def getSubmitNumber(self):
url = "%s?mid=%s&page=1&pagesize=1" % (bilibili.submitUrl, str(
self.mid))
# print(url)
try:
return bilibili.getDict(bilibili.getHTMLText(url))['data']['count']
except bException.bError as e:
raise e
def getSubRepliesNum(self):
try:
url = "%s?pn=1&type=%d&oid=%d&sort=1&ps=1&root=%d" % (
bilibili.subreplyUrl, 1, self.aid, self.rid)
res = bilibili.getDict(bilibili.getHTMLText(url))
return res['data']['page']['count']
except bException.bError as e:
raise e
def getHistoryDanmaku(self, date):
url = "%s?type=1&date=%s&oid=%d" % (bilibili.historyDanmakuUrl,
date.strftime("%Y-%m-%d"),
self.getOid())
print(url)
try:
return self.__getDanmakuHelper(
bilibili.getHTMLText(url, bilibili.login_headers))
except bException.bError as e:
raise e
def getReply(self, page=1, sort=1):
try:
url = "%s?pn=%d&type=%d&oid=%d&sort=%d" % (bilibili.replyUrl, page,
1, self.aid, sort)
# print(url)
res = bilibili.getDict(bilibili.getHTMLText(url))
return self.__getReplyHelper(res['data']['replies'])
except bException.bError as e:
raise e
def getReplyInfo(self):
try:
url = "%s?pn=%d&type=%d&oid=%d&sort=%d" % (bilibili.replyUrl, 1, 1,
self.getOid(), 1)
res = bilibili.getDict(bilibili.getHTMLText(url))
resDict = {}
resDict['acount'] = res['data']['page']['acount']
resDict['count'] = res['data']['page']['count']
except bException.bError as e:
raise e
def getSubmitEx(self):
url = "%s?mid=%s&page=1&pagesize=%s" % (
bilibili.submitUrl, str(self.mid), str(self.getSubmitNumber()))
# print(url)
submitDict = ""
resList = []
try:
submitDict = bilibili.getDict(bilibili.getHTMLText(url))
# print(submitDict)
vlist = submitDict['data']['vlist']
# 遍历每一个投稿
for item in vlist:
aid = item['aid']
submitDetailDict = {}
detail = {}
try:
# 取得每一个投稿的详细信息
url = "%s?aid=%s" % (bilibili.submitDetailUrl, str(aid))
submitDetailDict = bilibili.getDict(
bilibili.getHTMLText(url))
detail = submitDetailDict['data']
except:
return []
resList.append(
submit.submitEx(item['typeid'], item['play'],
item['title'], item['created'],
item['video_review'], item['favorites'],
aid, self.mid, detail['reply'],
detail['coin'], detail['like'],
detail['his_rank']))
except:
return resList
return resList
def getUpper(mid, cfg, proxy={}):
url = "%s?vmid=%s" % (bilibili.upInfoUrl, str(mid))
response = bilibili.getHTMLText(url)
if response == None:
return None
status_code = response[0]
if status_code != 200:
return status_code
# 获取基本信息
updict = bilibili.getDict(response[1])
#----------------------------------------------------------
url = bilibili.upInfoDetailUrl
postData = {
'csrf': cfg.getAttr('csrf'), #'099defc050cb8ad2827ca8493d06ab91'
'mid': mid
}
# 获取用户详细信息
r = requests.post(bilibili.upInfoDetailUrl,
data=postData,
headers=bilibili.detail_headers,
proxies=proxy)
status_code = r.status_code
# 获取失败
if status_code != 200:
return status_code
res = bilibili.getDict(r.text)
# 这里对regtime进行特殊处理是因为实践中发现regtime似乎并不是每个用户都有
# 有些特别的用户获取不到regtime. 另外有些字段获取的到不过为空或者其他什么奇怪的东西就是啦..
regtime = 0
if 'regtime' in res['data']:
regtime = res['data']['regtime']
try:
return upper(updict['data']['mid'], updict['data']['follower'],
res['data']['name'], res['data']['face'], regtime,
res['data']['sex'],
res['data']['level_info']['current_level'],
res['data']['vip']['vipType'],
res['data']['vip']['vipStatus'])
except:
return None
def getAllDanmakus(self, path):
# 获取当前时间
today = datetime.datetime.now()
# 获取视频发布时间
createdDate = datetime.datetime.fromtimestamp(self.createdTime)
# 获取两日间隔
daysGap = today - createdDate
fileobj = open(path, 'w', encoding="UTF-8")
# 写入文件头
fileobj.write('''
<?xml version="1.0" encoding="UTF-8"?><i>
<chatserver>chat.bilibili.com</chatserver>
<mission>0</mission>
<maxlimit>%d</maxlimit>
<state>0</state>
<real_name>0</real_name>
<source>k-v</source>
''' % (self.danmaku))
#循环每一天
for i in range(0, daysGap.days):
date = createdDate + datetime.timedelta(days=i)
# 请求地址
url = "%s?type=1&date=%s&oid=%d" % (bilibili.historyDanmakuUrl,
date.strftime("%Y-%m-%d"),
self.getOid())
text = ""
print("getting %s\n" % (url))
try:
text = bilibili.getHTMLText(url, bilibili.login_headers)
except:
continue
soup = BeautifulSoup(text, 'lxml')
ds = soup.find_all('d')
s = set()
for i in ds:
s.add(str(i))
for i in s:
fileobj.write(i)
fileobj.write("</i>")
fileobj.close()
def getSubReplies(self, sort=1):
try:
url = "%s?pn=1&type=%d&oid=%d&sort=%d&ps=%d&root=%d" % (
bilibili.subreplyUrl, 1, self.aid, sort,
self.getSubRepliesNum(), self.rid)
res = bilibili.getDict(bilibili.getHTMLText(url))
repliesList = []
subRepliesDict = res['data']['replies']
for r in subRepliesDict:
nr = reply(r['content']['message'], r['member']['mid'],
r['member']['uname'], r['floor'], r['ctime'],
r['like'], r['content']['plat'], r['oid'],
r['rpid'], r['root'], self.upmid)
repliesList.append(nr)
return repliesList
except bException.bError as e:
raise e
def getOid(self):
url = "%s%s" % (bilibili.archieveUrl, str(self.aid))
text = ""
try:
text = bilibili.getHTMLText(url)
except bException.bError as e:
raise e
oidInfo = re.findall(r'"cid":[\d]*', text)
'''
突然发现有一些视频不知道为什么提取不了cid. 这些视频的普遍特征就是在B站看的时候预览
显示不出播放量。 应该是早期作♂品
'''
try:
return eval(oidInfo[0].split(':')[1])
except:
oidInfo = re.findall(r'"cid": [\d]*', text)
try:
return eval(oidInfo[0].split(':')[1])
except:
return -1
def getSubmit(self):
url = "%s?mid=%s&page=1&pagesize=%s" % (
bilibili.submitUrl, str(self.mid), str(self.getSubmitNumber()))
# print(url)
submitDict = ""
resList = []
try:
submitDict = bilibili.getDict(bilibili.getHTMLText(url))
# print(submitDict)
vlist = submitDict['data']['vlist']
# 遍历每一个投稿
for item in vlist:
resList.append(
submit.submit(item['typeid'], item['play'], item['title'],
item['created'], item['video_review'],
item['favorites'], item['aid'], self.mid))
except bException.bError as e:
raise e
return resList
def getDanmaku(self):
url = "%s?oid=%s" % (bilibili.danmakuUrl, str(self.getOid()))
text = ""
# resList = []
try:
text = bilibili.getHTMLText(url)
# soup = BeautifulSoup(text, 'lxml')
# ds = soup.find_all('d')
# # 遍历所有弹幕标签
# for item in ds:
# dproperty = item.get('p')
# dps = dproperty.split(',')
# resList.append(
# danmaku.danmaku(
# time.strftime("%Y-%m-%d %H:%M:%S",
# time.localtime(eval(dps[4]))),
# item.get_text(), eval(dps[1]), self.aid))
return self.__getDanmakuHelper(text)
except bException.bError as e:
raise e
return resList