python 论坛自动发帖功能
生活随笔
收集整理的這篇文章主要介紹了
python 论坛自动发帖功能
小編覺得挺不錯的,現(xiàn)在分享給大家,幫大家做個參考.
# -*- coding: utf-8 -*-
"""
@author: amtsing
"""
'''
Google翻譯
'''
import execjsclass Py4Js():
def __init__(self):
self.ctx = execjs.compile("""
function TL(a) {
var k = "";
var b = 406644;
var b1 = 3293161072;
var jd = ".";
var $b = "+-a^+6";
var Zb = "+-3^+b+-f";
for (var e = [], f = 0, g = 0; g < a.length; g++) {
var m = a.charCodeAt(g);
128 > m ? e[f++] = m : (2048 > m ? e[f++] = m >> 6 | 192 : (55296 == (m & 64512)
&& g + 1 < a.length && 56320 == (a.charCodeAt(g + 1) & 64512) ? (m = 65536 +
((m & 1023) << 10) + (a.charCodeAt(++g) & 1023),
e[f++] = m >> 18 | 240,
e[f++] = m >> 12 & 63 | 128) : e[f++] = m >> 12 | 224,
e[f++] = m >> 6 & 63 | 128),
e[f++] = m & 63 | 128)
}
a = b;
for (f = 0; f < e.length; f++) a += e[f],
a = RL(a, $b);
a = RL(a, Zb);
a ^= b1 || 0;
0 > a && (a = (a & 2147483647) + 2147483648);
a %= 1E6;
return a.toString() + jd + (a ^ b)
};
function RL(a, b) {
var t = "a";
var Yb = "+";
for (var c = 0; c < b.length - 2; c += 3) {
var d = b.charAt(c + 2),
d = d >= t ? d.charCodeAt(0) - 87 : Number(d),
d = b.charAt(c + 1) == Yb ? a >>> d: a << d;
a = b.charAt(c) == Yb ? a + d & 4294967295 : a ^ d
}
return a
}
""")
def getTk(self, text):
return self.ctx.call("TL", text)
import urllib.request, urllib.parsedef open_url(url):
'''打開網(wǎng)頁鏈接'''
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64;rv:23.0)Gecko/20100101
Firefox/23.0'}
req = urllib.request.Request(url=url, headers=headers)
response = urllib.request.urlopen(req)
data = response.read().decode('utf-8')
return datadef translate(content):
'''定義翻譯函數(shù)'''
if len(content) > 4891:
print("翻譯的長度超過限制！！！")
return
# 獲取tk值
if len(content) > 4891:
print("翻譯的長度超過限制！！！")
return
js = Py4Js()
tk = js.getTk(content)
# 對輸入內(nèi)容編碼
content = urllib.parse.quote(content)
url = "http://translate.google.cn/translate_a/single?client=t&sl=en&tl=zh-CN&hl=zh-CN&dt
=at&dt=bd&dt=ex&dt=ld&dt=md&dt=qca&dt=rw&dt=rm&dt=ss&dt=t&ie=UTF-8&oe=UTF-8&
source=bh&otf=1&ssel=0&tsel=0&kc=1&tk=%s&q=%s" % (tk, content)
# 返回值是一個多層嵌套列表的字符串形式，解析起來還相當費勁，寫了幾個正則，發(fā)現(xiàn)也很不理想，
# 后來感覺，使用正則簡直就是把簡單的事情復雜化，這里直接切片就Ok了
result = open_url(url)
end = result.find("\",")
if end > 4:
print(' '+ result[4:end])
output = (' '+ result[4:end])
return str(output)
'''
識別驗證碼
'''
import os
import requests
from PIL import Image,ImageGrab
import pytesseract
from collections import Counter,OrderedDict# def downimg(url):
# '''下載圖片'''
# with open ('verifycodepage.jpg','wb') as f:
# s = requests.Session()
# response = s.get(url)
# f.write(response.content)
def acumulate_colors(image):
'''對色彩像素進行統(tǒng)計'''
img = Image.open(image)
pixdata = img.load()
# c = Counter()
# print(pixdata)
colors = {}
for y in range(img.size[1]):
for x in range(img.size[0]):
#print(pixdata[x, y])
# c.update(pixdata[x, y])
if pixdata[x, y] in colors:
colors[pixdata[x, y]] += 1
else:
colors[pixdata[x, y]] = 1
colors = sorted(colors.items(),key=lambda d:d[1],reverse=True)
# c = OrderedDict(c)
# print (c.values())
print(colors[2][0])
return colors# def gray():
# '''灰度化'''
# img = Image.open('verifycodepage.jpg')
# img.convert('L').save('灰色圖.jpg')
'''
convert() 是圖像實例對象的一個方法，接受一個 mode 參數(shù)，用以指定一種色彩模式，mode 的取值可以是如下幾種：
· 1 (1-bit pixels, black and white, stored with one pixel per byte)
· L (8-bit pixels, black and white)
· P (8-bit pixels, mapped to any other mode using a colour palette)
· RGB (3x8-bit pixels, true colour)
· RGBA (4x8-bit pixels, true colour with transparency mask)
· CMYK (4x8-bit pixels, colour separation)
· YCbCr (3x8-bit pixels, colour video format)
· I (32-bit signed integer pixels)
· F (32-bit floating point pixels)
怎么樣，夠豐富吧？其實如此之處，PIL 還有限制地支持以下幾種比較少見的色彩模式：
LA (L with alpha), RGBX (true colour with padding) and RGBa。
'''
def binary(image):
'''二值化'''
img = Image.open(image)
pixdata = img.load()
for y in range(img.size[1]):
for x in range(img.size[0]):
# if pixdata[x, y] != colors[0][0]:
# pixdata[x, y] = (255,255,255)
# else:
# pixdata[x, y] = (0,0,0)
if pixdata[x, y][0] < 115:
pixdata[x, y] = (0, 0, 0)# 黑色
for y in range(img.size[1]):
for x in range(img.size[0]):
if pixdata[x, y][1] < 90:
pixdata[x, y] = (0, 0, 0)
for y in range(img.size[1]):
for x in range(img.size[0]):
if pixdata[x, y][2] > 120:
pixdata[x, y] = (255, 255, 255)# 白色
img.save('2值.jpg')
'''
red
必要參數(shù)；Integer類型。數(shù)值范圍從 0 到 255，表示顏色的紅色成份。
green
必要參數(shù)；Integer類型。數(shù)值范圍從 0 到 255，表示顏色的綠色成份。
blue
必要參數(shù)；Integer類型。數(shù)值范圍從 0 到 255，表示顏色的藍色成份。
'''
def denoisepoint(n,opt_point=0):
'''去噪點'''
direction = [
[1, 1], [1, 0], [1, -1], [0, -1],
[-1, -1], [-1, 0], [-1, 1], [0, 1]
]
num = 0 # 操作數(shù)量
point = 0 # 噪點數(shù)
img = Image.open('2值.jpg')
pix = img.load() # 像素值
size = img.size #圖片大小
# print(size)
for y in range(size[1]):
for x in range(size[0]):
num += 1
if pix[x, y][0] < n:
nearpoint = 0
for (a, b) in direction:
if (x+a>= 0 and x+a <= size[0]-1) and (y+b>= 0 and y+b <= size[1]-1):
# 如果遇到邊界外的點不處理
if pix[x + a, y + b][0] < n:
nearpoint += 1
if nearpoint <= opt_point:
pix[x, y] = (255, 255, 255, 255)
point += 1 # 噪點數(shù)
img.save('無噪點.jpg')
return (num, point)
def img2string():
'''圖像轉驗證碼'''
img = Image.open('無噪點.jpg')
pytesseract.pytesseract.tesseract_cmd= 'C:\\Program Files(x86)\\Tesseract-OCR\\tesseract'
captcha = pytesseract.image_to_string(img,lang='eng')
print(captcha)
return captcha'''
自動發(fā)帖
'''
import requests
import re
from lxml import etree
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.common.action_chains import ActionChains
from selenium.common.exceptions import NoSuchElementException
import random
import time
import newspaper
from PIL import Imagedef get_content(url,language):
'''獲取正文'''
content = newspaper.Article(url, language)
content.download()
content.parse()
return contentlogin_url = "http://www.****.so/member.php?mod=logging&action=login"
def login(login_url):
'''模擬登陸'''
headers = {
"User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML,
like Gecko) Chrome/58.0.3026.3 Safari/537.36"
}
for key,value in headers.items():
webdriver.DesiredCapabilities.PHANTOMJS['phantomjs.page.customHeaders{}'.format
(key)] = valueacountdictionary = {
'*****':'*****',
'******':'*****',
'*******':'*****',
}
acount = random.choice(list(acountdictionary.items()))
name = acount[0]
password = acount[1]
print(name,password)
browser.get(login_url)
time.sleep(3)
browser.find_element_by_xpath('//input[@name="username"]').send_keys(name)
browser.find_element_by_xpath('//input[@name="password"]').send_keys(password)
# browser.get_screenshot_as_file('bks.png') # 截取當前網(wǎng)頁，該網(wǎng)頁有我們需要的驗證碼
# imgelement = browser.find_element_by_xpath('//*[@id="vseccode_cS"]/img') # 定位驗證碼
# location = imgelement.location # 獲取驗證碼x,y軸坐標
# size = imgelement.size # 獲取驗證碼的長寬
# rangle = (location['x']+ size['width'],
# location['y']+ ize['height'],
# location['x'] + size['width'],
# location['y'] + size['height']) # 寫成我們需要截取的位置坐標
# img = Image.open("bks.png") # 打開截圖
# frame = img.crop(rangle) # 使用Image的crop函數(shù)，從截圖中再次截取我們需要的區(qū)域
# frame.save('驗證碼.png')
# img = Image.open('驗證碼.png')
# img.show()
# colors = acumulate_colors('驗證碼.png')
# denoisepoint(10)
# binary('驗證碼.png')
# denoisepoint(100)
# # devide(4)
# captcha = img2string()
browser.find_element_by_xpath('//input[@name="seccodeverify"]').send_keys(captcha)
browser.find_element_by_xpath('//button[@name="loginsubmit"]').click()
for i in range(1,20):
try:
# browser.execute_script('window.scrollTo(0, 5)')
time.sleep(1)
a = browser.find_element_by_xpath('//*[@id="ntcwin"]/table/tbody/tr/td[2]/div/i')
a = a.textwhile a == '抱歉，驗證碼填寫錯誤':
time.sleep(4)
if browser.current_url == 'http://www.bike.so/':
# print(browser.current_url)
# print('驗證碼正確！！')
break
else:
print('你還有{0}嘗試機會'.format(20 - i))
i += 1
if 20-i == 0:
print('對不起驗證碼錯誤次數(shù)過多！！！')
time.sleep(4)
browser.close()
break
else:
print('驗證碼錯誤！！！！請重新輸入……')
browser.find_element_by_xpath('// *[ @ id = "seccode_cS"] / div
/ table / tbody / tr / td / a').click()
# browser.get_screenshot_as_file('bks.png') # 截取當前網(wǎng)頁，該網(wǎng)頁有我們
# 需要的驗證碼
# imgelement = browser.find_element_by_xpath('//*[@id="vseccode_cS"]
/img') # 定位驗證碼
# location = imgelement.location # 獲取驗證碼x,y軸坐標
# size = imgelement.size # 獲取驗證碼的長寬
# rangle = (location['x'] + size['width'],
# location['y'] + size['height'],
# location['x'] + size['width'],
# location['y'] + size['height']) # 寫成我們需要截取的位置坐標
# img = Image.open("bks.png") # 打開截圖
# frame = img.crop(rangle) # 使用Image的crop函數(shù)，從截圖中再次截取
# 我們需要的區(qū)域
# frame.save('驗證碼.png')
# img = Image.open('驗證碼.png')
# img.show()
# colors = acumulate_colors('驗證碼.png')
# denoisepoint(10)
# binary('驗證碼.png')
# denoisepoint(100)
# # devide(4)
# captcha = img2string()
browser.find_element_by_xpath('//input[@name="seccodeverify"]').clear()
browser.find_element_by_xpath('//input[@name="seccodeverify"]')
.send_keys(captcha)
browser.find_element_by_xpath('//button[@name="loginsubmit"]').click()
except NoSuchElementException:
print("驗證碼正確！！")
break
def locat_plate():
'''定位發(fā)帖板塊'''
browser.execute_script('window.scrollTo(0, 100)')
time.sleep(2)
# 所有版塊
plates = {
'plate1':"山地車，公路車，新聞，車友交流",
'plate2':"游泳，自行車，馬拉松，鐵人三項",
'plate3': "BMX小輪車",
'plate4': "國內(nèi)業(yè)余賽事網(wǎng)友交流",
'plate5': "智能自行車原理及動態(tài)",
'plate6': "自行車旅行路線新聞百科全書",
'plate7': "騎行眼鏡",
'plate8': "騎行書籍",
'plate9': "騎行飲料",
'plate10': "國產(chǎn)著名品牌/native",
'plate11': "Giant/捷安特",
'plate12': "Merida/美利達",
'plate13': "Lapierre/法國拉皮爾",
'plate14': "Trek/崔克",
'plate15': "Shimano/禧瑪諾"
}
print("""
"請選擇你要發(fā)表的版塊：",
'plate1':"山地車，公路車，新聞，車友交流",
'plate2':"游泳，自行車，馬拉松，鐵人三項",
'plate3': "BMX小輪車",
'plate4': "國內(nèi)業(yè)余賽事網(wǎng)友交流",
'plate5': "智能自行車原理及動態(tài)",
'plate6': "自行車旅行路線新聞百科全書",
'plate7': "騎行眼鏡",
'plate8': "騎行書籍",
'plate9': "騎行飲料",
'plate10': "國產(chǎn)著名品牌/native",
'plate11': "Giant/捷安特",
'plate12': "Merida/美利達",
'plate13': "Lapierre/法國拉皮爾",
'plate14': "Trek/崔克",
'plate15': "Shimano/禧瑪諾"
"""
)
browser.execute_script('window.scrollTo(100, 0.5*document.body.scrollHeight)')
time.sleep(1)
ratio = input('要重新定位到哪里？范圍是0~0.5：')
browser.execute_script('window.scrollTo(0.5*document.body.scrollHeight, {}*document.body.
scrollHeight)'.format(ratio))
plate = input('請輸入你要發(fā)帖的版塊：')
browser.find_element_by_link_text(plates[plate]).click()
time.sleep(2)
def random_pick(some_list, probabilities):
'''定義不等概率抽樣'''
x = random.uniform(0, 1)
cumulative_probability = 0.0
for item, item_probability in zip(some_list, probabilities):
cumulative_probability += item_probabilityif x < cumulative_probability: break
return itemdef post_content(content):
'''自動發(fā)帖'''
browser.find_element_by_id('newspecial').click()
browser.switch_to.frame("e_iframe")
browser.find_element_by_xpath('/html/body').send_keys(Keys.TAB)
a = content.text.split('\n')
postcontent = []
for i in a:
if i != '':
output = translate(i) + '\n'
postcontent.append(output)
else:
beautystyle = [i,
'……………………………………………………………………………………………………………………………………………',
'=====================================================',
'-----------------------------------------------------',
'—————————————————————————————————————————————————————'
]
probabilities = [0.8, 0.05, 0.05, 0.05, 0.05]
line = random_pick(beautystyle, probabilities)
postcontent.append(line + '\n')
browser.find_element_by_xpath('/html/body').send_keys(postcontent)
time.sleep(4)
browser.switch_to.default_content()
# 或者driver.switch_to.parent_frame()
if content.title != '':
# if flag == 0:
title = translate(content.title)
browser.find_element_by_xpath('//*[@id="subject"]').send_keys(title)
else:
browser.find_element_by_xpath('//*[@id="subject"]').send_keys(input('請輸入標題:'))
browser.execute_script('window.scrollTo(0, 300)')
time.sleep(2)
# browser.find_element_by_xpath('//button[@id="為了不給網(wǎng)站帶來麻煩，
請大家不要使用此命令"]').click()
# 編輯帖子
# browser.find_element_by_link_text('編輯').click()
# browser.page_source
if __name__ == '__main__':
# 獲取正文并翻譯
urls = [
'http://www.360doc.com/content/11/1021/10/7796166_157906146.shtml',
]
for url in urls:
# 登錄論壇
browser = webdriver.Chrome()
browser.maximize_window()
login(login_url)
content = get_content(url,'en')
# 定位發(fā)帖版塊
locat_plate()
# 發(fā)帖
post_content(content)
# browser.close()
總結
以上是生活随笔為你收集整理的python 论坛自动发帖功能的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。
- 上一篇： web漏洞类型概述（owasp top1
- 下一篇： 移动金融客户端应用软件备案、中国支付清算