def parse(self, response):
# 创建 contract
""" This function parase a property page.
@url http://web:3912/properties/property_000000.html
@returns items L
@scrapes title price description address image_urls
@scrapes url project spider server date
"""
# 比较实用的水平爬取和垂直爬取URL
# 水平
urls = response.xpath('//*[contains(@class,"next")]//@href').extract()
absUrls = [urlparse.urljoin(response.url, i) for i in urls]
# 垂直
urls = response.xpath('//*[@itemprop="url"]/@href').extract()
absUrls = [urlparse.urljoin(response.url, i) for i in urls]
# 使用爬虫预定义的方法log()，输出在基本字段表中总结的所有内容
self.log("title: %s" % response.xpath('//*[@itemprop="name"][1]/text()').extract())
self.log("price: %s" % response.xpath('//*[@itemprop="price"[1]/text()').re('[.0-9]+'))
self.log("description: %s" % response.xpath('//*[@itemprop="description"][1]/text()').extract())
self.log("address: %s" % response.xpath('//*[@itemprop="http://schema.org/Place"][1]/text()').extract())
self.log("image_urls: %s" % response.xpath('//*[@itemprop="image"][1]/@src').extract())
# # 填充Item
# item = PropertiesItem()
# item['title'] = response.xpath('//*[@itemprop="name"][1]/text()').extract()
# item['price'] = response.xpath('//*[@itemprop="price"[1]/text()').re('[.0-9]+')
# item['description'] = response.xpath('//*[@itemprop="description"][1]/text()').extract()
# item['address'] = response.xpath('//*[@itemprop="http://schema.org/Place"][1]/text()').extract()
# item['image_urls'] = response.xpath('//*[@itemprop="image"][1]/@src').extract()
# return item
# 清理 item 装载器与管理字段
L = ItemLoader(item=PropertiesItem(), response=response)
L.add_xpath('title', '//*[@itemprop="name"][1]/text()')
L.add_xpath('price', '//*[@itemprop="price"][1]/text()', re='[.0-9]+')
L.add_xpath('description', '//*[@itemprop="description"][1]/text()')
L.add_xpath('address', '//*[@itemprop="http://schema.org/Place"][1]/text()')
L.add_xpath('image_urls', '//*[@itemprop="image"][1]/@src')
# 使用处理器 用来对我们的Xpath/CSS结果进行处理。
# 在爬虫中使用几个这样子的处理器，并按照我们想要的方式输出
L.add_xpath('title', '//*[@itemprop="name"][1]/text()', MapCompose(unicode.strip, unicode.title))
L.add_xpath('price', '//*[@itemprop="price"][1]/text()', MapCompose(lambda i: i.replace(',', ''), float), re='[.0-9]+')
L.add_xpath('description', '//*[@itemprop="description"][1]/text()', MapCompose(unicode.strip), Join())
L.add_xpath('address', '//*[@itemprop="http://schema.org/Place"][1]/text()', MapCompose(unicode.strip))
L.add_xpath('image_urls', '//*[@itemprop="image"][1]/@src', MapCompose(lambda i : urlparse.urljoin(response.url, i)))
# 使用add_value方法设置管理字段
L.add_value('url', reponse.url)
L.add_value('project', self.settings.get('BOT_NAME'))
L.add_value('spider', self.name)
L.add_value('server', socket.gethostname)
L.add_value('date', datetime.datetime.now())
return L.load_item()
pass
def get_repo_url(mead_tag, nexus_base_url, prefix="hudson-", suffix=""):
"""
Creates repository Nexus group URL composed of:
<nexus_base_url>/content/groups/<prefix><mead_tag><suffix>
:param mead_tag: name of the MEAD tag used to create the proxy URL in settings.xml
:param nexus_base_url: the base URL of a Nexus instance
:param prefix: Nexus group name prefix, default is "hudson-"
:param suffix: Nexus group name suffix, e.g. "-jboss-central" or "-reverse"
:returns:
"""
result = urlparse.urljoin(nexus_base_url, "content/groups/")
result = urlparse.urljoin(result, "%s%s%s/" % (prefix, mead_tag, suffix))
return result
def get_repo_url(mead_tag, nexus_base_url, prefix="hudson-", suffix=""):
"""
Creates repository Nexus group URL composed of:
<nexus_base_url>/content/groups/<prefix><mead_tag><suffix>
:param mead_tag: name of the MEAD tag used to create the proxy URL in settings.xml
:param nexus_base_url: the base URL of a Nexus instance
:param prefix: Nexus group name prefix, default is "hudson-"
:param suffix: Nexus group name suffix, e.g. "-jboss-central" or "-reverse"
:returns:
"""
result = urlparse.urljoin(nexus_base_url, "content/groups/")
result = urlparse.urljoin(result, "%s%s%s/" % (prefix, mead_tag, suffix))
return result
def _get_directory(self,
url,
pattern,
url_group=1,
value_group=2,
value_fn=None):
response = self.request(url)
if value_group is None:
if value_fn is None:
value_fn = lambda m, u: m.group(0)
else:
if value_fn is None:
#value_fn = lambda v: v
value_fn = int
count = 0
for match in pattern.finditer(response):
count += 1
match_url = urlparse.urljoin(url, match.group(url_group))
if value_group is None:
yield (
match_url,
value_fn(match, match_url),
)
else:
yield (
match_url,
value_fn(match.group(value_group)),
)
def __init__(self, name) :
"""
@param name: URL to be opened
@keyword additional_headers: additional HTTP request headers to be added to the call
"""
try :
# Note the removal of the fragment ID. This is necessary, per the HTTP spec
req = Request(url=name.split('#')[0])
req.add_header('Accept', 'text/html, application/xhtml+xml')
self.data = urlopen(req)
self.headers = self.data.info()
if URIOpener.CONTENT_LOCATION in self.headers :
self.location = urlparse.urljoin(self.data.geturl(),self.headers[URIOpener.CONTENT_LOCATION])
else :
self.location = name
except urllib_HTTPError :
e = sys.exc_info()[1]
from pyMicrodata import HTTPError
msg = BaseHTTPRequestHandler.responses[e.code]
raise HTTPError('%s' % msg[1], e.code)
except Exception :
e = sys.exc_info()[1]
from pyMicrodata import MicrodataError
raise MicrodataError('%s' % e)
def download_file(self, file_path, dest_path='.'):
"""
Download a file from file_path to dest_path
:param file_path: Path to the resource to download
:type file_path: String
:param dest_path: Path to where the downloaded file should be saved
:type dest_path: String
"""
resource_path = urlparse.urljoin(self.connection.path,
file_path.strip('/'))
resp, content = self.connection.send_get(resource_path)
file_name = os.path.basename(file_path)
write_to_path = os.path.join(dest_path, file_name)
try:
file_fd = open(write_to_path, 'wb')
file_fd.write(content)
except IOError:
raise
finally:
file_fd.close()
return resp, content
def parse_editions_url(self, response):
name = response.css(
'div.mainContentFloat h1 a::text').extract_first().strip()
editions = response.meta['editions']
all_books_data = {}
if (name not in editions['name']):
editions['name'] = name
editions['urls'] = []
for book_page in response.css('a.bookTitle').xpath('@href'):
editions['urls'].append((urlparse.urljoin(response.url,
book_page.extract())))
next_page = response.xpath("//*[@rel='next']/@href").extract_first()
if next_page is not None and (len(editions['urls']) <= 200):
yield response.follow(next_page,
callback=self.parse_editions_url,
meta={'editions': editions})
else:
print(editions['name'])
print(len(editions['urls']))
for link in editions['urls']:
request = scrapy.Request(link,
callback=self.parse_editions_data,
meta={
'all_books_data': all_books_data,
'name': editions['name']
})
yield request
#yield editions
editions = {}
def download_file(request, file_id):
"""permet a l'utilisateur de telecharger le fichier grace a l'api"""
gi = request.galaxy
data = gi.datasets.show_dataset(dataset_id=file_id)
name = "error"
if isinstance(data, dict):
dlurl = data.get('download_url')
name = data.get('name')
name = name.replace(" ", "_")
name = name + "." + data.get('file_ext')
if not name:
name = "download"
if dlurl:
url = urlparse.urljoin(gi.base_url, dlurl)
response = urllib.urlopen(url)
stream_response = StreamingHttpResponse(response.read())
stream_response[
'Content-Disposition'] = 'attachment; filename=' + name
else:
stream_response = StreamingHttpResponse(
"No file download URL corresponds to the given dataset id " +
file_id)
else:
stream_response = StreamingHttpResponse(data)
return stream_response
def model_view(self, request, model_databrowse, url):
# If the object ID wasn't provided, redirect to the model page,
# Which is one level up.
if url is None:
return http.HttpResponseRedirect(
urlparse.urljoin(request.path, '../')
)
easy_model = EasyModel(
model_databrowse.site,
model_databrowse.model
)
try:
obj = easy_model.object_by_pk(url)
except ObjectDoesNotExist:
raise http.Http404('Id not found')
except ValueError:
raise http.Http404('Invalid format key provided')
return render(
request,
'databrowse/object_detail.html',
{
'object': obj,
'root_url': model_databrowse.site.root_url
}
)
def __init__(self, name):
"""
@param name: URL to be opened
@keyword additional_headers: additional HTTP request headers to be added to the call
"""
try:
# Note the removal of the fragment ID. This is necessary, per the HTTP spec
req = Request(url=name.split('#')[0])
req.add_header('Accept', 'text/html, application/xhtml+xml')
self.data = urlopen(req)
self.headers = self.data.info()
if URIOpener.CONTENT_LOCATION in self.headers:
self.location = urlparse.urljoin(
self.data.geturl(),
self.headers[URIOpener.CONTENT_LOCATION])
else:
self.location = name
except urllib_HTTPError:
e = sys.exc_info()[1]
from pyMicrodata import HTTPError
msg = BaseHTTPRequestHandler.responses[e.code]
raise HTTPError('%s' % msg[1], e.code)
except Exception:
e = sys.exc_info()[1]
from pyMicrodata import MicrodataError
raise MicrodataError('%s' % e)
def install_project(info, basefolder, serverurl, updateMode=False):
if not serverurl:
roam.utils.warning("No server url set for update")
raise ValueError("No server url given")
roam.utils.info("Downloading project zip")
if updateMode:
filename = "{}.zip".format(info['name'])
else:
filename = "{}-Install.zip".format(info['name'])
serverurl = add_slash(serverurl)
url = urlparse.urljoin(serverurl, "projects/{}".format(filename))
tempfolder = os.path.join(basefolder, "_updates")
if not os.path.exists(tempfolder):
os.mkdir(tempfolder)
zippath = os.path.join(tempfolder, filename)
for status in download_file(url, zippath):
yield status
yield "Installing"
with zipfile.ZipFile(zippath, "r") as z:
z.extractall(basefolder)
project = roam.project.Project.from_folder(os.path.join(basefolder, info['name']))
os.chdir(project.folder)
yield "Running update scripts.."
run_install_script(project.settings, "after_update")
project.projectUpdated.emit(project)
class CAIssuersParser:
'''Parses list of CA's from Mozilla, Chrome, Opera, iOS.'''
# https://en.wikipedia.org/wiki/Certificate_authority#Providers
CA_LISTS = {
'mozilla': {
'list': urlparser.urljoin(
'https://hg.mozilla.org/releases/mozilla-beta/raw-file/',
'tip/security/nss/lib/ckfw/builtins/certdata.txt',
),
'pattern': '# Issuer ',
}
}
ISSUERS = []
# TODO: parse the other lists and store the CA's into a file
def parse_issuers(self):
resp = requests.get(self.CA_LISTS['mozilla']['list'])
raw_list = resp.text
pattern = self.CA_LISTS['mozilla']['pattern']
for line in raw_list.split('\n'):
if line.startswith(pattern):
issuer = line.lstrip(pattern)
if issuer not in self.ISSUERS:
print(issuer)
self.ISSUERS.append(issuer)
def fetch_data(self, rootfolder, filename, serverurl):
"""
Download the update zip file for the project from the server
"""
serverurl = add_slash(serverurl)
tempfolder = os.path.join(rootfolder, "_updates")
if not os.path.exists(tempfolder):
os.mkdir(tempfolder)
filename = "{}.zip".format(filename)
url = urlparse.urljoin(serverurl, "projects/{}".format(filename))
zippath = os.path.join(tempfolder, filename)
if not self.check_url_found(url):
yield "Skipping data download"
yield "Done"
return
roam.utils.info("Downloading data zip from {}".format(url))
try:
for status in download_file(url, zippath):
yield status
except UpdateExpection as ex:
roam.utils.exception("Error in update for project")
yield "Error in downloading data"
return
yield "Extracting data.."
with zipfile.ZipFile(zippath, "r") as z:
members = z.infolist()
for i, member in enumerate(members):
z.extract(member, rootfolder)
roam.utils.debug("Extracting: {}".format(member.filename))
yield "Done"
def install_artifacts(artifacts, dirstruct, installdir, basestaticurl):
"""
Install the artifacts.
"""
assert basestaticurl.endswith("/"), "Basestaticurl should end with /"
installed = []
for reldir, artifactnames in list(dirstruct.items()):
destdir = os.path.join(installdir, reldir)
if not os.path.exists(destdir):
log.warn("Making install directory %s" % destdir)
os.makedirs(destdir)
else:
assert os.path.isdir(destdir)
for artifactname in artifactnames:
destpath = os.path.abspath(os.path.join(destdir, artifactname))
if artifactname in list(artifacts.keys()):
# The artifact must be loaded from jenkins
theartifact = artifacts[artifactname]
else:
# It's probably a static file, we can get it from the static collection
staticurl = urlparse.urljoin(basestaticurl, artifactname)
theartifact = Artifact(artifactname, staticurl)
theartifact.save(destpath)
installed.append(destpath)
return installed
def export_to_itol(request, file_id):
# retrieve newick from galaxy server
gi = request.galaxy
data = gi.datasets.show_dataset(dataset_id=file_id)
if isinstance(data, dict):
dlurl = data.get('download_url')
if dlurl:
url = urlparse.urljoin(gi.base_url, dlurl)
response = urllib.urlopen(url)
tmpfile = tempfile.NamedTemporaryFile()
tmpfile.write(response.read())
tmpfile.flush()
# send file to itol server
url_itol = 'https://itol.embl.de/upload.cgi'
payload = {
'tname': "",
'tfile': open(tmpfile.name, 'rb'),
}
r = requests.post(url_itol, files=payload)
return redirect(r.url)
return render(request, 'error.html', {
'errortitle': 'Error querying galaxy',
'errormessage': data
})
def parser(self, html):
data = []
if not html:
return data
soup = BeautifulSoup(html, "lxml")
for tag in soup.find_all("a", class_="a_title2"):
origin = urlparse.urljoin(self.root_url, tag['href'])
sub_html = self.downloader(origin)
sub_soup = BeautifulSoup(sub_html, 'lxml')
detail = sub_soup.find('div', class_='detail_xq w770')
title = detail.find('h2').get_text().strip()
lis = detail.find_all('li')
cnnvd_id = lis[0].get_text().strip()[8:]
cve_id = lis[2].find_all('a')[-1].get_text().strip()
description = sub_soup.find('div',
class_='d_ldjj').get_text().strip()
keyword = self.get_keyword(description)
created = lis[6].find_all('a')[-1].get_text().strip()
data.append({
"title": title,
"cnnvd_id": cnnvd_id,
"cve_id": cve_id,
"description": description,
"keyword": keyword,
"created": created,
"origin": origin,
})
return data
def download_pom(repo_url=None, artifact=None, pom_url=None, target_dir=None):
"""
Downloads a pom file with give GAV (as array) or from given pom_url and saves it as pom.xml into target_dir.
:param repo_url: repository URL from which the pom should be downloaded, mandatory only if no pom_url provided
:param artifact: MavenArtifact instance, mandatory only if no pom_url provided
:param pom_url: URL of the pom to download, not mandatory
:target_dir: target directory path, where the pom should be saved, not mandatory
:returns: path to the saved pom, useful if no target_dir provided
"""
if not pom_url:
pom_url = urlparse.urljoin(
repo_url, "%s/" % string.replace(artifact.groupId, ".", "/"))
pom_url = urlparse.urljoin(pom_url, "%s/" % artifact.artifactId)
pom_url = urlparse.urljoin(pom_url, "%s/" % artifact.version)
pom_url = urlparse.urljoin(
pom_url, "%s-%s.pom" % (artifact.artifactId, artifact.version))
handler = None
try:
handler = urlopen(pom_url)
except HTTPError as err:
logging.error("Failed to download POM %s. %s", pom_url, err)
return None
if not target_dir:
num = 1
while not target_dir or os.path.exists(target_dir):
target_dir = "/tmp/maven-temp-path-%s" % num
num += 1
pom_path = os.path.join(target_dir, "pom.xml")
if handler.getcode() == 200:
pom = handler.read()
handler.close()
if not os.path.exists(target_dir):
os.makedirs(target_dir)
pom_file = None
try:
pom_file = open(pom_path, "w")
pom_file.write(pom)
finally:
if pom_file:
pom_file.close()
return pom_path
def abs_url(url, response):
"""Return absolute link"""
base = response.xpath('//head/base/@href').extract()
if base:
base = base[0]
else:
base = response.url
return urlparse.urljoin(base, url)
def _get_new_urls(self, page_url, soup):
new_urls = {} #定义字典
links = soup.find_all('a', class_="e") #找节点
for link in links:
new_url = link['href']
new_full_url = urlparse.urljoin(page_url, new_url) #拼接
new_urls.add(new_full_url) #添加
return new_urls #返回
def _get_new_urls(self, page_url, soup):
new_urls = set()
links = soup.find_all('a', href=re.compile(r"/view/\d+\.htm"))
for link in links:
new_url = link['href']
new_full_url = urlparse.urljoin(page_url, new_url)
new_urls.add(new_full_url)
return new_urls
def download_pom(repo_url=None, artifact=None, pom_url=None, target_dir=None):
"""
Downloads a pom file with give GAV (as array) or from given pom_url and saves it as pom.xml into target_dir.
:param repo_url: repository URL from which the pom should be downloaded, mandatory only if no pom_url provided
:param artifact: MavenArtifact instance, mandatory only if no pom_url provided
:param pom_url: URL of the pom to download, not mandatory
:target_dir: target directory path, where the pom should be saved, not mandatory
:returns: path to the saved pom, useful if no target_dir provided
"""
if not pom_url:
pom_url = urlparse.urljoin(repo_url, "%s/" % string.replace(artifact.groupId, ".", "/"))
pom_url = urlparse.urljoin(pom_url, "%s/" % artifact.artifactId)
pom_url = urlparse.urljoin(pom_url, "%s/" % artifact.version)
pom_url = urlparse.urljoin(pom_url, "%s-%s.pom" % (artifact.artifactId, artifact.version))
handler = None
try:
handler = urlopen(pom_url)
except HTTPError as err:
logging.error("Failed to download POM %s. %s", pom_url, err)
return None
if not target_dir:
num = 1
while not target_dir or os.path.exists(target_dir):
target_dir = "/tmp/maven-temp-path-%s" % num
num += 1
pom_path = os.path.join(target_dir, "pom.xml")
if handler.getcode() == 200:
pom = handler.read()
handler.close()
if not os.path.exists(target_dir):
os.makedirs(target_dir)
pom_file = None
try:
pom_file = open(pom_path, "w")
pom_file.write(pom)
finally:
if pom_file:
pom_file.close()
return pom_path
def get_city_name(url_city):
'''获取当前所有的城市列表'''
base_url = "http://www.tianqihoubao.com"
city_url = urlparse.urljoin(base_url, url_city)
# print city_url
html = requests.get(city_url).content
html_tree = etree.HTML(html)
links = html_tree.xpath("//td//a/@href")
return map(get_name, links)
def _get_new_urls(page_url, links):
new_urls = set()
for link in links:
new_url = link
new_full_url = urlparse.urljoin(page_url, new_url)
OO0o = urlparse(new_full_url)
if OO0o.path.endswith(".action") or OO0o.path.endswith(".do"):
new_urls.add(new_full_url)
return new_urls
def parse_link_rel(url, fn):
"""
Read through html file ``fn`` downloaded from ``url``, looking for a
link tag of the form:
<link rel="alternate"
type="application/sage"
title="currently ignored"
href=".../example.sws" />
This function reads ``fn`` looking for such tags and returns a list
of dictionaries of the form
{'title': from title field in link, 'url': absolute URL to .sws file}
for the corresponding ``.sws`` files. Naturally if there are no
appropriate link tags found, the returned list is empty. If the HTML
parser raises an HTMLParseError, we simply return an empty list.
"""
from HTMLParser import HTMLParser
class GetLinkRelWorksheets(HTMLParser):
def __init__(self):
HTMLParser.__init__(self)
self.worksheets = []
def handle_starttag(self, tag, attrs):
if (tag == 'link' and ('rel', 'alternate') in attrs
and ('type', 'application/sage') in attrs):
self.worksheets.append({
'title': [_ for _ in attrs if _[0] == 'title'][0][1],
'url': [_ for _ in attrs if _[0] == 'href'][0][1]
})
parser = GetLinkRelWorksheets()
with open(fn) as f:
try:
parser.feed(f.read())
except HTMLParseError:
return []
ret = []
for d in parser.worksheets:
sws = d['url']
# is that link a relative URL?
if not urlparse.urlparse(sws).netloc:
# unquote-then-quote to avoid turning %20 into %2520, etc
ret.append({
'url':
urlparse.urljoin(url, urllib.quote(urllib.unquote(sws))),
'title':
d['title']
})
else:
ret.append({'url': sws, 'title': d['title']})
return ret
def _get_new_urls(self, page_url, soup):
new_urls = set()
#获取所有标签
links = soup.find_all('a', href=re.compile(r'/pg/\d+\.htm'))
for link in links:
new_url = link['link']
# 全路径
new_full_url = urlparse.urljoin(page_url, new_url)
new_urls.add(new_full_url)
return new_urls
def __query_implementation(self, identifier_name, value):
action_name = 'Sale/Query/{0}={1}'.format(identifier_name, value)
request_header = {
"MerchantKey": str(self.merchant_key),
'Content-Type': 'application/json',
'Accept': 'application/json'
}
return requests.get(urlparse.urljoin(self.host_uri, action_name),
headers=request_header)
def _get_new_urls(self, page_url, links):
#添加爬取到的新url
new_url = set()
for link in links:
new_url = link
new_full_url = urlparse.urljoin(page_url, new_url)
new_full_url = self.check_url(new_full_url)
if (self._judge(new_full_url)):
new_urls.add(new_full_url)
return new_urls
def retry_with_request(self, retry_sale_request):
request_header = {
"MerchantKey": str(self.merchant_key),
'Content-Type': 'application/json',
'Accept': 'application/json'
}
action_name = self.resource_name + '/Retry'
return requests.post(urlparse.urljoin(self.host_uri, action_name),
data=json.dumps(retry_sale_request,
cls=uuid_serialize),
headers=request_header)
def _init_request(path, params, headers, creds):
credentials = creds or Config()
hdrs = {
'Accept': 'application/vnd.pagerduty+json;version=2',
'Authorization': f'Token token={credentials["pagerduty"].api_key}'
}
if headers:
hdrs.update(headers)
params = params or {}
url = urlparse.urljoin(PAGERDUTY_API_URL, path)
return url, params, hdrs
def getDownloadList(url='http://www.yahoo.co.jp'):
dom = pq(url)
result = set()
for img in dom('img').items():
img_url = img.attr['src']
if img_url.startswith('http'):
result.add(img_url)
else:
result.add(urlparse.urljoin(url, img_url))
return result
def _load_from_uri(uri, timeout=None, headers={}, cookies=None):
response = requests.get(uri,
cookies=cookies,
timeout=timeout,
headers=headers)
content = response.content.strip()
parsed_url = urlparse.urlparse(uri)
prefix = parsed_url.scheme + '://' + parsed_url.netloc
base_path = os.path.normpath(parsed_url.path + '/..')
base_uri = urlparse.urljoin(prefix, base_path)
return M3U8(content, base_uri=base_uri), response.cookies
def get_arguments():
global base_url
global team_name
global access_token
parser = OptionParser(usage='''usage: %prog [options]
Marks all the channels of all users of given team as read.
Useful after using the Mattermost bulk import, as otherwise all users have tons of unread messages and
the Mattermost client has a hard time loading.''')
parser.add_option(
"-b",
"--base-url",
dest="base_url",
action="store",
type="string",
help=
"Base URL of Mattermost installation (mandatory), e.g. 'https://mattermost.mycompany.ch/'"
)
parser.add_option(
"-t",
"--team",
dest="team",
action="store",
type="string",
help="Team name of which channels should be marked as read (mandatory)"
)
parser.add_option(
"-a",
"--access-token",
dest="token",
action="store",
type="string",
help=
"A valid Mattermost API access token (optional, can be entered interactively)"
)
(options, args) = parser.parse_args()
if options.base_url is None:
parser.print_help()
parser.error("Base URL parameter is mandatory")
if options.team is None:
parser.error("Team parameter is mandatory")
if options.token is None:
access_token = getpass.getpass('Mattermost API access token:')
else:
access_token = options.token
base_url = urlparse.urljoin(options.base_url, '/api/v4')
team_name = options.team
print("team_name", team_name)
print("base_url = ", base_url)
print("options.base_url", options.base_url)
def _get_months(self, year, type="snapshots"):
url = urlparse.urljoin(self.base_url, "%s/%4d/" % (
type,
year,
))
return self._get_directory(
url,
self.YEAR_RE,
value_fn=lambda v: datetime.date(year, int(v), 1),
)
def get_keep(request, article_id):
logged_user = request.user
article = Article.objects.get(id=article_id)
articles = logged_user.article_set.all()
if article not in articles:
article.user.add(logged_user) # for m2m linking, have tested by shell
article.keep_num += 1
article.save()
return redirect('/focus/')
else:
url = urlparse.urljoin('/focus/', article_id)
return redirect(url)
def redirect(request, prefix, tiny, converter=default_converter):
"""
Redirect to a given object from a short URL.
"""
# Resolve the prefix and encoded ID into a model object and decoded ID.
# Many things here could go wrong -- bad prefix, bad value in
# SHORTEN_MODELS, no such model, bad encoding -- so just return a 404 if
# any of that stuff goes wrong.
try:
app_label, model_name = settings.SHORTEN_MODELS[prefix].split('.')
except KeyError:
raise Http404('Bad prefix.')
try:
model = models.get_model(app_label, model_name)
except LookupError:
model = False
if not model:
raise Http404('Bad model specified in SHORTEN_MODELS.')
try:
id = converter.to_decimal(tiny)
except ValueError:
raise Http404('Bad encoded ID.')
# Try to look up the object. If it's not a valid object, or if it doesn't
# have an absolute url, bail again.
obj = get_object_or_404(model, pk=id)
try:
url = obj.get_absolute_url()
except AttributeError:
raise Http404("'%s' models don't have a get_absolute_url() method." % model.__name__)
# We might have to translate the URL -- the badly-named get_absolute_url
# actually returns a domain-relative URL -- into a fully qualified one.
# If we got a fully-qualified URL, sweet.
if urlparse.urlsplit(url)[0]:
return HttpResponsePermanentRedirect(url)
# Otherwise, we need to make a full URL by prepending a base URL.
# First, look for an explicit setting.
if hasattr(settings, 'SHORTEN_FULL_BASE_URL') and settings.SHORTEN_FULL_BASE_URL:
base = settings.SHORTEN_FULL_BASE_URL
# Next, if the sites app is enabled, redirect to the current site.
elif Site._meta.installed:
base = 'http://%s/' % Site.objects.get_current().domain
# Finally, fall back on the current request.
else:
base = 'http://%s/' % RequestSite(request).domain
return HttpResponsePermanentRedirect(urlparse.urljoin(base, url))
def parse_link_rel(url, fn):
"""
Read through html file ``fn`` downloaded from ``url``, looking for a
link tag of the form:
<link rel="alternate"
type="application/sage"
title="currently ignored"
href=".../example.sws" />
This function reads ``fn`` looking for such tags and returns a list
of dictionaries of the form
{'title': from title field in link, 'url': absolute URL to .sws file}
for the corresponding ``.sws`` files. Naturally if there are no
appropriate link tags found, the returned list is empty. If the HTML
parser raises an HTMLParseError, we simply return an empty list.
"""
from HTMLParser import HTMLParser
class GetLinkRelWorksheets(HTMLParser):
def __init__(self):
HTMLParser.__init__(self)
self.worksheets = []
def handle_starttag(self, tag, attrs):
if (tag == 'link' and
('rel', 'alternate') in attrs and
('type', 'application/sage') in attrs):
self.worksheets.append({'title': [_ for _ in attrs if _[0] == 'title'][0][1],
'url': [_ for _ in attrs if _[0] == 'href'][0][1]})
parser = GetLinkRelWorksheets()
with open(fn) as f:
try:
parser.feed(f.read())
except HTMLParseError:
return []
ret = []
for d in parser.worksheets:
sws = d['url']
# is that link a relative URL?
if not urlparse.urlparse(sws).netloc:
# unquote-then-quote to avoid turning %20 into %2520, etc
ret.append({'url': urlparse.urljoin(url, urllib.quote(urllib.unquote(sws))),
'title': d['title']})
else:
ret.append({'url': sws, 'title': d['title']})
return ret
def tree_visualization(request, file_id):
gi = request.galaxy
data = gi.datasets.show_dataset(dataset_id=file_id)
if isinstance(data, dict):
dlurl = data.get('download_url')
historyid = data.get('history_id')
if dlurl and historyid:
url = urlparse.urljoin(gi.base_url, dlurl)
response = urllib.urlopen(url)
return render(request,
template_name='treeviz/tree.html',
context={'newick_tree': response.read(),
'history_id': historyid})
return render(request, 'error.html', {'errortitle': 'Error querying galaxy', 'errormessage': data})
def second_pass(self, response):
base_url = 'https://www.cityoflaurel.org'
links_with_dupes = response.css('div#site-main')[0].css('section#site-content')[0].css('a').xpath('@href').extract()
links = list(set(links_with_dupes))
for link in links:
print("LINK: " + link + '\n')
if link.endswith('.pdf'):
link = urlparse.urljoin(base_url, link)
yield Request(url=link, callback=self.save_pdf)
if "http" not in str(link):
yield Request(url=base_url + link + '/', callback=self.third_pass)
elif "cityoflaurel" in link:
yield Request(url=link, callback=self.third_pass)
else:
yield { "link": link }
def cleanup_url(self, value_url, source_url, mark):
"""
Transform relative URLs into absolute URLs if possible.
If the value_url is already absolute, or we don't know the
source_url, then return the existing value. If the value_url is
relative, and we know the source_url, then try to rewrite it.
"""
value = urlparse.urlparse(value_url)
if value.netloc or not source_url:
url = value_url
else:
url = urlparse.urljoin(source_url, value_url)
if url.startswith('//'):
url = 'http:' + url # MissingSchema fix
if mark:
url = url + mark
return url
def download_scan(self, ignore_files=False):
""" Téléchargement des scan
TODO:
Gérer les authentification HTTP
Remplace subprocess par la librairie curl directement
"""
for scan in self.list_pages_by_chapters():
print(">> Téléchargement du chapitre {}".format(scan[0]))
chapter_dir = "%s_%s" % (DEFAULT_SCAN_CHAPTER_DIRNAME, scan[0])
# On créé le répertoire de destination
chapter_path = self.create_dir(
os.path.join(self.scan_path, self.scan_name, chapter_dir))
for p in scan[1]:
img_found = False
page = "0%s" % p if p < 10 else p
url = urlparse.urljoin(
DEFAULT_SCAN_URL,
"%s/%s/%s" % (self.scan_name, scan[0], page))
# On cherche une URL valide en fonction de
# l'extension des images
for ext in DEFAULT_IMG_EXT:
dl_file = self.download_file(
"%s.%s" % (url, ext),
chapter_path,
ignore_files)
if dl_file:
print(">> Téléchargement de la page {}".format(page))
img_found = True
break
"""TODO: log dans un fichier
Si on a pas du tout trouvé d'image on saute
le téléchargement
"""
if not img_found:
print("la page {} n'a pas été trouvé".format(page))
continue
return
def export_to_itol(request, file_id):
# retrieve newick from galaxy server
gi = request.galaxy
data = gi.datasets.show_dataset(dataset_id=file_id)
if isinstance(data, dict):
dlurl = data.get('download_url')
if dlurl:
url = urlparse.urljoin(gi.base_url, dlurl)
response = urllib.urlopen(url)
tmpfile = tempfile.NamedTemporaryFile()
tmpfile.write(response.read())
tmpfile.flush()
# send file to itol server
url_itol = 'https://itol.embl.de/upload.cgi'
payload = {'tname': "", 'tfile': open(tmpfile.name, 'rb'), }
r = requests.post(url_itol, files=payload)
return redirect(r.url)
return render(request, 'error.html', {'errortitle': 'Error querying galaxy', 'errormessage': data})
def list_scan_chapters(self):
"""Parse la page du scan pour savoir combien de chapitre
sont disponibles.
TODO:
Faire en sorte de gérer les chapitres bonus
Returns:
Nombre de chapitre trouvé
"""
chapters = []
url = urlparse.urljoin(DEFAULT_CHAPTER_URL, "%s/" % self.scan_name)
if self.test_url(url):
html = str(urlopen(url).read())
tabs = re.findall(
r'(<td class="td">)([A-Za-z0-9\-\ \:]+)(chapitre)\ ([0-9]+)',
html)
for t in tabs:
chapters.append(t[3])
print("chapitre {} trouvé".format(t[3]))
return chapters
def download_file(request, file_id):
"""permet a l'utilisateur de telecharger le fichier grace a l'api"""
gi = request.galaxy
data = gi.datasets.show_dataset(dataset_id=file_id)
name = "error"
if isinstance(data, dict):
dlurl = data.get('download_url')
name = data.get('name')
name = name.replace(" ","_")
name = name + "." + data.get('file_ext')
if not name:
name = "download"
if dlurl:
url = urlparse.urljoin(gi.base_url, dlurl)
response = urllib.urlopen(url)
stream_response = StreamingHttpResponse(response.read())
stream_response['Content-Disposition'] = 'attachment; filename=' + name
else:
stream_response = StreamingHttpResponse("No file download URL corresponds to the given dataset id " + file_id)
else:
stream_response = StreamingHttpResponse(data)
return stream_response
def render(self, context):
try:
obj = self.obj.resolve(context)
except template.VariableDoesNotExist:
return ''
try:
prefix = self.get_prefix(obj)
except (AttributeError, KeyError):
return ''
tinyid = converter.from_decimal(obj.pk)
if hasattr(settings, 'SHORT_BASE_URL') and settings.SHORT_BASE_URL:
return urlparse.urljoin(settings.SHORT_BASE_URL, prefix+tinyid)
try:
return urlresolvers.reverse('shorturls.views.redirect', kwargs = {
'prefix': prefix,
'tiny': tinyid
})
except urlresolvers.NoReverseMatch:
return ''
def url(self, path):
return urlparse.urljoin(settings.TEST_DOMAIN, path)
