def down_album_source(self):
self.show_status_signal.emit("开始获取相册目录")
self.get_userspace_url()
catelog_outline_info = "相册总数:{}\n图片总数:{}\n相册目录地址:{}\n用户id:{}".format(
self.albumCount, self.photoCount, self.cacheFileUrl, self.userId
)
self.show_status_signal.emit(catelog_outline_info)
catelog_items = self.get_catelog_info()
catelog_detail_info = ""
for item in catelog_items:
catelog_detail_info += "相册:{},图片数量:{},描述:{},id:{}\n".format(
item["name"], item["count"], item["desc"], item["idd"]
)
self.show_status_signal.emit(catelog_detail_info)
fileutil.check_and_create_dir(self.backup_dir + "source")
for i, item in enumerate(catelog_items):
try:
self.show_status_signal.emit(
"相册进度:{}/{},{}".format(i + 1, len(catelog_items), item["name"])
)
self.down_single_album(item)
except:
print(sys.exc_info())
self.show_status_signal.emit(
"系统异常:" + str(sys.exc_info()[1]) + "\n单个相册下载失败,相册:" + item["name"]
)
def on_pb_init_project_clicked(self):
self.path = self.le_path.text()
if self.path and self.config.conf:
check_and_create_dir(self.path)
self.init_project_name()
# ~ self.show_result("$正在初始化项目" + self.project_name)
os.chdir(self.path)
cmd_init_project = "cd {};git init;git remote add origin [email protected]:{}/{}.git".format(
self.path, self.config.conf["username"], self.project_name)
self.exec_cmd(cmd_init_project)
self.show_result("$ 初始化项目成功")
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 get_catelog_info(self):
fileutil.check_and_create_dir(self.backup_dir + "source")
print(self.cacheFileUrl)
print(
"cd {};wget http://{} -O {}.txt".format(
self.backup_dir + "source", self.cacheFileUrl, "catelog_info.txt"
)
)
os.system(
"cd {};wget http://{} -O {}.txt".format(
self.backup_dir + "source", self.cacheFileUrl, "catelog_info"
)
)
with open(
self.backup_dir + "source/catelog_info.txt", "r", encoding="gb2312"
) as f:
content = f.read().strip()
self.show_status_signal.emit("获取相册目录成功")
field_name = {}
field_name["name"] = "name"
field_name["pattern"] = r"(?<=name:\').+?(?=\',)"
field_desc = {}
field_desc["name"] = "desc"
field_desc["pattern"] = r"(?<=desc:\').*?(?=\',)"
field_count = {}
field_count["name"] = "count"
field_count["pattern"] = r"(?<=count:).+?(?=,)"
field_purl = {}
field_purl["name"] = "purl"
field_purl["pattern"] = r"(?<=purl:\').*?(?=\'})"
field_id = {}
field_id["name"] = "idd"
field_id["pattern"] = r"(?<={id:).+?(?=,)"
fields = [field_name, field_desc, field_count, field_purl, field_id]
catelog_items = self.analyze_response(content, fields)
print("相册目录信息:", catelog_items)
return catelog_items
def get_single_blog(self, item, item_index):
link = item["link"]
blog_title = item["title"]
url = "http://{}.blog.163.com/{}".format(self.blog_name, link)
print("url:", url)
r = requests.get(url)
html_doc = r.text
fileutil.check_and_create_dir(self.backup_dir + "日志/source/")
with open(self.backup_dir + "日志/source/" + blog_title + ".txt",
"w+") as f:
f.write(r.text)
soup = BeautifulSoup(html_doc, "lxml")
blog_sep = soup.find("span", class_="blogsep")
blog_catelog = soup.find("a", class_="fc03 m2a")
if blog_sep is None:
print("无权限访问:" + item["title"])
pass
return
print("发表时间:{},分类:{}".format(blog_sep.string, blog_catelog.string))
blog_body = soup.find_all("div", class_="bct fc05 fc11 nbw-blog ztag")
if blog_body:
blog_imgs = BeautifulSoup(str(blog_body[0]),
"lxml").find_all("img")
print("正文:", blog_body[0])
single_blog_dir = (self.backup_dir + "日志/" + blog_catelog.string +
"/" + blog_title + "/")
fileutil.check_and_create_dir(single_blog_dir)
with open(
self.backup_dir + "日志/" + blog_catelog.string + "/" +
blog_title + ".html",
"w+",
) as f:
content = "<html><meta charset='utf-8'><body><h1>{}</h1><div class='tag'>{} | 分类: {}</div><hr>".format(
blog_title, blog_sep.string, blog_catelog.string)
if blog_body:
# ~ content += str(blog_body[0])
str_body = str(blog_body[0])
# r'(?<=title=").+?(?=";)'
# ~ r'(?<=src=").+?(?/=\d{5})'
pattern = re.compile(r'(?<=src=").+?(?=/\d{5})')
print(pattern.findall(str_body))
content += re.sub(pattern, blog_title, str_body)
content += "<br>阅读({}) | 评论({})".format(item["accessCount"],
item["commentCount"])
content += "</body></html>"
f.write(content)
# ~ 下载图片
if blog_imgs:
self.show_status_signal.emit("正在获取日志:{}的{}张图片".format(
item["title"], len(blog_imgs)))
for img in blog_imgs:
print(img)
if img["src"]:
img_name = img["src"][img["src"].rindex("/") + 1:]
print("下载图片:", img["src"], img_name)
self.show_status_signal.emit('下载图片:{}'.format(
img["src"]))
r = requests.get(img["src"])
img["src"] = blog_title + "/" + img_name
with open(single_blog_dir + img_name, "wb+") as f:
f.write(r.content)
def down_single_album(self, item):
if item["purl"].strip() != "":
print(
"cd {};wget http://{} -O {}.txt".format(
self.backup_dir + "source", item["purl"], item["name"]
)
)
os.system(
"cd {};wget http://{} -O {}.txt".format(
self.backup_dir + "source", item["purl"], item["name"].strip()
)
)
with open(
self.backup_dir + "source/{}.txt".format(item["name"].strip()),
"r+",
encoding="gb2312",
) as f:
content = f.read().strip()
# ~ print("content:",content)
field_desc = {}
field_desc["name"] = "desc"
field_desc["pattern"] = r"(?<=desc:\').*?(?=\',)"
# ~ field_desc["pattern"] = r"var"
field_purl = {}
field_purl["name"] = "murl"
field_purl["pattern"] = r"(?<=murl:\').*?(?=\',)"
fields = [field_desc, field_purl]
photos = self.analyze_response(str(content), fields)
print(item["name"], "相册目录信息:", photos)
if len(photos) > 0:
fileutil.check_and_create_dir(self.backup_dir + item["name"])
for i, photo in enumerate(photos):
try:
r = requests.get(self.img_url_prex + photo["murl"][1:])
if photo["desc"] == "":
slash_index = photo["murl"].rindex("/")
photo["desc"] = photo["murl"][slash_index:]
else:
slash_index = photo["murl"].rindex(".")
photo["desc"] = (
photo["desc"].replace(".JPG", "")
+ photo["murl"][slash_index:]
)
print("下载图片:{},{}".format(photo["desc"], photo["murl"]))
self.show_status_signal.emit(
"相册:{},{}/{},图片:{}".format(
item["name"], i, len(photos), photo["desc"]
)
)
with open(
self.backup_dir + item["name"] + "/" + photo["desc"], "wb+"
) as f:
f.write(r.content)
except:
print(sys.exc_info())
self.show_status_signal.emit(
"系统异常:"
+ str(sys.exc_info()[1])
+ "\n单张图片下载失败,图片:"
+ photo["desc"]
)
else:
self.show_status_signal.emit("空相册:{}".format(item["name"]))
def create_dir(self):
self.backup_dir = os.getcwd() + "/" + self.le_blog_name.text(
) + "的博客备份/"
fileutil.check_and_create_dir(self.backup_dir)