def _get_album_comment_data(self, album_info):
'''获取指定相册的评论数据
'''
if not self.can_access:
return
comment_url = "https://h5.qzone.qq.com/proxy/domain/app.photo.qzone.qq.com/cgi-bin/app/cgi_pcomment_xml_v2"
payload = {
"inCharset": "utf-8", # inCharset 必选
"outCharset": "utf-8", # outCharset 必选
"g_tk": self._account_info.g_tk,
"hostUin": self._account_info.target_uin,
"uin": self._account_info.self_uin,
"topicId": album_info.id, # topicId 必选，相册id
"order": "1",
"start": "0",
"num": "0" # num最大可设定为100
}
num = 100
start = 0
while True:
payload["start"] = "%s" % start
payload["num"] = "%s" % num
r = self._account_info.get_url(comment_url, params=payload)
json_data = get_json_data_from_response(r.text)
if "comments" not in json_data["data"] or len(
json_data["data"]["comments"]) == 0:
break
current_num = len(json_data["data"]["comments"])
photo_comment = PhotoComment(json_data, start, start + current_num,
self._directory, album_info.directory,
self._account_info)
photo_comment.export()
start += current_num
if start == 0:
print("get 0 comment, try to find comments by traversing album")
print(str(album_info), "comment[%d] done" % start)
return start
def _get_album_photo_data(self, album_info, need_get_comment=False):
'''获取相册中照片数据
'''
if not self.can_access:
return
print("process album, name: %s\tid: %s" %
(album_info.name, album_info.id))
list_photo_url = "https://h5.qzone.qq.com/proxy/domain/photo.qzone.qq.com/fcgi-bin/cgi_list_photo"
floatview_photo_list = "https://h5.qzone.qq.com/proxy/domain/photo.qzone.qq.com/fcgi-bin/cgi_floatview_photo_list_v2"
start = 0
num = 500
current_num = num
list_photo_payload = {
"inCharset": "utf-8",
"outCharset": "utf-8",
"g_tk": self._account_info.g_tk,
"hostUin": self._account_info.target_uin,
"uin": self._account_info.self_uin,
"topicId": album_info.id,
"pageStart": "%d" % start,
"pageNum": "%d" % current_num,
}
floatview_photo_payload = {
"g_tk": self._account_info.g_tk,
"topicId": album_info.id,
"hostUin": self._account_info.target_uin,
"uin": self._account_info.self_uin,
"fupdate": "1",
"plat": "qzone",
"source": "qzone",
"cmtNum": "99", # 必选
"sortOrder": "1",
"need_private_comment": "1",
"inCharset": "utf-8",
"outCharset": "utf-8",
"appid": "4",
"isFirst": "1",
"picKey": "unknown",
"postNum": "0" # 获取后续照片数量
}
ttt = '''{"data": {"comments":[]}}'''
single_comment_data = json.loads(ttt)
comment_exported_num = 0
total_comment_num = 0
loop_num = math.ceil(album_info.photo_num / num)
for i in range(loop_num):
start = i * num
current_num = num if i < loop_num - 1 else album_info.photo_num - i * num
list_photo_payload["pageStart"] = "%d" % start
list_photo_payload["pageNum"] = "%d" % current_num
r = self._account_info.get_url(list_photo_url,
params=list_photo_payload)
json_data = get_json_data_from_response(r.text)
photo_parser = PhotoParser(json_data, start, start + current_num,
self._directory, album_info.directory)
photo_parser.export()
# 获取原图及视频url
if "photoList" in json_data["data"] and json_data["data"]["photoList"] \
and len(json_data["data"]["photoList"]) > 0:
floatview_photo_payload["picKey"] = json_data["data"][
"photoList"][0]["lloc"]
floatview_photo_payload["postNum"] = "%d" % (current_num - 1)
r = self._account_info.get_url(floatview_photo_list,
params=floatview_photo_payload)
floatview_json_data = get_json_data_from_response(r.text)
photo_parser = PhotoParser(floatview_json_data, start,
start + current_num,
self._directory,
album_info.directory, True)
photo_parser.export()
# 获取评论数据
if need_get_comment:
for photo in json_data["data"]["photoList"]:
pic_comment_num = photo["forum"] or 0
if pic_comment_num == 0:
continue
print("find %d comment(s) in %s" %
(pic_comment_num, photo["lloc"]))
# 评论数可能显示错误
floatview_photo_payload["cmtNum"] = "%d" % (
pic_comment_num if pic_comment_num > 99 else 99)
floatview_photo_payload["picKey"] = photo["lloc"]
floatview_photo_payload["postNum"] = "0"
r = self._account_info.get_url(
floatview_photo_list,
params=floatview_photo_payload)
floatview_json_data = get_json_data_from_response(
r.text)
if not ("single" in floatview_json_data["data"]
and floatview_json_data["data"]["single"]):
continue
comment_data = floatview_json_data["data"]["single"][
"comments"]
single_comment_data["data"]["comments"] += comment_data
pic_comment_num = len(comment_data)
total_comment_num += pic_comment_num
if total_comment_num > 100 + comment_exported_num:
photo_comment = PhotoComment(
single_comment_data, comment_exported_num,
total_comment_num, self._directory,
album_info.directory, self._account_info)
photo_comment.export()
single_comment_data["data"]["comments"] = []
comment_exported_num = total_comment_num
random_sleep(0, 1)
random_sleep(1, 2)
# 导出剩余评论数据
if need_get_comment:
if comment_exported_num < total_comment_num:
photo_comment = PhotoComment(single_comment_data,
comment_exported_num,
total_comment_num,
self._directory,
album_info.directory,
self._account_info)
photo_comment.export()
print("get %d comment(s) in %s" %
(total_comment_num, album_info.name))
print(str(album_info), "photo data done")