diff --git a/README.md b/README.md
index 1acd2e8..2bd9a61 100644
--- a/README.md
+++ b/README.md
@@ -24,5 +24,9 @@
23、itchat 获取微信群或者微信好友分享文章
24、爬取微信公众号历史文章
25、itchat监听指定微信公众号分享的文章
+26、itchat微信群微信好友防撤回
+27、在微信群之间转发消息
+27、下载bilibili视频 也可以下载哔哩哔哩集合视频
+28、爬取m3u8视频
详细请移步简书[Python文集](http://www.jianshu.com/nb/18442681)
diff --git a/gongzhonghao.jpeg b/gongzhonghao.jpeg
new file mode 100644
index 0000000..0906f8a
Binary files /dev/null and b/gongzhonghao.jpeg differ
diff --git "a/\347\210\254\350\231\253\345\260\217demo/29 PythonCeHui.py" "b/\347\210\254\350\231\253\345\260\217demo/29 PythonCeHui.py"
new file mode 100644
index 0000000..6c5de66
--- /dev/null
+++ "b/\347\210\254\350\231\253\345\260\217demo/29 PythonCeHui.py"
@@ -0,0 +1,131 @@
+import sys
+import os, re, shutil, time, collections, json
+
+from html.parser import HTMLParser
+from xml.etree import ElementTree as ETree
+
+import itchat
+from itchat.content import *
+
+msg_store = collections.OrderedDict()
+timeout = 600
+sending_type = {'Picture': 'img', 'Video': 'vid'}
+data_path = 'data'
+nickname = ''
+bot = None
+
+if __name__ == '__main__':
+ if not os.path.exists(data_path):
+ os.mkdir(data_path)
+ # if the QR code doesn't show correctly, you can try to change the value
+ # of enableCdmQR to 1 or -1 or -2. It nothing works, you can change it to
+ # enableCmdQR=True and a picture will show up.
+ bot = itchat.new_instance()
+ bot.auto_login(hotReload=True, enableCmdQR=2)
+ nickname = bot.loginInfo['User']['NickName']
+
+def clear_timeouted_message():
+ now = time.time()
+ count = 0
+ for k, v in list(msg_store.items()):
+ if now - v['ReceivedTime'] > timeout:
+ count += 1
+ else:
+ break
+ for i in range(count):
+ item = msg_store.popitem(last=False)
+
+def get_sender_receiver(msg):
+ sender = nickname
+ receiver = nickname
+ if msg['FromUserName'][0:2] == '@@': # group chat
+ sender = msg['ActualNickName']
+ m = bot.search_chatrooms(userName=msg['FromUserName'])
+ if m is not None:
+ receiver = m['NickName']
+ elif msg['ToUserName'][0:2] == '@@': # group chat by myself
+ if 'ActualNickName' in msg:
+ sender = msg['ActualNickName']
+ else:
+ m = bot.search_friends(userName=msg['FromUserName'])
+ if m is not None:
+ sender = m['NickName']
+ m = bot.search_chatrooms(userName=msg['ToUserName'])
+ if m is not None:
+ receiver = m['NickName']
+ else: # personal chat
+ m = bot.search_friends(userName=msg['FromUserName'])
+ if m is not None:
+ sender = m['NickName']
+ m = bot.search_friends(userName=msg['ToUserName'])
+ if m is not None:
+ receiver = m['NickName']
+ return HTMLParser().unescape(sender), HTMLParser().unescape(receiver)
+
+def print_msg(msg):
+ msg_str = ' '.join(msg)
+ print(msg_str)
+ return msg_str
+
+def get_whole_msg(msg, download=False):
+ sender, receiver = get_sender_receiver(msg)
+ if len(msg['FileName']) > 0 and len(msg['Url']) == 0:
+ if download: # download the file into data_path directory
+ fn = os.path.join(data_path, msg['FileName'])
+ msg['Text'](fn)
+ if os.path.getsize(fn) == 0:
+ return []
+ c = '@%s@%s' % (sending_type.get(msg['Type'], 'fil'), fn)
+ else:
+ c = '@%s@%s' % (sending_type.get(msg['Type'], 'fil'), msg['FileName'])
+ return ['[%s]->[%s]:' % (sender, receiver), c]
+ c = msg['Text']
+ if len(msg['Url']) > 0:
+ try: # handle map label
+ content_tree = ETree.fromstring(msg['OriContent'])
+ if content_tree is not None:
+ map_label = content_tree.find('location')
+ if map_label is not None:
+ c += ' ' + map_label.attrib['poiname']
+ c += ' ' + map_label.attrib['label']
+ except:
+ pass
+ url = HTMLParser().unescape(msg['Url'])
+ c += ' ' + url
+ return ['[%s]->[%s]: %s' % (sender, receiver, c)]
+
+@bot.msg_register([TEXT, PICTURE, MAP, CARD, SHARING, RECORDING,
+ ATTACHMENT, VIDEO, FRIENDS], isFriendChat=True, isGroupChat=True)
+def normal_msg(msg):
+ print_msg(get_whole_msg(msg))
+ now = time.time()
+ msg['ReceivedTime'] = now
+ msg_id = msg['MsgId']
+ msg_store[msg_id] = msg
+ clear_timeouted_message()
+
+@bot.msg_register([NOTE], isFriendChat=True, isGroupChat=True)
+def note_msg(msg):
+ print_msg(get_whole_msg(msg))
+ content = HTMLParser().unescape(msg['Content'])
+ try:
+ content_tree = ETree.fromstring(content)
+ except Exception:
+ # invent/remove to chatroom
+ return
+ if content_tree is None:
+ return
+ revoked = content_tree.find('revokemsg')
+ if revoked is None:
+ return
+ old_msg_id = revoked.find('msgid').text
+ old_msg = msg_store.get(old_msg_id)
+ if old_msg is None:
+ return
+ msg_send = get_whole_msg(old_msg, download=True)
+ for m in msg_send:
+ bot.send(m, toUserName='filehelper')
+ clear_timeouted_message()
+
+if __name__ == '__main__':
+ bot.run()
\ No newline at end of file
diff --git "a/\347\210\254\350\231\253\345\260\217demo/30 PythonZhuanFa.py" "b/\347\210\254\350\231\253\345\260\217demo/30 PythonZhuanFa.py"
new file mode 100644
index 0000000..dd2d199
--- /dev/null
+++ "b/\347\210\254\350\231\253\345\260\217demo/30 PythonZhuanFa.py"
@@ -0,0 +1,174 @@
+
+import sys
+reload(sys)
+sys.setdefaultencoding('UTF8')
+
+import os, re, shutil, time, collections, json
+import requests
+from HTMLParser import HTMLParser
+from xml.etree import ElementTree as ETree
+import hashlib
+
+import itchat
+from itchat.content import *
+
+sending_type = {'Picture': 'img', 'Video': 'vid'}
+data_path = 'data'
+group_uin = {u'技术群1': '42235582@chatroom',
+ u'技术群2': '2424504406@chatroom',
+ u'技术群3': '6203978346@chatroom'}
+publishers = {u'技术群1': u'[阴险]',
+ u'技术群2': u'[菜刀]',
+ u'技术群3': u'[月亮]'}
+subscribers = [u'技术群1', u'技术群2', u'技术群3']
+nickname = ''
+bot = None
+as_chat_bot = True
+
+if __name__ == '__main__':
+ if not os.path.exists(data_path):
+ os.mkdir(data_path)
+ # if the QR code doesn't show correctly, you can try to change the value
+ # of enableCdmQR to 1 or -1 or -2. It nothing works, you can change it to
+ # enableCmdQR=True and a picture will show up.
+ bot = itchat.new_instance()
+ bot.auto_login(hotReload=True, enableCmdQR=2)
+ nickname = bot.loginInfo['User']['NickName']
+
+# tuling chat bot
+def talks_robot(info):
+ api_url = 'http://www.tuling123.com/openapi/api'
+ apikey = ''
+ data = {'key': apikey, 'info': info.lower()}
+ req = requests.post(api_url, data=data, timeout=10).text
+ replys = json.loads(req)['text']
+ return replys
+
+def get_sender_receiver(msg):
+ sender = nickname
+ receiver = nickname
+ if msg['FromUserName'][0:2] == '@@': # group chat
+ sender = msg['ActualNickName']
+ m = bot.search_chatrooms(userName=msg['FromUserName'])
+ if m is not None:
+ receiver = m['NickName']
+ elif msg['ToUserName'][0:2] == '@@': # group chat by myself
+ if 'ActualNickName' in msg:
+ sender = msg['ActualNickName']
+ else:
+ m = bot.search_friends(userName=msg['FromUserName'])
+ if m is not None:
+ sender = m['NickName']
+ m = bot.search_chatrooms(userName=msg['ToUserName'])
+ if m is not None:
+ receiver = m['NickName']
+ else: # personal chat
+ m = bot.search_friends(userName=msg['FromUserName'])
+ if m is not None:
+ sender = m['NickName']
+ m = bot.search_friends(userName=msg['ToUserName'])
+ if m is not None:
+ receiver = m['NickName']
+ return HTMLParser().unescape(sender), HTMLParser().unescape(receiver)
+
+def print_msg(msg):
+ msg_str = ' '.join(msg)
+ print msg_str
+ return msg_str
+
+def get_whole_msg(msg, prefix, download=False):
+ if len(msg['FileName']) > 0 and len(msg['Url']) == 0:
+ if download: # download the file into data_path directory
+ fn = os.path.join(data_path, msg['FileName'])
+ msg['Text'](fn)
+ if os.path.getsize(fn) == 0:
+ return []
+ c = '@%s@%s' % (sending_type.get(msg['Type'], 'fil'), fn)
+ else:
+ c = '@%s@%s' % (sending_type.get(msg['Type'], 'fil'), msg['FileName'])
+ return ['%s:' % (prefix), c]
+ c = msg['Text']
+ if len(msg['Url']) > 0:
+ if len(msg['OriContent']) > 0:
+ try: # handle map label
+ content_tree = ETree.fromstring(msg['OriContent'])
+ if content_tree is not None:
+ map_label = content_tree.find('location')
+ if map_label is not None:
+ c += ' ' + map_label.attrib['poiname']
+ c += ' ' + map_label.attrib['label']
+ except:
+ pass
+ url = HTMLParser().unescape(msg['Url'])
+ c += ' ' + url
+ return ['%s: %s' % (prefix, c)]
+
+@bot.msg_register([TEXT], isFriendChat=True, isGroupChat=False)
+def personal_msg(msg):
+ global as_chat_bot
+ text = msg['Text'].strip()
+ if text == u'闭嘴':
+ as_chat_bot = False
+ if text == u'张嘴吃药':
+ as_chat_bot = True
+ return talks_robot(text)
+
+@bot.msg_register([FRIENDS])
+def accept_friend(msg):
+ bot.add_friend(msg['RecommendInfo']['UserName'], 3)
+
+@bot.msg_register([TEXT, PICTURE, MAP, SHARING, RECORDING, ATTACHMENT, VIDEO],
+ isFriendChat=False, isGroupChat=True)
+def group_msg(msg):
+ # chat bot functionality
+ global as_chat_bot
+ if 'IsAt' in msg and msg['IsAt'] == True and \
+ msg['Type'] == 'Text' and \
+ msg['ToUserName'][0:2] != '@@' and \
+ msg['Text'].find(u'@' + nickname) >= 0:
+ text = msg['Text'].replace(u'@' + nickname, '').strip()
+ if text == u'shit':
+ as_chat_bot = False
+ return
+ if as_chat_bot:
+ info = talks_robot(text)
+ if info.find('No Know') >= 0:
+ return
+ if info.find('No Can') >= 0:
+ return
+ if info.find('Sorry') >= 0:
+ return
+ return info
+ return
+ # forwarding functionality
+ group = msg['FromUserName']
+ if msg['ToUserName'][0:2] == '@@': # message sent by myself
+ group = msg['ToUserName']
+sender, receiver = get_sender_receiver(msg)
+if sender == '':
+ sender = nickname
+ # check if the message is from the publisher groups
+ if receiver not in publishers: # if not in the publishers, do nothing
+ return
+# turn on the chat bot if this magic happens
+if msg['Type'] == 'Text' and \
+ hashlib.sha256(msg['Text']).hexdigest()[-2:] == '23':
+ as_chat_bot = True
+# process message and send it to all the subscribed groups
+prefix = '%s[%s]' % (publishers[receiver], sender)
+msg_send = get_whole_msg(msg, prefix=prefix, download=True)
+if len(msg_send) == 0:
+ return
+ print_msg(msg_send)
+ for tosend in subscribers:
+ room = bot.search_chatrooms(name=tosend)
+ for r in room:
+ if r['UserName'] == group: # don't send back to the source
+ continue
+ if r['NickName'] != tosend: # check group name exact match
+ continue
+ for m in msg_send: # iterate messages (for images, videos, and files)
+ bot.send(m, toUserName=r['UserName'])
+
+if __name__ == '__main__':
+ bot.run()
diff --git "a/\347\210\254\350\231\253\345\260\217demo/31 \344\270\213\350\275\275bilibili\350\247\206\351\242\221.py" "b/\347\210\254\350\231\253\345\260\217demo/31 \344\270\213\350\275\275bilibili\350\247\206\351\242\221.py"
new file mode 100644
index 0000000..85e2e27
--- /dev/null
+++ "b/\347\210\254\350\231\253\345\260\217demo/31 \344\270\213\350\275\275bilibili\350\247\206\351\242\221.py"
@@ -0,0 +1,60 @@
+import requests
+from lxml import html
+import re
+import urllib3
+urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
+
+def star(url):
+ url2 = "https://api.bilibili.com/x/player/playurl?avid={avid}&cid={cid}&qn=32&type=&otype=json"
+ headers2 = {
+ "host": "",
+ "Referer": "https://www.bilibili.com",
+ "User-Agent": "Mozilla/5.0(Windows NT 10.0;WOW64) AppleWebKit/537.36(KHTML,likeGecko)Chrome/63.0.3239.132Safari/537.36"
+ }
+
+ avid = re.findall("video/av(.+)\?", url)
+ print(avid)
+ cid ,name = get_cid(avid[0])
+ print(cid,name)
+ flv_url , size = get_flvurl(url2.format(avid=avid[0],cid=cid))
+ shuju = size / 1024 / 1024
+ print("本视频大小为：%.2fM" % shuju)
+
+ h = re.findall("https://(.+)com",flv_url)
+ host = h[0]+"com"
+
+ headers2["host"] = host
+ res = requests.get(flv_url,headers=headers2,stream=True, verify=False)
+ print(res.status_code)
+ save_movie(res,name)
+
+def get_cid(aid):#获得cid
+ header = {
+ 'host': 'api.bilibili.com',
+ 'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:6.0) Gecko/20100101 Firefox/6.0'
+ }
+ url = "https://api.bilibili.com/x/player/pagelist?aid={aid}&jsonp=jsonp".format(aid=aid)
+ response = requests.get(url,headers=header).json()
+ # print(response["data"])
+ # 这个地方设置index是因为下载集合里面的视频,顺序,0代表下载第一个视频,1代表下载集合里面第二个视频,2,3,4...依次类推
+ index = 0
+ return response["data"][index]["cid"] ,response["data"][index]["part"]
+def get_flvurl(url):#获得视频真实flv地址
+ header = {'host': 'api.bilibili.com',
+ 'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:6.0) Gecko/20100101 Firefox/6.0'}
+
+ response = requests.get(url,headers=header).json()
+ return response["data"]["durl"][0]["url"],response["data"]["durl"][0]["size"]
+def save_movie(res,name):#保存视频
+ chunk_size = 1024
+ with open("{name}.flv".format(name = name),"wb") as f:
+ for data in res.iter_content(1024):
+ f.write(data)
+
+
+if __name__ == "__main__":
+ # 把下面的av后面的'583959574'在要下载的视频集合里面找到就可以下载视频了
+ url = "https://www.bilibili.com/video/av583959574?spm_id_from=333.334.b_62696c695f646f756761.5"
+ star(url)
+
+
diff --git "a/\347\210\254\350\231\253\345\260\217demo/32 m3u8.py" "b/\347\210\254\350\231\253\345\260\217demo/32 m3u8.py"
new file mode 100644
index 0000000..53f8f46
--- /dev/null
+++ "b/\347\210\254\350\231\253\345\260\217demo/32 m3u8.py"
@@ -0,0 +1,69 @@
+import requests
+import re
+from Crypto.Cipher import AES
+
+def m3u8(url):
+ header = {
+ 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36'
+ }
+ # requests得到m3u8文件内容
+ content = requests.get(url, headers=header).text
+ if "#EXTM3U" not in content:
+ print("这不是一个m3u8的视频链接！")
+ return False
+ if "EXT-X-KEY" not in content:
+ print("没有加密")
+ return False
+
+ # 使用re正则得到key和视频地址
+ jiami = re.findall('#EXT-X-KEY:(.*)',content)
+ key = re.findall('URI="(.*)"', jiami[0])
+ vi = re.findall('IV=(.*)', jiami[0])[0]
+
+ # 得到每一个ts视频链接
+
+ # tslist = re.findall('EXTINF:(.*), (. *)',content.replace(' ', '').replace(r'\n', ''))
+ tslist = re.findall('v.f240.ts(.*)',content)
+
+ newlist = []
+ for i in tslist:
+ newlist.append("v.f240.ts" + i)
+ # print(newlist)
+ # 得到key的链接并请求得到加密的key值
+ keyurl = key[0]
+ keycontent = requests.get(keyurl, headers=header).content
+
+ # 得到每一个完整视频的链接地址
+ base_url = url.replace(url.split('/')[-1], '')
+ # print(base_url)
+ tslisturl = []
+ for i in newlist:
+ tsurl = base_url + i
+ tslisturl.append(tsurl)
+
+ # 得到解密方法，这里要导入第三方库 pycrypto
+ # 这里有一个问题，安装pycrypto成功后，导入from Crypto.Cipher import AES报错
+ # 找到使用python环境的文件夹，在Lib文件夹下有一个 site-packages 文件夹，里面是我们环境安装的包。
+ # 找到一个crypto文件夹，打开可以看到 Cipher文件夹，此时我们将 crypto文件夹改为 Crypto 即可使用了
+ # 必须添加b'0000000000000000'，防止报错ValueError: IV must be 16 bytes long
+ cryptor = AES.new(keycontent, AES.MODE_CBC, b'0000000000000000')
+
+ # for循环获取视频文件
+ for i in tslisturl:
+ print(i)
+ res = requests.get(i, header)
+ # 使用解密方法解密得到的视频文件
+ cont = cryptor.decrypt(res.content)
+ # 以追加的形式保存为mp4文件，mp4可以随意命名，这里命名为小鹅通视频下载测试
+ with open('14-搜索组件界面实现.mp4', 'ab+') as f:
+ f.write(cont)
+ return True
+
+if __name__ == '__main__':
+ # 这个是网页上查到的小鹅通的卖u8地址
+ # url = "https://1252524126.vod2.myqcloud.com/9764a7a5vodtransgzp1252524126/91c29aad5285890807164109582/drm/v.f146750.m3u8"
+ # url = "https://1258102968.vod2.myqcloud.com/ed7d8254vodtranscq1258102968/a61912e43701925923160746329/drm/v.f240.m3u8?t=62dfad73&us=DYws6oOg3A&sign=1d4381d06b276e87eae478a23f3d6375"
+ url = "https://1258102968.vod2.myqcloud.com/ed7d8254vodtranscq1258102968/a3ae8ff93701925923160630524/drm/v.f240.m3u8?t=62dfaf5a&us=RquNSsL6XT&sign=8bec9ca974f9413c9bad7a9e8d620ae2"
+ pd = m3u8(url)
+ if pd:
+ print('视频下载完成！')
\ No newline at end of file