def update_conf(cur_file):
check_and_create(config_file)
with open(config_file, "w+") as f:
conf = {}
conf["cur_file"] = cur_file
f.write(json.dumps(conf))
f.flush()
def init_conf():
check_and_create(config_file)
with open(config_file, "r") as f:
content = f.read()
if content.strip() != "":
conf = json.loads(content)
return conf
def update_conf(host, port):
check_and_create(config_file)
with open(config_file, "w+") as f:
conf = {}
conf["host"] = host
conf["port"] = port
f.write(json.dumps(conf))
f.flush()
def init_confs(self):
check_and_create(self.config_file)
with open(self.config_file, "r") as f:
content = f.read()
if content.strip() != "":
json_content = json.loads(content)
self.confs = json_content
else:
self.confs = []
def run(self):
try:
# ~ if self.continue_on_failure is not True:
self.down_blog_source()
self.convert_to_html_file()
self.show_status_signal.emit("备份随笔结束")
except:
if self.continue_on_failure:
fileutil.check_and_create(self.backup_dir + "config.json")
with open(self.backup_dir + "config.json", "r") as f:
f.write(str(self.continue_index))
print(sys.exc_info())
self.show_status_signal.emit("系统异常:" + str(sys.exc_info()[1]) +
"\n下载失败")
def init_conf(self):
check_and_create(self.config_path)
with open(self.config_path, "r") as f:
content = f.read().strip()
# ~ print("content:" + content)
if content != "":
conf = json.loads(content)
self.le_username.setText(conf["username"])
self.le_email.setText(conf["email"])
# ~ self.le_project.setText(conf["project"])
self.conf = conf
self.path = conf["path"]
else:
self.conf = None
def on_buttonBox_accepted(self):
conf = {}
conf["username"] = self.le_username.text()
conf["email"] = self.le_email.text()
# ~ conf["project"] = self.le_project.text()
conf["path"] = self.path
check_and_create(self.config_path)
check_and_create_dir(self.path)
with open(self.config_path, "w+") as f:
f.write(json.dumps(conf))
os.chdir(self.path)
self.exec_cmd(
"cd {};git config --global user.name {};git config --global user.email {}"
.format(self.path, conf["username"], conf["email"]))
self.show_result("$ 设置帐号信息成功")
self.conf = conf
def convert_to_html_file(self):
with open(self.backup_dir + self.mood_file, "r") as f:
str1 = f.read().strip()
field_content = {}
field_content["name"] = "content"
field_content["pattern"] = r'(?<=content=").+?(?=";)'
field_publishTime = {}
field_publishTime["name"] = "publishTime"
field_publishTime["pattern"] = r"(?<=publishTime=).+?(?=;)"
field_commentCount = {}
field_commentCount["name"] = "commentCount"
field_commentCount["pattern"] = r"(?<=commentCount=).+?(?=;)"
field_id = {}
field_id["name"] = "id"
field_id["pattern"] = r'(?<=id=").+?(?=";)'
fields = [field_content, field_publishTime, field_commentCount, field_id]
items = self.analyze_response(str1, fields)
print("心情随笔:", items)
html_content = "<html><meta charset='utf-8'><body>"
items_count = len(items)
for i, item in enumerate(items):
self.show_status_signal.emit("进度:" + str(i + 1) + "/" + str(items_count))
commentCount = item["commentCount"]
html_content = (
html_content
+ "<div class='item'><div class='content'>"
+ item["content"]
+ "</div><div class='publishTime'>"
+ item["publishTime"]
+ ",评论("
+ commentCount
+ ")</div><hr></div>"
)
if commentCount != "0":
self.show_status_signal.emit(
"正在获取第{}条心情随笔的{}条评论".format(i + 1, commentCount)
)
comment_items = self.get_commet(item["id"], item["commentCount"])
html_content += self.append_comment(comment_items)
html_content += "</body></html>"
fileutil.check_and_create(self.backup_dir + self.mood_html_file)
with open(self.backup_dir + self.mood_html_file, "w+") as f2:
f2.write(html_content)
print("保存html格式的心情随笔成功", html_content)
def get_userspace_url(self):
album_catelog_url = "http://photo.163.com/photo/{}/dwr/call/plaincall/UserSpaceBean.getUserSpace.dwr?u={}".format(
self.blog_name, self.blog_name
)
self.post_userspace_data["c0-param0"] = self.blog_name
r = requests.post(
album_catelog_url, data=self.post_userspace_data, headers=self.headers
)
fileutil.check_and_create(self.backup_dir + self.album_file)
with open(self.backup_dir + self.album_catelog_file, "w+") as f:
f.write(r.text)
self.show_status_signal.emit("下载心情随笔的原始数据成功\n开始解析原始数据")
self.albumCount = re.search(r"(?<=albumCount:).+?(?=,)", r.text)[0]
self.photoCount = re.search(r"(?<=photoCount:).+?(?=,)", r.text)[0]
self.userId = re.search(r"(?<=userId:).+?(?=,)", r.text)[0]
self.usedSpace = re.search(r"(?<=usedSpace:).+?(?=,)", r.text)[0]
self.cacheFileUrl = re.search(r'(?<=cacheFileUrl:").+?(?=",)', r.text)[0]
print(self)
def down_blog_source(self):
self.show_status_signal.emit("开始下载{}条日志".format(self.blog_count))
get_blog_url = "http://api.blog.163.com/{}/dwr/call/plaincall/BlogBeanNew.getBlogsNewTheme.dwr".format(
self.blog_name)
self.post_blog_data["c0-param0"] = self.user_id
self.post_blog_data["c0-param2"] = self.blog_count
fileutil.check_and_create(self.backup_dir + self.blog_source_file)
print("get_blog_url:{},post_blog_data:{}".format(
get_blog_url, self.post_blog_data))
r = requests.post(get_blog_url,
data=self.post_blog_data,
headers=self.headers)
# ~ print(r.text)
with open(self.backup_dir + self.blog_source_file, "w+") as f:
f.write(r.text)
self.show_status_signal.emit("下载日志的原始数据成功\n开始解析原始数据")
def down_mood_source(self):
self.show_status_signal.emit("开始下载{}条心情随笔".format(self.mood_count))
get_mood_url = "http://api.blog.163.com/{}/dwr/call/plaincall/FeelingsBeanNew.getRecentFeelingCards.dwr".format(
self.blog_name
)
self.post_mood_data["c0-param0"] = self.user_id
self.post_mood_data["c0-param2"] = self.mood_count
print(
"get_mood_url:{},self.post_mood_data:{}".format(
get_mood_url, self.post_mood_data
)
)
r = requests.post(get_mood_url, data=self.post_mood_data, headers=self.headers)
# ~ print(r.text)
fileutil.check_and_create(self.backup_dir + self.mood_file)
with open(self.backup_dir + self.mood_file, "w+") as f:
f.write(r.text)
self.show_status_signal.emit("下载心情随笔的原始数据成功\n开始解析原始数据")
def __init__(self, backup_dir, blog_name, user_id, blog_count,
continue_on_failure):
super().__init__()
self.blog_source_file = "日志/source_blog.txt"
self.blog_html_file = "日志/blog.html"
self.backup_dir = backup_dir
self.blog_name = blog_name
self.user_id = user_id
self.blog_count = blog_count
self.continue_on_failure = continue_on_failure
self.continue_index = 0
if continue_on_failure:
fileutil.check_and_create(backup_dir + "config.json")
with open(backup_dir + "config.json", "r") as f:
index_content = f.read().strip()
if f.read().strip():
self.continue_index = int(index_content)
self.post_blog_data = {
"callCount": "1",
"scriptSessionId": "187",
"c0-scriptName": "BlogBeanNew",
"c0-methodName": "getBlogsNewTheme",
"c0-id": "0",
# ~ "c0-param0": "",
"c0-param1": "0",
"c0-param2": "1",
"batchId": "159937",
}
self.headers = {
"contents-Type":
"text/plain",
"Referer":
"http://api.blog.163.com/crossdomain.html?publish_time=20100205",
"User-Agent":
"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.80 Safari/537.36",
}
def convert_to_html_file(self):
fileutil.check_and_create(self.backup_dir + self.blog_html_file)
with open(self.backup_dir + self.blog_source_file, "r") as f:
str1 = f.read().strip()
field_title = {}
field_title["name"] = "title"
field_title["pattern"] = r'(?<=title=").+?(?=";)'
field_link = {}
field_link["name"] = "link"
field_link["pattern"] = r'(?<=permalink=").+?(?=";)'
field_publishTime = {}
field_publishTime["name"] = "publishTime"
field_publishTime["pattern"] = r"(?<=publishTime=).+?(?=;)"
field_accessCount = {}
field_accessCount["name"] = "accessCount"
field_accessCount["pattern"] = r"(?<=accessCount=).+?(?=;)"
field_commentCount = {}
field_commentCount["name"] = "commentCount"
field_commentCount["pattern"] = r"(?<=commentCount=).+?(?=;)"
field_id = {}
field_id["name"] = "id"
field_id["pattern"] = r'(?<=id=").+?(?=";)'
fields = [
field_title,
field_link,
field_publishTime,
field_accessCount,
field_commentCount,
field_id,
]
items = self.analyze_response(str1, fields)
print("日志数量:{},日志内容:{}".format(len(items), items))
html_content = "<html><meta charset='utf-8'><body>"
items_count = len(items)
for i, item in enumerate(items, self.continue_index - 1):
self.continue_index = i
self.show_status_signal.emit("进度:{}/{},{}".format(
i + 1, items_count, item["title"]))
commentCount = item["commentCount"]
html_content = (
html_content +
"<div class='item'><div class='title'>{}</div><div class='publishTime'>{},评论({})</div><div class='link'>{}</div><hr></div>"
.format(item["title"], item["publishTime"], commentCount,
item["link"]))
try:
self.get_single_blog(item, i + 1)
except:
self.show_status_signal.emit("系统异常:" + str(sys.exc_info()[1]) +
"\n下载失败")
# ~ if commentCount != "0":
# ~ self.show_status_signal.emit(
# ~ "正在获取第{}条日志的{}条评论".format(i + 1, commentCount)
# ~ )
# ~ comment_items = get_commet(self.blog_name,item["id"],item["commentCount"],html_content)
# ~ html_content = append_comment(html_content,comment_items)
html_content += "</body></html>"
fileutil.check_and_create(self.backup_dir + self.blog_html_file)
with open(self.backup_dir + self.blog_html_file, "w+") as f2:
f2.write(html_content)
print("保存html格式的日志成功")
