blackteay/DrissionPage
1
0
Fork 0
mirror of https://gitee.com/g1879/DrissionPage.git synced 2024-12-10 04:00:23 +08:00
Code Issues Projects Releases Wiki Activity

修改报错提示；download()函数出错时可显示详细信息；_make_response()改为返回tuple

Browse Source
This commit is contained in:
g1879 2020-08-03 23:28:22 +08:00
parent 95287fd8a9
commit beff8263fc
1 changed files with 18 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
DrissionPage/session_page.py
View File

@ -92,7 +92,7 @@ class SessionPage(object):
if not url or (not go_anyway and self.url == to_url): if not url or (not go_anyway and self.url == to_url):
return return
self._url = to_url self._url = to_url
self._response = self._make_response(to_url, **kwargs) self._response = self._make_response(to_url, **kwargs)[0]
if self._response: if self._response:
self._response.html.encoding = self._response.encoding # 修复requests_html丢失编码方式的bug self._response.html.encoding = self._response.encoding # 修复requests_html丢失编码方式的bug
self._url_available = True if self._response and self._response.ok else False self._url_available = True if self._response and self._response.ok else False
@ -104,7 +104,7 @@ class SessionPage(object):
if not url or (not go_anyway and self._url == to_url): if not url or (not go_anyway and self._url == to_url):
return return
self._url = to_url self._url = to_url
self._response = self._make_response(to_url, mode='post', data=data, **kwargs) self._response = self._make_response(to_url, mode='post', data=data, **kwargs)[0]
if self._response: if self._response:
try: try:
self._response.html.encoding = self._response.encoding # 修复requests_html丢失编码方式的bug self._response.html.encoding = self._response.encoding # 修复requests_html丢失编码方式的bug
@ -138,11 +138,11 @@ class SessionPage(object):
if 'timeout' not in kwargs: if 'timeout' not in kwargs:
kwargs['timeout'] = 20 kwargs['timeout'] = 20
r = self._make_response(file_url, mode='get', **kwargs) r, info = self._make_response(file_url, mode='get', **kwargs)
if not r: if not r:
if show_msg: if show_msg:
print('Invalid link') print(info)
return False, 'Invalid link' return False, info
# -------------------获取文件名------------------- # -------------------获取文件名-------------------
# header里有文件名，则使用它，否则在url里截取，但不能保证url包含文件名 # header里有文件名，则使用它，否则在url里截取，但不能保证url包含文件名
if 'Content-disposition' in r.headers: if 'Content-disposition' in r.headers:
@ -178,33 +178,29 @@ class SessionPage(object):
full_name = avoid_duplicate_name(goal_path, full_name) full_name = avoid_duplicate_name(goal_path, full_name)
full_path = Path(f'{goal_path}\\{full_name}') full_path = Path(f'{goal_path}\\{full_name}')
else: else:
raise ValueError("file_exists can only be selected in 'skip', 'overwrite', 'rename'") raise ValueError("Argument file_exists can only be 'skip', 'overwrite', 'rename'.")
Path(goal_path).mkdir(parents=True, exist_ok=True) Path(goal_path).mkdir(parents=True, exist_ok=True)
# 打印要下载的文件 if show_msg: # 打印要下载的文件
if show_msg: print(full_name if file_name == full_name else f'{file_name} -> {full_name}')
print_txt = full_name if file_name == full_name else f'{file_name} -> {full_name}'
print(print_txt)
print(f'Downloading to: {goal_path}') print(f'Downloading to: {goal_path}')
# -------------------开始下载------------------- # -------------------开始下载-------------------
# 获取远程文件大小 # 获取远程文件大小
file_size = int(r.headers['Content-Length']) if 'Content-Length' in r.headers else None file_size = int(r.headers['Content-Length']) if 'Content-Length' in r.headers else None
# 已下载文件大小和下载状态 downloaded_size, download_status = 0, False # 已下载文件大小和下载状态
downloaded_size, download_status = 0, False
# 完整的存放路径
try: try:
with open(str(full_path), 'wb') as tmpFile: with open(str(full_path), 'wb') as tmpFile:
for chunk in r.iter_content(chunk_size=1024): for chunk in r.iter_content(chunk_size=1024):
if chunk: if chunk:
tmpFile.write(chunk) tmpFile.write(chunk)
# 如表头有返回文件大小，显示进度 if show_msg and file_size: # 如表头有返回文件大小，显示进度
if show_msg and file_size:
downloaded_size += 1024 downloaded_size += 1024
rate = downloaded_size / file_size if downloaded_size < file_size else 1 rate = downloaded_size / file_size if downloaded_size < file_size else 1
print('\r {:.0%} '.format(rate), end="") print('\r {:.0%} '.format(rate), end="")
except Exception as e: except Exception as e:
download_status, info = False, f'Download failed.\n{e}' download_status, info = False, f'Download failed.\n{e}'
raise
else: else:
download_status, info = (False, 'File size is 0.') if full_path.stat().st_size == 0 else (True, 'Success.') download_status, info = (False, 'File size is 0.') if full_path.stat().st_size == 0 else (True, 'Success.')
finally: finally:
@ -218,7 +214,7 @@ class SessionPage(object):
info = f'{goal_path}\\{full_name}' if download_status else info info = f'{goal_path}\\{full_name}' if download_status else info
return download_status, info return download_status, info
def _make_response(self, url: str, mode: str = 'get', data: dict = None, **kwargs) -> Union[HTMLResponse, bool]: def _make_response(self, url: str, mode: str = 'get', data: dict = None, **kwargs) -> tuple:
"""生成response对象。接收mode参数，以决定用什么方式。 """生成response对象。接收mode参数，以决定用什么方式。
:param url: 要访问的网址 :param url: 要访问的网址
:param mode: 'get', 'post' 中选择 :param mode: 'get', 'post' 中选择
@ -227,7 +223,7 @@ class SessionPage(object):
:return: Response对象 :return: Response对象
""" """
if mode not in ['get', 'post']: if mode not in ['get', 'post']:
raise ValueError("mode must be 'get' or 'post'.") raise ValueError("Argument mode can only be 'get' or 'post'.")
url = quote(url, safe='/:&?=%;#@') url = quote(url, safe='/:&?=%;#@')
# 设置referer和host值 # 设置referer和host值
@ -253,8 +249,8 @@ class SessionPage(object):
r = self.session.get(url, **kwargs) r = self.session.get(url, **kwargs)
elif mode == 'post': elif mode == 'post':
r = self.session.post(url, data=data, **kwargs) r = self.session.post(url, data=data, **kwargs)
except: except Exception as e:
return_value = False return None, e
else: else:
headers = dict(r.headers) headers = dict(r.headers)
if 'Content-Type' not in headers or 'charset' not in headers['Content-Type']: if 'Content-Type' not in headers or 'charset' not in headers['Content-Type']:
@ -268,5 +264,4 @@ class SessionPage(object):
# 避免存在退格符导致乱码或解析出错 # 避免存在退格符导致乱码或解析出错
r._content = r.content if 'stream' in kwargs and kwargs['stream'] else r.content.replace(b'\x08', b'\\b') r._content = r.content if 'stream' in kwargs and kwargs['stream'] else r.content.replace(b'\x08', b'\\b')
r.encoding = charset r.encoding = charset
return_value = r return r, 'Success'
return return_value