemoryDistributedBackend'

SETTINGS.LOGGING_MANAGER_ENABLED = True
SETTINGS.LOGGING_BACKEND_ENABLED = True
SETTINGS.MAX_REQUESTS = 100
SETTINGS.MAX_NEXT_REQUESTS = 10

SEEDS = [
'http://www.imdb.com',
]

LINK_RE = re.compile(r'<a.+?href="(.*?)".?>', re.I)


def extract_page_links(response):
return [urljoin(response.url, link) for link in LINK_RE.findall(response.text)]

if __name__ == '__main__':

frontier = RequestsFrontierManager(SETTINGS)
frontier.add_seeds([requests.Request(url=url) for url in SEEDS])
while True:
next_requests = frontier.get_next_requests()
if not next_requests:
break
for request in next_requests:
try:
response = requests.get(request.url)
links = [
requests.Request(url=url)
for url in extract_page_links(response)
]
frontier.page_crawled(response)
print('Crawled', response.url, '(found', len(links), 'urls)')

if links:
frontier.links_extracted(request, links)
except requests.RequestException as e:
error_code = type(e).__name__
frontier.request_error(request, error_code)
print('Failed to process request', request.url, 'Error:', e)

 无论用的py2或者py3,都会报以下的错误。raise NameError("Module '%s' doesn't define any object named '%s'" % (module, name))
NameError: Module 'frontera.contrib.backends.memory' doesn't define any object named 'FIFO' 查看全部
代码如下:
from __future__ import print_function

import re

import requests

from frontera.contrib.requests.manager import RequestsFrontierManager
# from frontera.contrib.requests.manager import RequestsFrontierManager
from frontera import Settings

from six.moves.urllib.parse import urljoin


SETTINGS = Settings()
SETTINGS.BACKEND = 'frontera.contrib.backends.memory.FIFO'
# SETTINGS.BACKEND = 'frontera.contrib.backends.memory.MemoryDistributedBackend'

SETTINGS.LOGGING_MANAGER_ENABLED = True
SETTINGS.LOGGING_BACKEND_ENABLED = True
SETTINGS.MAX_REQUESTS = 100
SETTINGS.MAX_NEXT_REQUESTS = 10

SEEDS = [
'http://www.imdb.com',
]

LINK_RE = re.compile(r'<a.+?href="(.*?)".?>', re.I)


def extract_page_links(response):
return [urljoin(response.url, link) for link in LINK_RE.findall(response.text)]

if __name__ == '__main__':

frontier = RequestsFrontierManager(SETTINGS)
frontier.add_seeds([requests.Request(url=url) for url in SEEDS])
while True:
next_requests = frontier.get_next_requests()
if not next_requests:
break
for request in next_requests:
try:
response = requests.get(request.url)
links = [
requests.Request(url=url)
for url in extract_page_links(response)
]
frontier.page_crawled(response)
print('Crawled', response.url, '(found', len(links), 'urls)')

if links:
frontier.links_extracted(request, links)
except requests.RequestException as e:
error_code = type(e).__name__
frontier.request_error(request, error_code)
print('Failed to process request', request.url, 'Error:', e)

 无论用的py2或者py3,都会报以下的错误。
raise NameError("Module '%s' doesn't define any object named '%s'" % (module, name))
NameError: Module 'frontera.contrib.backends.memory' doesn't define any object named 'FIFO'

scrapy-rabbitmq 不支持python3 [修改源码使它支持]

python爬虫李魔佛 发表了文章 • 0 个评论 • 3029 次浏览 • 2019-07-17 17:24 • 来自相关话题

官方版本在2015年就没有更新了。
在python3上运行的收会报错。
 
需要修改以下地方:
 
待续。。
官方版本在2015年就没有更新了。
在python3上运行的收会报错。
 
需要修改以下地方:
 
待续。。

scrapy rabbitmq 分布式爬虫

python爬虫李魔佛 发表了文章 • 0 个评论 • 5750 次浏览 • 2019-07-17 16:59 • 来自相关话题

对于没接触过rabbitmq的同学,可以看这个文章:https://blog.csdn.net/hellozpc/article/details/81436980
rabbitmq是个不错的消息队列服务,可以配合scrapy作为消息队列.
 
下面是一个简单的demo:import re
import requests
import scrapy
from scrapy import Request
from rabbit_spider import settings
from scrapy.log import logger
import json
from rabbit_spider.items import RabbitSpiderItem
import datetime
from scrapy.selector import Selector
import pika

# from scrapy_rabbitmq.spiders import RabbitMQMixin
# from scrapy.contrib.spiders import CrawlSpider

class Website(scrapy.Spider):
name = "rabbit"

def start_requests(self):
headers = {'Accept': '*/*',
'Accept-Encoding': 'gzip, deflate, br',
'Accept-Language': 'en-US,en;q=0.9,zh-CN;q=0.8,zh;q=0.7',
'Host': '36kr.com',
'Referer': 'https://36kr.com/information/web_news',
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.108 Safari/537.36'
}

url = 'https://36kr.com/information/web_news'


yield Request(url=url,
headers=headers)

def parse(self, response):


credentials = pika.PlainCredentials('admin', 'admin')
connection = pika.BlockingConnection(pika.ConnectionParameters('192.168.1.101', 5672, '/', credentials))

channel = connection.channel()
channel.exchange_declare(exchange='direct_log', exchange_type='direct')

result = channel.queue_declare(exclusive=True, queue='')

queue_name = result.method.queue

# print(queue_name)
# infos = sys.argv[1:] if len(sys.argv)>1 else ['info']
info = 'info'

# 绑定多个值

channel.queue_bind(
exchange='direct_log',
routing_key=info,
queue=queue_name
)
print('start to receive [{}]'.format(info))

channel.basic_consume(
on_message_callback=self.callback_func,
queue=queue_name,
auto_ack=True,
)

channel.start_consuming()


def callback_func(self, ch, method, properties, body):
print(body)
 启动spider:from scrapy import cmdline
cmdline.execute('scrapy crawl rabbit'.split())
 然后往rabbitmq里面推送数据:import pika
import settings

credentials = pika.PlainCredentials('admin','admin')
connection = pika.BlockingConnection(pika.ConnectionParameters('192.168.1.101',5672,'/',credentials))

channel = connection.channel()
channel.exchange_declare(exchange='direct_log',exchange_type='direct') # fanout 就是组播

routing_key = 'info'
message='https://36kr.com/pp/api/aggregation-entity?type=web_latest_article&b_id=59499&per_page=30'
channel.basic_publish(
exchange='direct_log',
routing_key=routing_key,
body=message
)

print('sending message {}'.format(message))
connection.close()
 
推送数据后,scrapy会马上接受到队里里面的数据。
注意不能在start_requests里面写等待队列的命令,因为start_requests函数需要返回一个生成器,否则程序会报错。
 
待续。。。
###### 2019-08-29 更新 ################### 
发现一个坑,就是rabbitMQ在接受到数据后,无法在回调函数里面使用yield生成器。
  查看全部
对于没接触过rabbitmq的同学,可以看这个文章:https://blog.csdn.net/hellozpc/article/details/81436980
rabbitmq是个不错的消息队列服务,可以配合scrapy作为消息队列.
 
下面是一个简单的demo:
import re
import requests
import scrapy
from scrapy import Request
from rabbit_spider import settings
from scrapy.log import logger
import json
from rabbit_spider.items import RabbitSpiderItem
import datetime
from scrapy.selector import Selector
import pika

# from scrapy_rabbitmq.spiders import RabbitMQMixin
# from scrapy.contrib.spiders import CrawlSpider

class Website(scrapy.Spider):
name = "rabbit"

def start_requests(self):
headers = {'Accept': '*/*',
'Accept-Encoding': 'gzip, deflate, br',
'Accept-Language': 'en-US,en;q=0.9,zh-CN;q=0.8,zh;q=0.7',
'Host': '36kr.com',
'Referer': 'https://36kr.com/information/web_news',
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.108 Safari/537.36'
}

url = 'https://36kr.com/information/web_news'


yield Request(url=url,
headers=headers)

def parse(self, response):


credentials = pika.PlainCredentials('admin', 'admin')
connection = pika.BlockingConnection(pika.ConnectionParameters('192.168.1.101', 5672, '/', credentials))

channel = connection.channel()
channel.exchange_declare(exchange='direct_log', exchange_type='direct')

result = channel.queue_declare(exclusive=True, queue='')

queue_name = result.method.queue

# print(queue_name)
# infos = sys.argv[1:] if len(sys.argv)>1 else ['info']
info = 'info'

# 绑定多个值

channel.queue_bind(
exchange='direct_log',
routing_key=info,
queue=queue_name
)
print('start to receive [{}]'.format(info))

channel.basic_consume(
on_message_callback=self.callback_func,
queue=queue_name,
auto_ack=True,
)

channel.start_consuming()


def callback_func(self, ch, method, properties, body):
print(body)

 启动spider:
from scrapy import cmdline
cmdline.execute('scrapy crawl rabbit'.split())

 然后往rabbitmq里面推送数据:
import pika
import settings

credentials = pika.PlainCredentials('admin','admin')
connection = pika.BlockingConnection(pika.ConnectionParameters('192.168.1.101',5672,'/',credentials))

channel = connection.channel()
channel.exchange_declare(exchange='direct_log',exchange_type='direct') # fanout 就是组播

routing_key = 'info'
message='https://36kr.com/pp/api/aggregation-entity?type=web_latest_article&b_id=59499&per_page=30'
channel.basic_publish(
exchange='direct_log',
routing_key=routing_key,
body=message
)

print('sending message {}'.format(message))
connection.close()

 
推送数据后,scrapy会马上接受到队里里面的数据。
注意不能在start_requests里面写等待队列的命令,因为start_requests函数需要返回一个生成器,否则程序会报错。
 
待续。。。
###### 2019-08-29 更新 ################### 
发现一个坑,就是rabbitMQ在接受到数据后,无法在回调函数里面使用yield生成器。
 

exchange_declare() got an unexpected keyword argument 'type'

李魔佛 发表了文章 • 0 个评论 • 2798 次浏览 • 2019-07-16 14:40 • 来自相关话题

In new version of pika, now it is using 
exchange_type instead of type
 
credentials = pika.PlainCredentials('admin','admin')
connection = pika.BlockingConnection(pika.ConnectionParameters('192.168.1.101',5672,'/',credentials))

channel = connection.channel()

channel.exchange_declare(exchange='logs',exchange_type='fanout') 查看全部
In new version of pika, now it is using 
exchange_type instead of type
 
	credentials = pika.PlainCredentials('admin','admin')
connection = pika.BlockingConnection(pika.ConnectionParameters('192.168.1.101',5672,'/',credentials))

channel = connection.channel()

channel.exchange_declare(exchange='logs',exchange_type='fanout')

twisted的getPage已经不建议使用,新接口为twisted.web.client.Agent

python爬虫李魔佛 发表了文章 • 2 个评论 • 3466 次浏览 • 2019-07-12 11:31 • 来自相关话题

Twisted-16.7.0 is coming soon, and it deprecates twisted.web.client.getPage (and client.HTTPClientFactory). We use these in some of the unit tests, to fetch one of the HTTP WAPI/WUI pages and make sure the contents look right.

We need to change these tests to use twisted.web.client.Agent instead, or a package named "treq", which is a Twisted flavor of the excellent (but blocking) requests library.

 
  查看全部


Twisted-16.7.0 is coming soon, and it deprecates twisted.web.client.getPage (and client.HTTPClientFactory). We use these in some of the unit tests, to fetch one of the HTTP WAPI/WUI pages and make sure the contents look right.

We need to change these tests to use twisted.web.client.Agent instead, or a package named "treq", which is a Twisted flavor of the excellent (but blocking) requests library.


 
 

twisted reactor运行后,添加了addBoth函数,但是还是无法停止

李魔佛 发表了文章 • 0 个评论 • 3827 次浏览 • 2019-07-11 09:43 • 来自相关话题

代码如下:
  from scrapy.selector import Selector

def get_response_callback(content):
txt = str(content,encoding='utf-8')
resp = Selector(text=txt)
title = resp.xpath('//title/text()').extract_first()
print(title)

@defer.inlineCallbacks
def task():
url = 'http://www.baidu.com'
d=getPage(url.encode('utf-8'))
d.addCallback(get_response_callback)
yield d

def done():
reactor.stop()

def done1(*args,**kwargs):
reactor.stop()

task_list =
for i in range(4):
d=task()
task_list.append(d)

dd = defer.DeferredList(task_list)

dd.addBoth(done)

reactor.run()
上面的代码是无法停止的,如果使用的是 
dd.addBoth(done)
 
done函数的定义是没有参数的。 
 
而使用另一个done函数带参数的done(*args,**kwargs)
是可以正常退出的,done里面写了reactor.stop() 函数
 
原创文章
转载请注明出处:
http://30daydo.com/article/509
  查看全部
代码如下:
 
	from scrapy.selector import Selector

def get_response_callback(content):
txt = str(content,encoding='utf-8')
resp = Selector(text=txt)
title = resp.xpath('//title/text()').extract_first()
print(title)

@defer.inlineCallbacks
def task():
url = 'http://www.baidu.com'
d=getPage(url.encode('utf-8'))
d.addCallback(get_response_callback)
yield d

def done():
reactor.stop()

def done1(*args,**kwargs):
reactor.stop()

task_list =
for i in range(4):
d=task()
task_list.append(d)

dd = defer.DeferredList(task_list)

dd.addBoth(done)

reactor.run()

上面的代码是无法停止的,如果使用的是 
dd.addBoth(done)
 
done函数的定义是没有参数的。 
 
而使用另一个done函数带参数的done(*args,**kwargs)
是可以正常退出的,done里面写了reactor.stop() 函数
 
原创文章
转载请注明出处:
http://30daydo.com/article/509
 

cv2 distanceTransform函数的用法 python

李魔佛 发表了文章 • 0 个评论 • 11365 次浏览 • 2019-07-08 15:35 • 来自相关话题

distanceTransform
Calculates the distance to the closest zero pixel for each pixel of the source image.


Python: cv2.distanceTransform(src, distanceType, maskSize[, dst]) → dst

Python: cv.DistTransform(src, dst, distance_type=CV_DIST_L2, mask_size=3, mask=None, labels=None) → None
Parameters:
src – 8-bit, single-channel (binary) source image.
dst – Output image with calculated distances. It is a 32-bit floating-point, single-channel image of the same size as src .
distanceType – Type of distance. It can be CV_DIST_L1, CV_DIST_L2 , or CV_DIST_C .
maskSize – Size of the distance transform mask. It can be 3, 5, or CV_DIST_MASK_PRECISE (the latter option is only supported by the first function). In case of the CV_DIST_L1 or CV_DIST_C distance type, the parameter is forced to 3 because a 3\times 3 mask gives the same result as 5\times 5 or any larger aperture.
labels – Optional output 2D array of labels (the discrete Voronoi diagram). It has the type CV_32SC1 and the same size as src . See the details below.
labelType – Type of the label array to build. If labelType==DIST_LABEL_CCOMP then each connected component of zeros in src (as well as all the non-zero pixels closest to the connected component) will be assigned the same label. If labelType==DIST_LABEL_PIXEL then each zero pixel (and all the non-zero pixels closest to it) gets its own label.
The functions distanceTransform calculate the approximate or precise distance from every binary image pixel to the nearest zero pixel. For zero image pixels, the distance will obviously be zero.


When maskSize == CV_DIST_MASK_PRECISE and distanceType == CV_DIST_L2 , the function runs the algorithm described in [Felzenszwalb04]. This algorithm is parallelized with the TBB library.

In other cases, the algorithm [Borgefors86] is used. This means that for a pixel the function finds the shortest path to the nearest zero pixel consisting of basic shifts: horizontal, vertical, diagonal, or knight’s move (the latest is available for a 5\times 5 mask). The overall distance is calculated as a sum of these basic distances. Since the distance function should be symmetric, all of the horizontal and vertical shifts must have the same cost (denoted as a ), all the diagonal shifts must have the same cost (denoted as b ), and all knight’s moves must have the same cost (denoted as c ). For the CV_DIST_C and CV_DIST_L1 types, the distance is calculated precisely, whereas for CV_DIST_L2 (Euclidean distance) the distance can be calculated only with a relative error (a 5\times 5 mask gives more accurate results). For a,``b`` , and c , OpenCV uses the values suggested in the original paper:

CV_DIST_C (3\times 3) a = 1, b = 1
CV_DIST_L1 (3\times 3) a = 1, b = 2
CV_DIST_L2 (3\times 3) a=0.955, b=1.3693
CV_DIST_L2 (5\times 5) a=1, b=1.4, c=2.1969
Typically, for a fast, coarse distance estimation CV_DIST_L2, a 3\times 3 mask is used. For a more accurate distance estimation CV_DIST_L2 , a 5\times 5 mask or the precise algorithm is used. Note that both the precise and the approximate algorithms are linear on the number of pixels.

The second variant of the function does not only compute the minimum distance for each pixel (x, y) but also identifies the nearest connected component consisting of zero pixels (labelType==DIST_LABEL_CCOMP) or the nearest zero pixel (labelType==DIST_LABEL_PIXEL). Index of the component/pixel is stored in \texttt{labels}(x, y) . When labelType==DIST_LABEL_CCOMP, the function automatically finds connected components of zero pixels in the input image and marks them with distinct labels. When labelType==DIST_LABEL_CCOMP, the function scans through the input image and marks all the zero pixels with distinct labels.

In this mode, the complexity is still linear. That is, the function provides a very fast way to compute the Voronoi diagram for a binary image. Currently, the second variant can use only the approximate distance transform algorithm, i.e. maskSize=CV_DIST_MASK_PRECISE is not supported yet.

Note
An example on using the distance transform can be found at opencv_source_code/samples/cpp/distrans.cpp
(Python) An example on using the distance transform can be found at opencv_source/samples/python2/distrans.py 

  查看全部
distanceTransform
Calculates the distance to the closest zero pixel for each pixel of the source image.


Python: cv2.distanceTransform(src, distanceType, maskSize[, dst]) → dst

Python: cv.DistTransform(src, dst, distance_type=CV_DIST_L2, mask_size=3, mask=None, labels=None) → None

Parameters:
src – 8-bit, single-channel (binary) source image.
dst – Output image with calculated distances. It is a 32-bit floating-point, single-channel image of the same size as src .

distanceType – Type of distance. It can be CV_DIST_L1, CV_DIST_L2 , or CV_DIST_C .
maskSize – Size of the distance transform mask. It can be 3, 5, or CV_DIST_MASK_PRECISE (the latter option is only supported by the first function). In case of the CV_DIST_L1 or CV_DIST_C distance type, the parameter is forced to 3 because a 3\times 3 mask gives the same result as 5\times 5 or any larger aperture.

labels – Optional output 2D array of labels (the discrete Voronoi diagram). It has the type CV_32SC1 and the same size as src . See the details below.

labelType – Type of the label array to build. If labelType==DIST_LABEL_CCOMP then each connected component of zeros in src (as well as all the non-zero pixels closest to the connected component) will be assigned the same label. If labelType==DIST_LABEL_PIXEL then each zero pixel (and all the non-zero pixels closest to it) gets its own label.
The functions distanceTransform calculate the approximate or precise distance from every binary image pixel to the nearest zero pixel. For zero image pixels, the distance will obviously be zero.


When maskSize == CV_DIST_MASK_PRECISE and distanceType == CV_DIST_L2 , the function runs the algorithm described in [Felzenszwalb04]. This algorithm is parallelized with the TBB library.

In other cases, the algorithm [Borgefors86] is used. This means that for a pixel the function finds the shortest path to the nearest zero pixel consisting of basic shifts: horizontal, vertical, diagonal, or knight’s move (the latest is available for a 5\times 5 mask). The overall distance is calculated as a sum of these basic distances. Since the distance function should be symmetric, all of the horizontal and vertical shifts must have the same cost (denoted as a ), all the diagonal shifts must have the same cost (denoted as b ), and all knight’s moves must have the same cost (denoted as c ). For the CV_DIST_C and CV_DIST_L1 types, the distance is calculated precisely, whereas for CV_DIST_L2 (Euclidean distance) the distance can be calculated only with a relative error (a 5\times 5 mask gives more accurate results). For a,``b`` , and c , OpenCV uses the values suggested in the original paper:

CV_DIST_C (3\times 3) a = 1, b = 1
CV_DIST_L1 (3\times 3) a = 1, b = 2
CV_DIST_L2 (3\times 3) a=0.955, b=1.3693
CV_DIST_L2 (5\times 5) a=1, b=1.4, c=2.1969
Typically, for a fast, coarse distance estimation CV_DIST_L2, a 3\times 3 mask is used. For a more accurate distance estimation CV_DIST_L2 , a 5\times 5 mask or the precise algorithm is used. Note that both the precise and the approximate algorithms are linear on the number of pixels.

The second variant of the function does not only compute the minimum distance for each pixel (x, y) but also identifies the nearest connected component consisting of zero pixels (labelType==DIST_LABEL_CCOMP) or the nearest zero pixel (labelType==DIST_LABEL_PIXEL). Index of the component/pixel is stored in \texttt{labels}(x, y) . When labelType==DIST_LABEL_CCOMP, the function automatically finds connected components of zero pixels in the input image and marks them with distinct labels. When labelType==DIST_LABEL_CCOMP, the function scans through the input image and marks all the zero pixels with distinct labels.

In this mode, the complexity is still linear. That is, the function provides a very fast way to compute the Voronoi diagram for a binary image. Currently, the second variant can use only the approximate distance transform algorithm, i.e. maskSize=CV_DIST_MASK_PRECISE is not supported yet.

Note
An example on using the distance transform can be found at opencv_source_code/samples/cpp/distrans.cpp
(Python) An example on using the distance transform can be found at opencv_source/samples/python2/distrans.py
 

 

Win10下PhantomJS无法运行 【版本兼容问题】

李魔佛 发表了文章 • 0 个评论 • 5250 次浏览 • 2019-07-04 09:07 • 来自相关话题

以前在win7上运行的好好的。
在win10下就报错:
selenium.common.exceptions.WebDriverException: Message: Service C:\Tool\phantomjs-2.5.0-beta2-windows\phantomjs-2.5.0-beta2-windows\bin\phantomjs.exe unexpectedly exited. Status code was: 4294967295
 
后来替换了一个旧的版本,发现问题就这么解决了。
旧版本:phantomjs-2.1.1-windows
 
原创文章
转载请注明出处 
http://30daydo.com/article/505
  查看全部
以前在win7上运行的好好的。
在win10下就报错:
selenium.common.exceptions.WebDriverException: Message: Service C:\Tool\phantomjs-2.5.0-beta2-windows\phantomjs-2.5.0-beta2-windows\bin\phantomjs.exe unexpectedly exited. Status code was: 4294967295
 
后来替换了一个旧的版本,发现问题就这么解决了。
旧版本:phantomjs-2.1.1-windows
 
原创文章
转载请注明出处 
http://30daydo.com/article/505
 

喜马拉雅app 爬取音频文件

python爬虫李魔佛 发表了文章 • 0 个评论 • 5782 次浏览 • 2019-06-30 12:24 • 来自相关话题

============== 2019-10-28更新 =================
因为喜马拉雅的源码格式改了,所以爬虫代码也更新了一波
# -*- coding: utf-8 -*-
# website: http://30daydo.com
# @Time : 2019/6/30 12:03
# @File : main.py

import requests
import re
import os

url = 'http://180.153.255.6/mobile/v1/album/track/ts-1571294887744?albumId=23057324&device=android&isAsc=true&isQueryInvitationBrand=true&pageId={}&pageSize=20&pre_page=0'
headers = {'User-Agent': 'Xiaomi'}

def download():
for i in range(1, 3):
r = requests.get(url=url.format(i), headers=headers)
js_data = r.json()
data_list = js_data.get('data', {}).get('list', [])
for item in data_list:
trackName = item.get('title')
trackName = re.sub('[\/\\\:\*\?\"\<\>\|]', '_', trackName)
# trackName=re.sub(':','',trackName)
src_url = item.get('playUrl64')
filename = '{}.mp3'.format(trackName)
if not os.path.exists(filename):

try:
r0 = requests.get(src_url, headers=headers)
except Exception as e:
print(e)
print(trackName)
r0 = requests.get(src_url, headers=headers)


else:
with open(filename, 'wb') as f:
f.write(r0.content)

print('{} downloaded'.format(trackName))

else:
print(f'{filename}已经下载过了')

import shutil

def rename_():
for i in range(1, 3):
r = requests.get(url=url.format(i), headers=headers)
js_data = r.json()
data_list = js_data.get('data', {}).get('list', [])
for item in data_list:
trackName = item.get('title')
trackName = re.sub('[\/\\\:\*\?\"\<\>\|]', '_', trackName)
src_url = item.get('playUrl64')

orderNo=item.get('orderNo')

filename = '{}.mp3'.format(trackName)
try:

if os.path.exists(filename):
new_file='{}_{}.mp3'.format(orderNo,trackName)
shutil.move(filename,new_file)
except Exception as e:
print(e)





if __name__=='__main__':
rename_()
 
音频文件也更新了,详情见百度网盘。
 
 
======== 2018-10=============
 爬取喜马拉雅app上 杨继东的投资之道 的音频文件
运行环境:python3# -*- coding: utf-8 -*-
# website: http://30daydo.com
# @Time : 2019/6/30 12:03
# @File : main.py

import requests
import re
url = 'https://www.ximalaya.com/revision/play/album?albumId=23057324&pageNum=1&sort=1&pageSize=60'
headers={'User-Agent':'Xiaomi'}

r = requests.get(url=url,headers=headers)
js_data = r.json()
data_list = js_data.get('data',{}).get('tracksAudioPlay',)
for item in data_list:
trackName=item.get('trackName')
trackName=re.sub(':','',trackName)
src_url = item.get('src')
try:
r0=requests.get(src_url,headers=headers)
except Exception as e:
print(e)
print(trackName)
else:
with open('{}.m4a'.format(trackName),'wb') as f:
f.write(r0.content)
print('{} downloaded'.format(trackName))
保存为main.py
然后运行 python main.py
稍微等几分钟就自动下载好了。







附下载好的音频文件:
链接:https://pan.baidu.com/s/1t_vJhTvSJSeFdI1IaDS6fA 
提取码:e3zb 
 

原创文章
转载请注明出处
http://30daydo.com/article/503 查看全部
============== 2019-10-28更新 =================
因为喜马拉雅的源码格式改了,所以爬虫代码也更新了一波
# -*- coding: utf-8 -*-
# website: http://30daydo.com
# @Time : 2019/6/30 12:03
# @File : main.py

import requests
import re
import os

url = 'http://180.153.255.6/mobile/v1/album/track/ts-1571294887744?albumId=23057324&device=android&isAsc=true&isQueryInvitationBrand=true&pageId={}&pageSize=20&pre_page=0'
headers = {'User-Agent': 'Xiaomi'}

def download():
for i in range(1, 3):
r = requests.get(url=url.format(i), headers=headers)
js_data = r.json()
data_list = js_data.get('data', {}).get('list', [])
for item in data_list:
trackName = item.get('title')
trackName = re.sub('[\/\\\:\*\?\"\<\>\|]', '_', trackName)
# trackName=re.sub(':','',trackName)
src_url = item.get('playUrl64')
filename = '{}.mp3'.format(trackName)
if not os.path.exists(filename):

try:
r0 = requests.get(src_url, headers=headers)
except Exception as e:
print(e)
print(trackName)
r0 = requests.get(src_url, headers=headers)


else:
with open(filename, 'wb') as f:
f.write(r0.content)

print('{} downloaded'.format(trackName))

else:
print(f'{filename}已经下载过了')

import shutil

def rename_():
for i in range(1, 3):
r = requests.get(url=url.format(i), headers=headers)
js_data = r.json()
data_list = js_data.get('data', {}).get('list', [])
for item in data_list:
trackName = item.get('title')
trackName = re.sub('[\/\\\:\*\?\"\<\>\|]', '_', trackName)
src_url = item.get('playUrl64')

orderNo=item.get('orderNo')

filename = '{}.mp3'.format(trackName)
try:

if os.path.exists(filename):
new_file='{}_{}.mp3'.format(orderNo,trackName)
shutil.move(filename,new_file)
except Exception as e:
print(e)





if __name__=='__main__':
rename_()

 
音频文件也更新了,详情见百度网盘。
 
 
======== 2018-10=============
 爬取喜马拉雅app上 杨继东的投资之道 的音频文件
运行环境:python3
# -*- coding: utf-8 -*-
# website: http://30daydo.com
# @Time : 2019/6/30 12:03
# @File : main.py

import requests
import re
url = 'https://www.ximalaya.com/revision/play/album?albumId=23057324&pageNum=1&sort=1&pageSize=60'
headers={'User-Agent':'Xiaomi'}

r = requests.get(url=url,headers=headers)
js_data = r.json()
data_list = js_data.get('data',{}).get('tracksAudioPlay',)
for item in data_list:
trackName=item.get('trackName')
trackName=re.sub(':','',trackName)
src_url = item.get('src')
try:
r0=requests.get(src_url,headers=headers)
except Exception as e:
print(e)
print(trackName)
else:
with open('{}.m4a'.format(trackName),'wb') as f:
f.write(r0.content)
print('{} downloaded'.format(trackName))

保存为main.py
然后运行 python main.py
稍微等几分钟就自动下载好了。


喜马拉雅.PNG


附下载好的音频文件:
链接:https://pan.baidu.com/s/1t_vJhTvSJSeFdI1IaDS6fA 
提取码:e3zb 
 

原创文章
转载请注明出处
http://30daydo.com/article/503