async def __get_video_list(self, url):
"""Get video's HASH id list
Base on the url to fetch the response body and get the key data by pyquery
Demo: https://v.qq.com/x/cover/p69wlzli02uqwms/d0023ka5gj7.html
Args:
url: target video' url
"""
try:
info(f"Url: {url}")
response = await self.__async_session.get(url)
self.__list_info, self.__cover_info, self.__video_info = Parser.get_details(
response)
self.__root_path = f'{self.__root_path}/{self.__cover_info["title"]}'
info(f"Name: [{self.__root_path}]")
initPath(self.__root_path)
create_json(self.__list_info, f"{self.__root_path}/list_info.json")
create_json(self.__cover_info,
f"{self.__root_path}/cover_info.json")
create_json(self.__video_info,
f"{self.__root_path}/video_info.json")
except Exception as e:
raise e
def create_danmu_xlsx(self, title):
xlsx_path = f"{self.__root_path}/xlsx"
initPath(xlsx_path)
tmp_data = []
data_length = len(self.__results.keys())
tmp_data.append(title)
for did, item in self.__results.items():
tmp_data_bottom = []
for tid, titem in item["datas"].items():
tmp_data_bottom.append([titem[_] for _ in title])
tmp_data.extend(tmp_data_bottom)
if data_length > 2:
create_xlsx(tmp_data_bottom, title,
f"{xlsx_path}/{item['number']}.xlsx")
create_xlsx(tmp_data, title,
f"{self.__root_path}/{self.__res_xlsx_name}")
def create_word_clouds(self):
"""
demo: {"n0023msdsmb": {
"number": 29,
"targetid": "1871591968",
"datas": {
"6258341153647188912": {
"commentid": "6258341153647188912",
"content": "我来了，我困了",
"upcount": 2,
"isfriend": 0,
"isop": 0,
"isself": 0,
"timepoint": 15,
"headurl": "http://q4.qlogo.cn/g?b=qq&k=QAyiafGCYJbfG8lRKTsVTFQ&s=40",
"opername": "沉默Deheart",
"bb_bcolor": "0x985850",
"bb_head": "http://i.gtimg.cn/qqlive/images/20160602/pic_luhan.png",
"bb_level": "http://i.gtimg.cn/qqlive/images/20170104/i1483523275_1.jpg",
"content_style": ""
}}}}
"""
image_path = f"{self.__root_path}/imgs"
word_cloud_path = f"{self.__root_path}/words"
initPath(image_path)
initPath(word_cloud_path)
img_array = get_pic_array(self.__cover_info["vertical_pic_url"],
f"{image_path}/vertical_pic.png")
all_words = ""
for indexHash, item in self.__results.items():
words = " ".join(
map(lambda data: data[1]["content"],
list(item["datas"].items())))
all_words += words
create_singel_word_cloud(words,
f"{word_cloud_path}/{item['number']}",
img_array)
create_singel_word_cloud(all_words,
f"{self.__root_path}/{self.__res_png_name}",
img_array)