def get_parse_dict(danmaku_list):
logging.info("Starting parsing sentences in Danmaku...")
parse_dict = dict()
jieba.load_userdict(constants.USER_DICT_PATH)
emotion_dict_path = os.path.join(FileUtil.get_project_root_path(),
"WordSegment", "emotion_dict.txt")
emotion_dict = load_emotion_dict(emotion_dict_path)
for danmaku in danmaku_list:
rowId = danmaku.rowId
if danmaku.content is not None:
words = wordSegment(emotion_dict, danmaku.content)
parse_dict[rowId] = words
else:
parse_dict[rowId] = None
logging.info("parse dictionary has generated!")
return parse_dict
parse_dict = dict()
jieba.load_userdict(constants.USER_DICT_PATH)
emotion_dict_path = os.path.join(FileUtil.get_project_root_path(),
"WordSegment", "emotion_dict.txt")
emotion_dict = load_emotion_dict(emotion_dict_path)
for danmaku in danmaku_list:
rowId = danmaku.rowId
if danmaku.content is not None:
words = wordSegment(emotion_dict, danmaku.content)
parse_dict[rowId] = words
else:
parse_dict[rowId] = None
logging.info("parse dictionary has generated!")
return parse_dict
if __name__ == "__main__":
# 测试代码
danmaku_list = getDataSource(constants.DATASOURCE)
emotion_dict_path = os.path.join(FileUtil.get_project_root_path(),
"WordSegment", "emotion_dict.txt")
emotion_dict = load_emotion_dict(emotion_dict_path)
for (key, value_set) in emotion_dict.items():
print key, u"\t", u"\t".join(value for value in value_set), u"\n"
for danmaku in danmaku_list:
if danmaku.content is None:
continue
words = wordSegment(emotion_dict, danmaku.content)
for word in words:
print word.content
for barrage_tuple in barrages:
barrage = Barrage(play_timestamp=barrage_tuple[0],
type=barrage_tuple[1],
font_size=barrage_tuple[2],
font_color=barrage_tuple[3],
unix_timestamp=barrage_tuple[4],
pool=barrage_tuple[5],
sender_id=barrage_tuple[6],
row_id=barrage_tuple[7],
content=barrage_tuple[8])
barrage_list.append(barrage)
return barrage_list
if __name__ == "__main__":
# 测试代码，测试从xml文件中读取的数据。
# danmakuList = getDanmakuListFromTxtFile(FILE_PATH)
# for danmaku in danmakuList:
# print danmaku.videoSecond, u"\t", danmaku.content
# 将xml文件的弹幕数据读取出来，排序后写入当前的文件夹下。
# gen_sorted_danmaku_file_from_xml(os.path.join(FileUtil.get_project_root_path(), "data", "movie", "2065063.xml"))
# 从弹幕的live数据中读取信息。
danmaku_list = getDanmakuListFromLiveTextFile(
os.path.join(FileUtil.get_project_root_path(), "data", "AlphaGo",
"bilibili", "2016-03-09.txt"))
for danmaku in danmaku_list:
print str(danmaku.videoSecond
), u"\t", danmaku.senderId, u"\t", danmaku.content, u"\n"