def is_archive_file(name):
# type: (str) -> bool
"""Return True if `name` is a considered as an archive file."""
ext = splitext(name)[1].lower()
if ext in ARCHIVE_EXTENSIONS:
return True
return False
def _download_http_url(link, session, temp_dir, hashes, progress_bar):
"""Download link url into temp_dir using provided session"""
target_url = link.url.split('#', 1)[0]
try:
resp = session.get(
target_url,
# We use Accept-Encoding: identity here because requests
# defaults to accepting compressed responses. This breaks in
# a variety of ways depending on how the server is configured.
# - Some servers will notice that the file isn't a compressible
# file and will leave the file alone and with an empty
# Content-Encoding
# - Some servers will notice that the file is already
# compressed and will leave the file alone and will add a
# Content-Encoding: gzip header
# - Some servers won't notice anything at all and will take
# a file that's already been compressed and compress it again
# and set the Content-Encoding: gzip header
# By setting this to request only the identity encoding We're
# hoping to eliminate the third case. Hopefully there does not
# exist a server which when given a file will notice it is
# already compressed and that you're not asking for a
# compressed file and will then decompress it before sending
# because if that's the case I don't think it'll ever be
# possible to make this work.
headers={"Accept-Encoding": "identity"},
stream=True,
)
resp.raise_for_status()
except requests.HTTPError as exc:
logger.critical(
"HTTP error %s while getting %s", exc.response.status_code, link,
)
raise
content_type = resp.headers.get('content-type', '')
filename = link.filename # fallback
# Have a look at the Content-Disposition header for a better guess
content_disposition = resp.headers.get('content-disposition')
if content_disposition:
type, params = cgi.parse_header(content_disposition)
# We use ``or`` here because we don't want to use an "empty" value
# from the filename param.
filename = params.get('filename') or filename
ext = splitext(filename)[1]
if not ext:
ext = mimetypes.guess_extension(content_type)
if ext:
filename += ext
if not ext and link.url != resp.url:
ext = os.path.splitext(resp.url)[1]
if ext:
filename += ext
file_path = os.path.join(temp_dir, filename)
with open(file_path, 'wb') as content_file:
_download_url(resp, link, content_file, hashes, progress_bar)
return file_path, content_type
def splitext(self):
return splitext(posixpath.basename(self.path.rstrip('/')))
def splitext(self):
# type: () -> Tuple[str, str]
return splitext(posixpath.basename(self.path.rstrip('/')))
def _download_http_url(
link, # type: Link
session, # type: PipSession
temp_dir, # type: str
hashes, # type: Optional[Hashes]
progress_bar # type: str
):
# type: (...) -> Tuple[str, str]
"""Download link url into temp_dir using provided session"""
target_url = link.url.split('#', 1)[0]
try:
resp = session.get(
target_url,
# We use Accept-Encoding: identity here because requests
# defaults to accepting compressed responses. This breaks in
# a variety of ways depending on how the server is configured.
# - Some servers will notice that the file isn't a compressible
# file and will leave the file alone and with an empty
# Content-Encoding
# - Some servers will notice that the file is already
# compressed and will leave the file alone and will add a
# Content-Encoding: gzip header
# - Some servers won't notice anything at all and will take
# a file that's already been compressed and compress it again
# and set the Content-Encoding: gzip header
# By setting this to request only the identity encoding We're
# hoping to eliminate the third case. Hopefully there does not
# exist a server which when given a file will notice it is
# already compressed and that you're not asking for a
# compressed file and will then decompress it before sending
# because if that's the case I don't think it'll ever be
# possible to make this work.
headers={"Accept-Encoding": "identity"},
stream=True,
)
resp.raise_for_status()
except requests.HTTPError as exc:
logger.critical(
"HTTP error %s while getting %s",
exc.response.status_code,
link,
)
raise
content_type = resp.headers.get('content-type', '')
filename = link.filename # fallback
# Have a look at the Content-Disposition header for a better guess
content_disposition = resp.headers.get('content-disposition')
if content_disposition:
filename = parse_content_disposition(content_disposition, filename)
ext = splitext(filename)[1] # type: Optional[str]
if not ext:
ext = mimetypes.guess_extension(content_type)
if ext:
filename += ext
if not ext and link.url != resp.url:
ext = os.path.splitext(resp.url)[1]
if ext:
filename += ext
file_path = os.path.join(temp_dir, filename)
with open(file_path, 'wb') as content_file:
_download_url(resp, link, content_file, hashes, progress_bar)
return file_path, content_type
def splitext(self):
# type: () -> Tuple[str, str]
return splitext(posixpath.basename(self.path.rstrip('/')))
def is_archive_file(name):
"""Return True if `name` is a considered as an archive file."""
ext = splitext(name)[1].lower()
if ext in ARCHIVE_EXTENSIONS:
return True
return False
def splitext(self):
return splitext(posixpath.basename(self.path.rstrip('/')))
def ext(self):
# type: () -> str
return splitext()[1]
def splitext(self) -> Tuple[str, str]:
return splitext(posixpath.basename(self.path.rstrip("/")))
def is_archive_file(name):
# type: (str) -> bool
"""Return True if `name` is a considered as an archive file."""
ext = splitext(name)[1].lower()
return ext in ARCHIVE_EXTENSIONS