Protected: Chegg Chapter Solution->Markdown / chegg 答案转markdown
Enter your password to view comments.
There is no excerpt because this is a protected post.
Category: Coding
Flask code 400, message Bad HTTP/0.9 request type
Error from Flask: code 400, message Bad HTTP/0.9 request type This is due to feeding HTTPS to Flask. Solution: Set HTTPS, use HTTP or use Nginx to… Read more »
onedrivecmd：加入quota
下个版本加个setup.py吧。。。
onedrivecmd: Yet another Onedrive command-line client for Linux and OSX / Onedrive的命令行工具
https://github.com/cnbeining/onedrivecmd 又撸了一个东西玩。 MS经常给EDU邮箱，但是Linux下没有工具，也就是说有巨大备份需求的大户反而跑不了。 按megacmd，照猫画虎，撸一个这玩意。 MS的SDK挺难用的，文档挺语焉不详的。但是幸好没遇到什么很大的需要debug的东西。 老样子，欢迎PR。 AGPL，麻烦想偷的自己琢磨琢磨先。
Things to read in the free time
Speech side: Audio Segmenting: http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0144610#sec008 Then run FFMpeg with -s and -t with subprocess Google Speech API: https://cloud.google.com/speech/reference/rest/v1beta1/speech/syncrecognize curl ‘https://speech.googleapis.com/v1beta1/speech:syncrecognize?key=AIzaSyBmmqjUsStJat65IP7KgKuH2cz6rRvlIr8’ -H ‘Referer: https://cloud.google.com/‘ -H ‘Origin: https://cloud.google.com‘ -H ‘User-Agent: Mozilla/5.0 (Macintosh; Intel… Read more »
Biligrab日常换key更新
没什么要说的，换了个key，继续续命。 不行了再把新算法拿出来。
Acfun自动老司机：自动按正则回复私信
有人提议，我就写个。 老规矩，GPLv2,自己测试，风险自担。 https://gist.github.com/cnbeining/b77a4f5762a78fb3878c
|
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 |
#!/usr/bin/env python #coding:utf-8 # Author: Beining --<i@cnbeining.com> # Purpose: Auto reply Acfun's msg # Created: 01/05/2016 # License: GPLv2 import sys import unittest import requests import json import urllib.parse import time cookiepath = '' VER = '0.01' global cookiepath global HEADER global UA import re global regex_expression_list regex_expression_list = [ ('ACICFG', 'Hi!') ] #---------------------------------------------------------------------- def read_cookie(cookiepath): """str->list Original target: set the cookie Target now: Set the global header""" #print(cookiepath) try: cookies_file = open(cookiepath, 'r') cookies = cookies_file.readlines() cookies_file.close() # print(cookies) return cookies except Exception: print('Cannot read cookie, may affect some videos...') return [''] #---------------------------------------------------------------------- def get_unread_list(): """""" req = requests.get('http://www.acfun.tv/api/mail.aspx?name=getGroups&page=1', headers = HEADER) content = json.loads(req.content) return [str(i) for i in b['unReadList']] #---------------------------------------------------------------------- def get_last_msg_by_p2p(p2p): """""" req = requests.get('http://www.acfun.tv/api/mail.aspx?name=getMails&page=1&p2p={p2p}'.format(p2p = p2p), headers = HEADER) content = json.loads(req.content) return json.loads(content['mailList'][0]) #---------------------------------------------------------------------- def get_regex_object_list(regex_list): """""" list_this = [] for i in regex_list: list_this.append(((eval('re.compile(r"{regex}")'.format(regex = i[0]))), i[1])) return list_this #---------------------------------------------------------------------- def get_reply_by_text(text): """""" for i in regex_object_list: if i[0].match(mail): return i[1] #---------------------------------------------------------------------- def send_reply(userId, content): """""" content = urllib.parse.quote(content) data = 'userId={userId}&content={content}'.format(userId = userId, content = content) requests.post('http://www.acfun.tv/api/mail.aspx?name=newMail', headers=HEADER, data=data) #---------------------------------------------------------------------- def main(): """""" unReadList = get_unread_list() for p2p in unReadList: mail = get_last_msg_by_p2p(p2p) reply = get_reply_by_text(mail['text']) fromuId = mail['fromuId'] fromusername = mail['fromusername'] send_reply(fromuId, reply) print('Received: {mail} from {fromusername}, Sent: {reply}') #---------------------------------------------------------------------- def usage(): """""" pass if __name__=='__main__': argv_list = [] argv_list = sys.argv[1:] cookiepath,wait_time = '', 5 try: opts, args = getopt.getopt(argv_list, "hc:t:", ['help', "cookie=", 'time=']) except getopt.GetoptError: usage() exit() for o, a in opts: if o in ('-h', '--help'): usage() exit() if o in ('-c', '--cookie'): cookiepath = a if o in ('-t', '--time'): wait_time = a if cookiepath == '': cookiepath = './accookies' if not os.path.exists(cookiepath): print('Unable to open the cookie\'s file!') print('Please put your cookie in the file \"bilicookies\" or set a path yourself') exit() cookies = read_cookie(cookiepath)[0] UA = 'Acfun Auto Msg/{VER} (cnbeining@gmail.com) (Python-urllib/{python_ver_str}, like libcurl/1.0 NSS-Mozilla/2.0)'.format(VER = VER, python_ver_str = python_ver_str) HEADER = {'User-Agent': UA, 'Cache-Control': 'no-cache', 'Pragma': 'no-cache', 'Cookie': cookies[0]} regex_object_list = get_regex_object_list(regex_expression_list) global regex_object_list while 1: main() time.sleep(wait_time) |
备份：Bilibili 历史弹幕下载
原作者的gists死了，备份一下以免灭失。 https://kirito.me/python/download-bilibili-historical-danmu.html
|
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 |
#!/usr/bin/env python # -*- coding=utf-8 -*- # 哔哩哔哩历史弹幕 (XML) 下载器 # 使用：downdanmu.py av314 import StringIO import datetime import gzip import json import os import re import urllib2 import zlib # 接受参数 av****** 并创建 xml 保存目录 av_number = sys.argv[1] xml_folder = r'./%s' % av_number if os.path.exists(xml_folder): pass else: os.makedirs(xml_folder) # 处理 bilibili 视频页面 video_page_url = 'http://www.bilibili.tv/video/%s' % av_number video_page_request = urllib2.Request(video_page_url) video_page_gz = urllib2.urlopen(video_page_request).read() # gzip 解压 # 方法来自 [url]http://stackoverflow.com/a/3947241[/url] video_page_buffer = StringIO.StringIO(video_page_gz) video_page_html = gzip.GzipFile(fileobj = video_page_buffer).read() # 获取视频 cid cid_number = re.findall(r'cid=(\d+)', video_page_html)[0] # 获取视频所有历史弹幕 comments_page_url = 'http://comment.bilibili.tv/rolldate,%s' % cid_number comments_page_request = urllib2.Request(comments_page_url) comments_page_zip = urllib2.urlopen(comments_page_request).read() # deflate 解压 # 方法来自 [url]http://stackoverflow.com/a/9583564[/url] comments_page_json = zlib.decompressobj(-zlib.MAX_WBITS).decompress(comments_page_zip) # 解析历史弹幕信息 comments_python_object = json.loads(comments_page_json) for i in range(0, len(comments_python_object)): comment_timestamp = comments_python_object[i]['timestamp'] comment_date = datetime.datetime.fromtimestamp(int(comment_timestamp)).strftime('%Y%m%d') comment_then_url = 'http://comment.bilibili.tv/dmroll,%s,%s' % (comment_timestamp, cid_number) comment_then_request = urllib2.Request(comment_then_url) comment_then_zip = urllib2.urlopen(comment_then_request).read() comment_then_xml = zlib.decompressobj(-zlib.MAX_WBITS).decompress(comment_then_zip) comment_file = open('%s/%s.xml' % (xml_folder, comment_date), 'wb') comment_file.write(comment_then_xml) comment_file.close() else: pass |
重新封装一下Bilibili弹幕组件的API
主要为了算PMF。 不授权任何转载。
|
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 |
import xml.etree.ElementTree as ET import requests ######################################################################## class BilibiliDanmaku: """""" cid = 0 danmaku_list = [] danmaku_url = 'http://comment.bilibili.com/{cid}.xml' danmaku_xml = '' danmaku_xml_tree = {} danmaku_pmf_data = {} headers = { 'accept-encoding': 'gzip, deflate, sdch', 'accept-language': 'en-CA,en;q=0.8,en-US;q=0.6,zh-CN;q=0.4,zh;q=0.2', 'user-agent': '(Python-urllib/2.7, like libcurl/1.0 NSS-Mozilla/2.0)', 'accept': '*/*',} chatserver = '' #self.chatid = 0 mission = 0 maxlimit = 0 source = '' #---------------------------------------------------------------------- def __init__(self): """Constructor""" pass #---------------------------------------------------------------------- def init(self): """great init""" if self.cid <= 0: raise ValueError('invalid cid') self.get() self.parse() pass @classmethod #---------------------------------------------------------------------- def setcid(self, cid): """""" self.cid = cid self.danmaku_url = self.danmaku_url.format(cid = cid) #---------------------------------------------------------------------- def get(self): """""" if not self.cid: raise ValueError('Cid not set') responce = requests.get(self.danmaku_url, headers= self.headers) self.danmaku_xml = responce.content @classmethod #---------------------------------------------------------------------- def load(self, file_this): """""" if type(file_this) == str: self.danmaku_xml = file_this elif type(file_this) == file: f = open(file_this, 'r') self.danmaku_xml = f.read() f.close() #---------------------------------------------------------------------- def parse(self): """""" if not self.danmaku_xml: raise ValueError('No Danmaku Data') tree = ET.ElementTree(ET.fromstring(self.danmaku_xml)) root = tree.getroot() for child_of_root in root: if child_of_root.tag == 'chatserver': self.chatserver = child_of_root.text if child_of_root.tag == 'chatid': self.cid = int(child_of_root.text) if child_of_root.tag == 'mission': self.mission = child_of_root.text if child_of_root.tag == 'maxlimit': self.maxlimit = int(child_of_root.text) if child_of_root.tag == 'source': self.source = child_of_root.text if child_of_root.tag == 'd': info = str(child_of_root.attrib.get('p')).split(',') self.danmaku_xml_tree[info[7]] = {'stime': info[0], 'mode': info[1], 'size': info[2], 'color': info[3], 'timestamp': info[4], 'pool': info[5], 'sender': info[6], 'msg': child_of_root.text } @classmethod #---------------------------------------------------------------------- def get_pmf(self, period): """""" timelist = [(k, v['stime']) for k, v in self.danmaku_xml_tree.iteritems()] timelist.sort(key = lambda tup:tup[1]) if period == 0: return timelist start = 0 #not 0 self.danmaku_pmf_data = {0: [], } for i in timelist: if i[1] <= int(start + period): self.danmaku_pmf_data[start].append(i[0]) elif i[1] > int(start + period): start += period self.danmaku_pmf_data[start] = [] self.danmaku_pmf_data[start].append(i[0]) |