def parse_recent_visit(self, file_path, time_step):
# 必须新开线程执行
while True:
try:
url, _ = self.get_main_page_url()
res = self.req.get(url=url, headers=self.headers)
content = json.loads(self.get_json(
res.content.decode("utf-8")))
visit_data = content['data']['module_3']['data']
if 'items' in visit_data:
visit_list = visit_data['items']
for item in visit_list:
self.visit_list.append(
dict(qq=item['uin'],
time=util.get_full_time_from_mktime(
item['time']),
name=item['name']))
visit_df = pd.DataFrame(self.visit_list)
visit_df.drop_duplicates(inplace=True)
visit_df.to_excel(file_path, index=False)
time.sleep(time_step)
except BaseException:
print("获取最近访客出错")
exit(3)
def __init__(self):
self.sp = QQZoneSpider(use_redis=False,
debug=False,
from_client=True,
mood_num=20)
warm_tip = "****************************************\n" \
"**************QQ空间抽奖小程序***************\n" \
"****************************************"
self.output(warm_tip)
self.output("请输入获取最近访客的时间间隔，默认为60秒")
time_step = input()
try:
time_step = int(time_step)
except:
time_step = 60
visit_file_name = "最近访客" + get_full_time_from_mktime(int(
time.time())) + ".xlsx"
self.output("最近访客文件名:" + visit_file_name)
try:
self.sp.login_with_qr_code()
self.output("用户" + self.sp.username + "登陆成功！")
except BaseException:
self.output("用户登陆失败！请检查网络连接或稍后再试！")
exit(1)
visit_t = threading.Thread(target=self.sp.parse_recent_visit,
args=[visit_file_name, time_step])
visit_t.start()
self.output("正在获取最近的说说...")
url_mood = self.sp.get_mood_url()
url_mood = url_mood + '&uin=' + str(self.sp.username)
self.content_list = self.get_content_list(url_mood, 0)
self.content_list += self.get_content_list(url_mood, 20)
self.content_list += self.get_content_list(url_mood, 40)
self.output('------------------------')
self.output("最近的60条说说:")
for item in self.content_list:
content = item['content']
if len(content) > 20:
content = content[0:20] + '。。。'
item_str = '|' + str(item['order']) + '|' + content
self.output(item_str)
while True:
try:
self.output('------------------------')
self.output("**以下输入请全部只输入数字！按回车键结束输入！**")
self.output("**输入Q退出本程序**")
is_digit = False
while not is_digit:
self.output('请输入您要选择的说说序号:')
mood_order = input()
is_digit = self.check_input(mood_order)
mood_order = int(mood_order)
if mood_order > len(self.content_list):
pos = (math.ceil(mood_order / 20) - 1) * 20
mood_order = mood_order % 20
t1 = threading.Thread(target=self.get_all,
args=(url_mood, pos, mood_order))
t1.setDaemon(True)
t1.start()
else:
unikey = self.content_list[mood_order - 1]
key = unikey['unikey']
tid = unikey['tid']
t2 = threading.Thread(target=self.start_like_cmt_thread,
args=(key, tid))
t2.setDaemon(True)
t2.start()
is_digit = False
while not is_digit:
self.output('请输入抽奖的类型，1-点赞；2-评论；(其它)-我全都要！ ：')
type = input()
is_digit = self.check_input(type)
is_digit = False
while not is_digit:
self.output('请选择抽奖的用户数量：')
user_num = input()
is_digit = self.check_input(user_num)
# 等待线程运行完
try:
t1.join()
t2.join()
self.like_t.join()
self.cmt_t.join()
except:
pass
self.type = int(type)
self.user_num = int(user_num)
self.file_name = self.content_list[mood_order - 1]['content']
if len(self.file_name) > 10:
self.file_name = self.file_name[:10]
self.file_name = re.sub('[^\w\u4e00-\u9fff]+', '',
self.file_name)
if len(self.file_name) <= 0:
self.file_name = str(mood_order)
print("说说:", self.file_name)
self.do_raffle()
cmt_df = pd.DataFrame(self.cmt_list)
like_df = pd.DataFrame(self.like_list)
cmt_df.to_excel("评论-" + self.file_name + '.xlsx', index=False)
like_df.to_excel("点赞-" + self.file_name + '.xlsx', index=False)
except BaseException as e:
if str(e) == '2':
exit(2)
else:
self.output('----------------------')
print(e)
self.output("未知错误，请重新尝试")
self.output('----------------------')
def clean_friend_data(self):
"""
清洗好友数据，生成csv
:return:
"""
try:
if len(self.friend_list) == 0:
self.load_friend_data()
friend_total_num = len(self.friend_list)
print("valid friend num:", friend_total_num)
friend_list_df = pd.DataFrame(self.friend_list)
self.friend_detail_list = []
if friend_total_num == 0:
print("该用户没有好友")
return False
for friend in self.friend_detail:
try:
friend_uin = friend['friendUin']
add_friend_time = friend['addFriendTime']
img = friend_list_df.loc[friend_list_df['uin'] ==
friend_uin, 'img'].values[0]
nick = friend['nick']
nick_name = remove_special_tag(nick[str(friend_uin)])
common_friend_num = len(friend['common']['friend'])
common_group_num = len(friend['common']['group'])
common_group_names = friend['common']['group']
self.friend_detail_list.append(
dict(uin=self.username,
friend_uin=friend_uin,
add_friend_time=add_friend_time,
nick_name=nick_name,
common_friend_num=common_friend_num,
common_group_num=common_group_num,
common_group_names=common_group_names,
img=img))
except BaseException as e:
if self.debug:
print("单向好友:", friend)
self.friend_detail_list.append(
dict(uin=0,
friend_uin=friend['friendUin'],
add_friend_time=0,
nick_name='单向好友',
common_friend_num=0,
common_group_num=0,
common_group_names='',
img=''))
friend_df = pd.DataFrame(self.friend_detail_list)
friend_df.sort_values(by='add_friend_time', inplace=True)
friend_df['add_friend_time2'] = friend_df['add_friend_time'].apply(
lambda x: util.get_full_time_from_mktime(x))
friend_df.fillna('', inplace=True)
if self.export_excel:
friend_df.to_excel(self.FRIEND_DETAIL_EXCEL_FILE_NAME)
if self.export_csv:
friend_df.to_csv(self.FRIEND_DETAIL_LIST_FILE_NAME)
if self.debug:
print("Finish to clean friend data...")
print("File Name:", self.FRIEND_DETAIL_LIST_FILE_NAME)
self.friend_df = friend_df
return True
except BaseException as e:
self.format_error(e, "Failed to parse friend_info")
return False