def Download(index):
try:
print('\r' + 'Loading...\n', end='', flush=True)
for i in range(int(index)):
url = r"https://picsum.photos/xxx/yyy"
size_x = [
640, 800, 800, 960, 1024, 1024, 1152, 1280, 1280, 1280, 1366,
1400, 1440, 1440, 1600, 1600, 1680, 1856, 1920, 1920, 1920,
2048, 2560, 2560, 3840
]
size_y = [
480, 576, 600, 648, 720, 720, 768, 768, 800, 900, 900, 960,
1050, 1050, 1080, 1080, 1200, 1200, 1392, 1440, 1440, 1536,
1600, 2160, 4320
]
data = url.replace('xxx',
str(size_x[random.randint(0,
len(size_x) - 1)]))
data = data.replace(
'yyy', str(size_y[random.randint(0,
len(size_y) - 1)]))
#print(data)
if not os.path.exists('images'):
os.makedirs('images')
imgfilename = 'images/' + datetime.datetime.today().strftime(
'%d%m%Y-%H%M%S%f%p') + '.jpg'
req.urlretrieve(data + '.jpg', imgfilename)
req.urlcleanup()
print('\r' + '\nCompleted\n', end='', flush=True)
except KeyboardInterrupt:
print("\n[0] Force Exit Command Executed\n")
req.urlcleanup()
exit()
def getPic(pageUrl, savingPath):
"""
抓取所有图片
"""
# global urlList, nameList
html = urlopen(pageUrl)
bsObj = BeautifulSoup(html, features='html.parser')
img = bsObj.find("div", {
'class': 'picsbox picsboxcenter'
}).find("img", {"src": re.compile("https://img\.lovebuy99\.com.*jpg$")})
imgName = bsObj.find("h1").get_text() # 获取图片名字
imgUrl = img.attrs['src']
# print(imgName)
# print(imgUrl)
# urlList.append(imgUrl)
# nameList.append(imgName)
# if not os.path.exists(savingPath): # 为每一model创建文件夹
# os.mkdir(savingPath)
urlretrieve(
imgUrl, filename=savingPath + imgName +
".jpg") # 下载图片，注意filename格式，前面必须要加保存路径，才能将图片保存在指定文件夹中，否则将保存在当前文件夹
urlcleanup()
# 抓取下一页的图片
next_page = bsObj.find('a', text=u"下一页")
next_pageUrl = urljoin(pageUrl, next_page.attrs['href'])
# print(next_pageUrl)
if next_page.attrs['href'] != "#":
time.sleep(1) # 暂停1秒，避免网站访问过快被反爬机制认为是蜘蛛
getPic(next_pageUrl, savingPath)
def download_file(self, url, filename, cwd=None):
"""
Download an `url` to `outfn`
"""
if not url:
return
def report_hook(index, blksize, size):
if size <= 0:
progression = '{0} bytes'.format(index * blksize)
else:
progression = '{0:.2f}%'.format(index * blksize * 100. /
float(size))
stdout.write('- Download {}\r'.format(progression))
stdout.flush()
if cwd:
filename = join(cwd, filename)
if exists(filename):
unlink(filename)
# Clean up temporary files just in case before downloading.
urlcleanup()
print('Downloading {0}'.format(url))
urlretrieve(url, filename, report_hook)
return filename
def _get_genomes(self):
"""Parse genomes from assembly summary txt files."""
genomes = []
names = [
"assembly_summary_refseq.txt",
"assembly_summary_genbank.txt",
"assembly_summary_refseq_historical.txt",
]
sys.stderr.write(
"Downloading assembly summaries from NCBI, " + "this will take a while...\n"
)
seen = {}
for fname in names:
urlcleanup()
with urlopen(os.path.join(self.assembly_url, fname)) as response:
lines = response.read().decode("utf-8").splitlines()
header = lines[1].strip("# ").split("\t")
for line in lines[2:]:
vals = line.strip("# ").split("\t")
# Don't repeat samples with the same asn_name
if vals[15] not in seen: # asn_name
genomes.append(dict(zip(header, vals)))
seen[vals[15]] = 1
return genomes
def download_podcast(podcast):
try:
if 'part' in podcast:
filename = LOCAL_PATTERN_MULTI.format(**podcast)
else:
filename = LOCAL_PATTERN.format(**podcast)
if os.path.exists(filename):
return
print('+', filename, '==> ', end='')
mp3_url = find_mp3_url(podcast['url'])
print(mp3_url)
try:
os.makedirs(os.path.dirname(filename))
except OSError:
pass
tempfile, _ = urlretrieve(mp3_url, reporthook=download_progress)
print() # Go past progress bar
shutil.move(tempfile, filename)
except Exception:
print('FAILED')
finally:
urlcleanup()
def getImg(self):
try:
reg = r'src="(.+?\.jpg)"'
imglist = re.findall(reg, self.html)
if (len(imglist)):
for i in range(len(imglist)):
imglist[i] = 'http://www.fzlu.com' + imglist[i]
for imgurl in imglist:
try:
request.urlretrieve(
imgurl,
'E:/photo/%d.jpg' % (self.num + self.baseImgNum))
print('已保存第%d张图片' % (self.num + self.baseImgNum))
print(threading.current_thread())
self.allImgList.append(imgurl)
if self.num == 10:
break
except Exception as e:
print(e.args)
request.urlcleanup()
except Exception as e:
print("正则表达式异常")
return self.num, self.allImgList
def _post_process_download(self, name, localname, out_dir, mask="soft"):
"""
Replace accessions with sequence names in fasta file.
Parameters
----------
name : str
NCBI genome name
out_dir : str
Output directory
"""
# Get the FTP url for this specific genome and download
# the assembly report
for genome in self.genomes:
if name in [genome["asm_name"], genome["asm_name"].replace(" ", "_")]:
url = genome["ftp_path"]
url += "/" + url.split("/")[-1] + "_assembly_report.txt"
url = url.replace("ftp://", "https://")
break
# Create mapping of accessions to names
tr = {}
urlcleanup()
with urlopen(url) as response:
for line in response.read().decode("utf-8").splitlines():
if line.startswith("#"):
continue
vals = line.strip().split("\t")
tr[vals[6]] = vals[0]
localname = get_localname(name, localname)
# Check of the original genome fasta exists
fa = os.path.join(out_dir, "{}.fa".format(localname))
if not os.path.exists(fa):
raise Exception("Genome fasta file not found, {}".format(fa))
# Use a tmp file and replace the names
new_fa = os.path.join(out_dir, ".process.{}.fa".format(localname))
if mask != "soft":
sys.stderr.write(
"NCBI genomes are softmasked by default. Changing mask...\n"
)
with open(fa) as old:
with open(new_fa, "w") as new:
for line in old:
if line.startswith(">"):
desc = line.strip()[1:]
name = desc.split(" ")[0]
new.write(">{} {}\n".format(tr.get(name, name), desc))
elif mask == "hard":
new.write(re.sub("[actg]", "N", line))
elif mask not in ["hard", "soft"]:
new.write(line.upper())
else:
new.write(line)
# Rename tmp file to real genome file
shutil.move(new_fa, fa)
def print_pl2_label(self, macaddress):
mac = macaddress
data = {"message": "printing PL2 label"}
self._signal_printer.emit(data)
sleep(0.5)
try:
url = self.corelight.get_pl2_label_download_url(mac)
filename = os.path.basename(url)
filepath = os.path.join(os.getcwd(), filename)
urlretrieve(url, filepath, self.download_callback)
print("download pl2:", url, filename, filepath)
if self.download_percent == 100:
self.download_percent = 0
if os.path.exists(filepath):
self.printing(filepath)
sleep(0.1)
data = {
"message": "print PL2 label success",
"filepath": filepath
}
self._signal_printer.emit(data)
sleep(0.5)
os.unlink(filepath)
except Exception as e:
print(e)
data = {"message": "print PL2 label fail"}
self._signal_printer.emit(data)
finally:
urlcleanup()
def tmploop_get_remote_files(i,matching,user,pw,
server,remote_path,
path_local):
"""
Function to download files using ftp. Tries 10 times before failing.
"""
print("File: ",matching[i])
print("src path: ", remote_path)
pw = quote(pw) # to escape special characters
dlstr=('ftp://' + user + ':' + pw + '@'
+ server + remote_path + matching[i])
for attempt in range(10):
print ("Attempt to download data: ")
try:
print ("Downloading file")
urlretrieve(dlstr, os.path.join(path_local, matching[i]))
urlcleanup()
except Exception as e:
print (e.__doc__)
print (e.message)
print ("Waiting for 10 sec and retry")
time.sleep(10)
else:
break
else:
print ('An error was raised and I ' +
'failed to fix problem myself :(')
print ('Exit program')
sys.exit()
def main(url, args):
''' Convert given tar file to conda packages '''
cwd = os.getcwd()
args.output_folder = os.path.abspath(args.output_folder)
os.makedirs(args.output_folder, exist_ok=True)
args.recipe_dir = os.path.abspath(args.recipe_dir)
if os.path.isfile(args.recipe_dir):
args.recipe_dir = os.path.dirname(args.recipe_dir)
download = False
if url.startswith('http:') or url.startswith('https:'):
print_err('> download %s' % url)
download = True
url, headers = urlretrieve(url)
urlcleanup()
elif os.path.exists(url):
url = os.path.abspath(url)
with TemporaryDirectory() as temp:
with tarfile.open(url, url.endswith('tar') and 'r:' or 'r:gz') as tar:
tar.extractall(temp)
# Clean up
if download:
urlcleanup()
os.chdir(temp)
url = os.path.join(temp, glob.glob('R-swat*')[0])
# Create conda package for each R version
for base, versions in get_supported_versions(args.platform).items():
for ver in versions:
update_recipe(args.recipe_dir,
url=url,
version=get_version(url),
r_base='{}-base'.format(base),
r_version=ver)
cmd = ['conda', 'build', '-q', '--no-test']
cmd.extend(['--R', ver])
if args.output_folder:
cmd.extend(['--output-folder', args.output_folder])
if args.override_channels:
cmd.append('--override-channels')
if args.channel:
for chan in args.channel:
cmd.extend(['--channel', chan])
cmd.append(args.recipe_dir)
print_err('>' + ' '.join(cmd))
subprocess.check_output(cmd)
os.chdir(cwd)
def fetch_from_PDB(self):
"""
Connects to PDB FTP server, downloads a .gz file of interest,
decompresses the .gz file into .ent and then dumps a copy of
the pdb{code}.ent file into cwd.
Parameters
----------
None
Examples
--------
>>> inst = PDBFile('1rcy')
>>> path_to_file = inst.fetch_from_PDB()
>>> print(path_to_file)
"""
subdir = self.code[1:3]
infile = 'pdb{}.ent.gz'.format(self.code)
decompressed = infile.strip('.gz')
fullpath = ROOT.format(subdir, infile)
try:
urlcleanup()
urlretrieve(fullpath, infile)
except Exception:
return 'URLError'
else:
with gzip.open(infile, 'rb') as gz:
with open(decompressed, 'wb') as out:
out.writelines(gz)
remove(infile)
return path.join(getcwd(), decompressed)
def checkForUpdate(self,):
# check on web if update available
# return boolean for update_PMV,update_ePMV and update_pyubics
# where to check and what type dev/stable/host
self.new_version = self.liste_plugin
self.update_notes = ""
self.result_json = None
# need version
URI = self.url
tmpFileName = "update_notes_" + self.host + ".json"
# if not os.path.isfile(tmpFileName):
urllib.urlcleanup()
if checkURL(URI):
urllib.urlretrieve(URI, tmpFileName) # ,reporthook=self.helper.reporthook)
# geturl(URI, tmpFileName)
else:
print("problem connecting to server")
return None
with open(tmpFileName, "r") as fp: # doesnt work with symbol link ?
self.result_json = json.load(fp)
do_update = []
for plug in self.liste_plugin:
self.liste_plugin[plug]["update"] = False
if self.liste_plugin[plug]["version_current"] != self.result_json[plug]["version_" + self.typeUpdate]:
if self.result_json[plug]["host"] == ["all"] or self.host in self.result_json[plug]["host"]:
self.liste_plugin[plug]["update"] = True
self.liste_plugin[plug]["host"] = self.result_json[plug]["host"]
do_update.append(self.liste_plugin[plug]["update"])
self.update_notes = self.result_json["notes"]
# self.merge_list_plug()
print(self.update_notes)
os.remove(tmpFileName)
return do_update
def getdocument(url):
try:
return req.urlopen(url)
except req.URLError as e:
print(e.reason)
req.urlcleanup()
sys.exit(1)
def prepare_file(uplodad=False):
if uplodad:
for file in glob("out/**"):
if os.path.isfile(file):
try:
os.unlink(file)
except Exception:
pass
i = 0
while i < 8:
print("on loop", i + 1)
submitter = "me"
vid = sys.argv[1]
duration = get_duration(vid)
print(duration)
start = 0
if duration > DURATION:
start = int(random.random() * (duration - DURATION))
duration = DURATION
filename, info_text, failed = v_glitch(
vid, i, submitter, start, duration
)
urlcleanup()
if failed:
print("something went wrong")
print("FAILED:", info_text)
else:
print("filename if'ed")
print(info_text)
print("new path:", filename)
vid = filename
i += 1
return info_text, filename
def fetch():
url = 'https://us.battle.net/forums/en/wow/1011639/'
results = []
req = Request(url)
try:
urlcleanup()
response = urlopen(req)
except URLError as e:
if hasattr(e, 'reason'):
print(' We failed to reach a server.')
print(' Reason: ', e.reason)
elif hasattr(e, 'code'):
print(' The server couldn\'t fulfill the request.')
print(' Error code: ', e.code)
return None, None
else:
html = response.read()
soup = BeautifulSoup(html, 'html.parser')
# get text
text = soup.findAll('a', attrs={'class': 'ForumTopic'})
for topic in text:
title = topic.find('span', attrs={'class': 'ForumTopic-title'})
title = re.sub(r'[^\x00-\x7F]+', ' ', title.text.strip())
if re.search(r'^[^<>]+$', title):
results.append((topic['href'][21:], title))
return results
def download_images(imgs: [], path: str, c=0):
for i in imgs:
urllib.urlretrieve(i, os.path.join(path, str(c) + '.png'))
c = c + 1
urllib.urlcleanup()
def download_file(self, url, filename, cwd=None):
"""
Download an `url` to `outfn`
"""
if not url:
return
def report_hook(index, blksize, size):
if size <= 0:
progression = '{0} bytes'.format(index * blksize)
else:
progression = '{0:.2f}%'.format(
index * blksize * 100. / float(size))
stdout.write('- Download {}\r'.format(progression))
stdout.flush()
if cwd:
filename = join(cwd, filename)
if exists(filename):
unlink(filename)
# Clean up temporary files just in case before downloading.
urlcleanup()
print('Downloading {0}'.format(url))
urlretrieve(url, filename, report_hook)
return filename
def download_document(request, pk):
requested_doc = Document.objects.get(id=pk)
# requested_doc = get_object_or_404(Document, pk=pk)
# context = {'data': requested_doc}
# pdf = render_to_pdf()
template_name = 'editor/DownloadDocument3.html'
# print('-'*30)
# print("this is the url of requested file : ",request,"id = ",pk)
# print('-'*30)
# print("this is the url of requested file --------- : ",request.path)
# url_to_be_used = "http://localhost:8000"+request.path
# print("url which should be passed -> :",url_to_be_used)
# print('-'*40)
# print(urlretrieve(url_to_be_used))
# print("\n ----------------- now focus on downloading ----------------- ")
# try:
# name, _ = url_to_be_used
# requested_doc.signed_file.save("{timestamp}.pdf".format(timestamp=timezone.now().strftime('%Y-%m-%d%/%H-%M-%S')), File(open(tempname, 'rb')))
# finally:
# urlcleanup()
try:
# request.encoding = 'koi8-r'
print("-trying to render it into pdf-\n")
pdf = render_to_pdf(template_name, {
'data': requested_doc.content,
'title': 'download page3',
})
finally:
urlcleanup()
print("-pdf rendering successfull-")
return HttpResponse(pdf, content_type='application/pdf', charset='utf-8')
def runner(source):
"Download a file from a url into a directory"
# Get the base file name
url = source[0]
directory = source[1]
p = urlparse(url)
file_name = path.basename(p.path)
# Concatenate patha and file name
path_and_file_name = path.join(directory, file_name)
# Download file if not already exists
# If you are getting errors of incomplete data, try reducing the number of max_workers
try:
if not path.exists(path_and_file_name):
if url.startswith("ftp"):
urlcleanup()
urlretrieve(url, path_and_file_name)
else:
retrieve(url,path_and_file_name)
logging.info(path_and_file_name)
if path_and_file_name.endswith(".tar.gz"):
shutil.unpack_archive(path_and_file_name, directory)
logger.info(f"Unpacked: {path_and_file_name}")
except Exception as e:
logger.error(f"Problem with {file_name}.. You may need to manually download from: {url}")
logger.error(e)
def getNDFDlist(listof, area=None, timerange=None, ndfd_server=NDFD_SERVER):
"""
Description: Returns a list of available NDFD parameters
Parameters:
listof (str): Either "areas", "timeranges", or "vars"
area (str): Needed if listof="timeranges" or "vars"
timerange (str): Needed if listof="vars"
ndfd_server (str): URL to NDFD server with files
Returns:
lines (list): List of extracted parameters
"""
if listof == "areas":
regex = r"(?<=a href=\"AR\.).*(?=\/\">)"
elif listof == "timeranges":
ndfd_server += NDFD_AREA.format(area)
regex = r"(?<=a href=\"VP\.)\d\d\d\-\d\d\d(?=\/)"
elif listof == "vars":
ndfd_server += NDFD_AREA.format(area) + NDFD_TRNG.format(timerange)
regex = r"(?<=a href=\"ds\.).*(?=\.bin\")"
with urlopen(ndfd_server) as file:
lines = file.readlines()
lines = [line.decode("utf-8") for line in lines]
lines = "\n".join(lines)
lines = re.findall(regex, lines)
urlcleanup()
return lines
def megach_update():
try:
url = "https://raw.githubusercontent.com/LinkkG/megach/master/megach.py"
file_to_replace = "{}{}megach.py".format(paths.u_bot, os.sep)
with urlreq.urlopen(url) as info_online:
info_online = info_online.read().decode("utf-8").splitlines()
megach_online_v = [x for x in info_online
if "version =" in x][0].split("=")[1]
megach_online_v = megach_online_v.replace("'", "").lstrip(" ")
with open(file_to_replace, encoding="utf-8") as a_megach:
a_megach = a_megach.read().splitlines()
megach_local_v = [x for x in a_megach
if "version =" in x][0].split("=")[1]
megach_local_v = megach_local_v.replace("'", "").lstrip(" ")
if a_megach == info_online:
download = [False, megach_local_v, megach_online_v]
else:
urlreq.urlretrieve(url, file_to_replace)
download = [True, megach_local_v, megach_online_v]
urlreq.urlcleanup()
return download
a_megach.close()
info_online.close()
except:
return "Error: {}".format(str(tools.error_def()))
def ub_test(url):
request.urlretrieve(url,filename="21.html")
request.urlcleanup()
file = request.urlopen(url).read()
# while True:
fileline = request.urlopen(url).readline()
# print(fileline,"\n")
return file,fileline
def getDistrictInfo(i):
num = i + 1
file_name = base_file_name + str(num).rjust(num_padding,
'0') + file_extension
local_file_name, headers = request.urlretrieve(base_url + file_name)
ZipFile(local_file_name, 'r').extractall()
request.urlcleanup()
return
def urlretrieve(url):
from urllib import request
webname = "".join(("".join(url.split("//")[1:])).split("/")[:1])
request.urlretrieve(url,dir+webname+'.html')
#清除使用urlopen或urlretrieve后产生的缓存文件
request.urlcleanup()
gevent.sleep(1)
print("{} fetch success!".format(webname))
def download_to_local(self, url):
try:
name, _ = urlretrieve(url)
f_name = os.path.basename(url)
self.document.save(f_name, File(open(name, 'rb')))
finally:
#clear temp files after load
urlcleanup()
def dataFetch(self, charClass, charSpec, guide):
print('>Fetching {1} {0} {2}'.format(charClass, charSpec, guide))
charClass = '-'.join(charClass.lower().split(' '))
charSpec = '-'.join(charSpec.lower().split(' '))
guide = '-'.join(guide.lower().split(' '))
url = 'https://www.wowhead.com/{1}-{0}-{2}'.format(
charClass, charSpec, guide)
req = Request(url)
try:
urlcleanup()
response = urlopen(req)
except URLError as e:
if hasattr(e, 'reason'):
print(' We failed to reach a server.')
print(' Reason: ', e.reason)
elif hasattr(e, 'code'):
print(' The server couldn\'t fulfill the request.')
print(' Error code: ', e.code)
return None, None
else:
html = response.read()
soup = BeautifulSoup(html, 'html.parser')
# kill all script and style elements
for script in soup(["script", "style"]):
script.extract() # rip it out
# get text
text = soup.get_text()
# break into lines and remove leading and trailing space on each
lines = (line.strip() for line in text.splitlines())
# break multi-headlines into a line each
chunks = (phrase.strip() for line in lines
for phrase in line.split(" "))
# drop blank lines
text = '\n'.join(chunk for chunk in chunks if chunk)
lines = text.split('\n')
# Finds the title in the text
title = lines[0].replace(' - Guides - Wowhead', '')
# Finds the Context - It is the line after "ReportLinks"
content = ''
nextIsContent = False
for line in lines:
if nextIsContent:
content += line
if 'ReportLinks' in line:
nextIsContent = True
if 'Share your comments about ' in line:
break
return title, content
def download(url, des_path='.'):
try:
print('downloading {}'.format(url))
request.urlretrieve(url, os.path.join(des_path, os.path.basename(url)))
request.urlcleanup()
except request.HTTPError as e:
print('HTTP Error: {} {}'.format(e.code, url))
except request.URLError as e:
print('URL Error: {} {}'.format(e.reason, url))
def download_images(imgs: [], path: str, volume=1, name=1):
for i in imgs:
urllib.urlretrieve(
i, os.path.join(path,
str(volume) + '-' + str(name) + '.png'))
name = name + 1
urllib.urlcleanup()
def _post_process_download(self, name, genome_dir, mask="soft"):
"""
Replace accessions with sequence names in fasta file.
Parameters
----------
name : str
NCBI genome name
genome_dir : str
Genome directory
"""
# Get the FTP url for this specific genome and download
# the assembly report
for genome in self.genomes:
if genome["asm_name"] == name:
url = genome["ftp_path"]
url += "/" + url.split("/")[-1] + "_assembly_report.txt"
url = url.replace("ftp://", "https://")
break
# Create mapping of accessions to names
tr = {}
urlcleanup()
response = urlopen(url)
for line in response.read().decode('utf-8').splitlines():
if line.startswith("#"):
continue
vals = line.strip().split("\t")
tr[vals[6]] = vals[0]
name = name.replace(" ", "_")
# Check of the original genome fasta exists
fa = os.path.join(genome_dir, name, "{}.fa".format(name))
if not os.path.exists(fa):
raise Exception("Genome fasta file not found, {}".format(fa))
# Use a tmp file and replace the names
new_fa = os.path.join(genome_dir, name, ".process.{}.fa".format(name))
if mask == "hard":
sys.stderr.write("masking lower-case.\n")
with open(fa) as old:
with open(new_fa, "w") as new:
for line in old:
if line.startswith(">"):
desc = line.strip()[1:]
name = desc.split(" ")[0]
new.write(">{} {}\n".format(tr.get(name, name), desc))
elif mask == "hard":
new.write(re.sub('[actg]', 'N', line))
else:
new.write(line)
# Rename tmp file to real genome file
shutil.move(new_fa, fa)
def retrieve_social_profile_photo(user_profile, url):
""" Retrieve and save a retrieved user's profile photo from a url
"""
try:
filename, _ = urlretrieve(url)
user_profile.profile_photo.save(filename, File(open(filename, 'rb')))
user_profile.generate_nonce()
user_profile.save()
finally:
urlcleanup()
def terminate_download_callback(event):
# Clean up after urllib urlretrieve which is used internally
# in grass.utils.
from urllib import request # pylint: disable=import-outside-toplevel
self._download_in_progress = False
request.urlcleanup()
sys.stdout.write("Download aborted")
self.thread = gThread()
self._change_download_btn_label()
def main():
data=urllib.request.urlopen('http://www.baidu.com')
print(data.getcode())
print(data.geturl())
data_read=data.read()
fhandle=open("E:/1.html","wb")
fhandle.write(data_read)
#另一种方法
req.urlcleanup()
filename=req.urlretrieve("http://edu.51cto.com","E:/2.html")
def get_tcc(cleanup=True):
BUILD_DIR.mkdir(parents=True, exist_ok=True)
try:
if WINDOWS:
_get_tcc_windows()
else:
_get_tcc_good_os(cleanup)
finally:
_info(f"Cleaning up downloaded temporary files.")
urlcleanup()
def do_local(self):
for dic in self.lista_etiq:
llave = list(dic.keys())[0]
for elemento in dic[llave]:
value = dic[llave][elemento]
if value:
if (elemento == "src") and (value != "cancion.ogg"):
URL = value
filename = URL[URL.rfind("/") + 1:]
data = urlretrieve(URL, filename)
urlcleanup()
dic[llave][elemento] = data[0]
def readUpdateNote(self,):
URI = self.url
tmpFileName = "update_notes_" + self.host + ".json"
urllib.urlcleanup()
if checkURL(URI):
urllib.urlretrieve(URI, tmpFileName) # ,reporthook=self.helper.reporthook)
# geturl(URI, tmpFileName)
else:
print("problem connecting to server")
return None
with open(tmpFileName, "r") as fp: # doesnt work with symbol link ?
self.result_json = json.load(fp)
def _get_genomes(self):
"""Parse genomes from assembly summary txt files."""
genomes = []
names = [
"assembly_summary_refseq.txt",
"assembly_summary_refseq_historical.txt",
]
for fname in names:
urlcleanup()
response = urlopen(self.assembly_url + "/" + fname)
lines = response.read().decode('utf-8').splitlines()
header = lines[1].strip("# ").split("\t")
for line in lines[2:]:
vals = line.strip("# ").split("\t")
genomes.append(dict(zip(header, vals)))
return genomes
def getRemoteData(url):
# Download from URL
try:
local_filename, headers = UrlRequest.urlretrieve(url)
except IOError as e:
print('IO Error! Abort!\n')
print(e)
return -1
except:
print('Unknow Error occured! Abort!')
return -1
# Open and Read local temporary File
html = open(local_filename)
data = html.read()
html.close()
# Delete temporary Internet File
UrlRequest.urlcleanup()
return data
def update_plug(self, plug, path=None, typeUpdate="std", backup=False):
import zipfile
p = path
if p is None:
p = self.liste_plugin[plug]["path"] # AutoFill.__path__[0]+os.sep #path of plug
# print "update_AF",AFwrkDir1
if self.host in self.result_json[plug]["host"]:
URI = self.server + "/" + plug + "_" + typeUpdate + "_" + self.host + ".zip"
else:
URI = self.server + "/" + plug + "_" + typeUpdate + "_all.zip"
os.chdir(p)
os.chdir("../")
patchpath = os.path.abspath(os.curdir)
tmpFileName = patchpath + os.sep + plug + "_" + typeUpdate + ".zip"
urllib.urlcleanup()
if checkURL(URI):
urllib.urlretrieve(URI, tmpFileName, reporthook=self.helper.reporthook)
else:
return False
zfile = zipfile.ZipFile(tmpFileName)
# TF=tarfile.TarFile(tmpFileName)
dirname1 = p # +os.sep+".."+os.sep+"AutoFill"
import shutil
if backup:
# rename AF to AFv
dirname2 = dirname1 + self.liste_plugin[plug]["version_current"] # the version
print(dirname1, dirname2)
if os.path.exists(dirname2):
shutil.rmtree(dirname2, True)
shutil.copytree(dirname1, dirname2)
if os.path.exists(dirname1):
shutil.rmtree(dirname1, True)
# TF.extractall(patchpath)
zfile.extractall(patchpath)
zfile.close()
os.remove(tmpFileName)
return True
def download(self):
furlo = FBURLopener({})
try:
tmpfile, msg = furlo.retrieve(self.url, reporthook=self.rhook)
print()
except HTTPError as ex:
urlcleanup()
sys.exit(ex)
except URLError as ex:
urlcleanup()
sys.exit(ex)
if os.path.exists(self.dlpath) and filecmp.cmp(self.dlpath, tmpfile):
print('You already have the newest version of ' + self.plugin)
done = True
else:
shutil.copyfile(tmpfile, self.dlpath)
print(self.plugin + ' downloaded.')
done = False
urlcleanup()
if done or self.format == 'jar':
return
try:
shutil.unpack_archive(self.dlpath, self.dest_dir, self.format)
except ValueError as ex:
sys.exit('Error: ' + str(ex))
def download(self):
if os.path.exists(self.filename):
print('File %r exists locally.' % self.filename)
return
try:
print('Downloading: %r' % self.url)
self.urlo.retrieve(self.url, self.filename, reporthook=self.rhook)
print()
except HTTPError as ex:
request.urlcleanup()
sys.exit(ex)
except URLError as ex:
request.urlcleanup()
sys.exit(ex)
request.urlcleanup()
def cleanUpTemporaryFiles():
UrlRequest.urlcleanup()
def download_genome(self, name, genome_dir, localname=None, mask="soft", regex=None, invert_match=False, version=None):
"""
Download a (gzipped) genome file to a specific directory
Parameters
----------
name : str
Genome / species name
genome_dir : str
Directory to install genome
mask: str , optional
Masking, soft, hard or none (all other strings)
"""
genome_dir = os.path.expanduser(genome_dir)
if not os.path.exists(genome_dir):
os.makedirs(genome_dir)
dbname, link = self.get_genome_download_link(name, mask=mask, version=version)
myname = dbname
if localname:
myname = localname
myname = myname.replace(" ", "_")
gzipped = False
if link.endswith(".gz"):
gzipped = True
if not os.path.exists(os.path.join(genome_dir, myname)):
os.makedirs(os.path.join(genome_dir, myname))
urlcleanup()
response = urlopen(link)
sys.stderr.write("downloading from {}...\n".format(link))
down_dir = genome_dir
fname = os.path.join(genome_dir, myname, myname + ".fa")
if regex:
down_dir = mkdtemp()
fname = os.path.join(down_dir, myname + ".fa")
with open(fname, "wb") as f_out:
if gzipped:
# Supports both Python 2.7 as well as 3
with gzip.GzipFile(fileobj=io.BytesIO(response.read())) as f_in:
shutil.copyfileobj(f_in, f_out)
else:
f_out.write(response.read())
sys.stderr.write("done...\n")
if link.endswith("tar.gz"):
self.tar_to_bigfile(fname, fname)
if hasattr(self, '_post_process_download'):
self._post_process_download(name, down_dir, mask)
if regex:
infa = fname
outfa = os.path.join(genome_dir, myname, myname + ".fa")
filter_fasta(
infa,
outfa,
regex=regex,
v=invert_match,
force=True
)
not_included = [k for k in Fasta(infa).keys() if k not in Fasta(outfa).keys()]
shutil.rmtree(down_dir)
fname = outfa
sys.stderr.write("name: {}\n".format(dbname))
sys.stderr.write("local name: {}\n".format(myname))
sys.stderr.write("fasta: {}\n".format(fname))
# Create readme with information
readme = os.path.join(genome_dir, myname, "README.txt")
with open(readme, "w") as f:
f.write("name: {}\n".format(myname))
f.write("original name: {}\n".format(dbname))
f.write("original filename: {}\n".format(os.path.split(link)[-1]))
f.write("url: {}\n".format(link))
f.write("mask: {}\n".format(mask))
f.write("date: {}\n".format(time.strftime("%Y-%m-%d %H:%M:%S")))
if regex:
if invert_match:
f.write("regex: {} (inverted match)\n".format(regex))
else:
f.write("regex: {}\n".format(regex))
f.write("sequences that were excluded:\n")
for seq in not_included:
f.write("\t{}\n".format(seq))
#
return myname
def _post_process_download(self, name, genome_dir, mask="soft"):
"""
Replace accessions with sequence names in fasta file.
Parameters
----------
name : str
NCBI genome name
genome_dir : str
Genome directory
"""
# Get the FTP url for this specific genome and download
# the assembly report
for genome in self.genomes:
if genome["asm_name"] == name:
url = genome["ftp_path"]
url += "/" + url.split("/")[-1] + "_assembly_report.txt"
break
# Create mapping of accessions to names
tr = {}
urlcleanup()
response = urlopen(url)
for line in response.read().decode('utf-8').splitlines():
if line.startswith("#"):
continue
vals = line.strip().split("\t")
tr[vals[6]] = vals[0]
name = name.replace(" ", "_")
# Check of the original genome fasta exists
fa = os.path.join(genome_dir, name, "{}.fa".format(name))
if not os.path.exists(fa):
raise Exception("Genome fasta file not found, {}".format(fa))
# Use a tmp file and replace the names
new_fa = os.path.join(
genome_dir, name,
".process.{}.fa".format(name)
)
if mask == "hard":
sys.stderr.write("masking lower-case.\n")
with open(fa) as old:
with open(new_fa, "w") as new:
for line in old:
if line.startswith(">"):
desc = line.strip()[1:]
name = desc.split(" ")[0]
new.write(">{} {}\n".format(
tr.get(name, name),
desc
))
elif mask == "hard":
new.write(re.sub('[actg]', 'N', line))
else:
new.write(line)
# Rename tmp file to real genome file
shutil.move(new_fa, fa)
def download():
count = 0
# Set the limits of the range according to the "id" keys
for i in range(1, 2000):
count += 1
try:
if retain_original_names:
urr.urlretrieve(link + str(i))
else:
urr.urlretrieve(link + str(i), "Lecture " + str(count))
except AttributeError:
with urr.urlopen(link + str(i)) as in_data, open("Lecture " + str(count), 'wb') as out_video:
copyfileobj(in_data, out_video)
i += ticker
time.sleep(buffer_time)
print (str(count) + " videos have been downloaded.")
# Removing any temporary files left behind
urr.urlcleanup()
##############################################################################################################
## Known Issues
## If the downloaded files are named "Lecture 1,2,3 ..." even though retain_original_names is set to True -
## 1. Python Org as finally deprecated the urlretrieve attribute
## 2. I still haven't figured out how to scrape Coursera's website
##############################################################################################################
