def run_tool(tool_id,
history_id,
params,
api_key,
galaxy_url,
wait=True,
sleep_time=None,
**kwargs):
sleep_time = sleep_time or DEFAULT_SLEEP_TIME
tools_url = urljoin(galaxy_url, 'api/tools')
payload = {
'tool_id': tool_id,
}
if history_id:
payload['history_id'] = history_id
payload['inputs'] = params
rval = post(api_key, tools_url, payload)
if wait:
outputs = list(rval['outputs'])
while outputs:
finished_datasets = []
for i, dataset_dict in enumerate(outputs):
if dataset_is_terminal(dataset_dict['id'],
api_key=api_key,
galaxy_url=galaxy_url):
finished_datasets.append(i)
for i in reversed(finished_datasets):
outputs.pop(0)
if wait and outputs:
time.sleep(sleep_time)
return rval
def update(self):
'''
更新Question，并获取Answers
'''
self.lastModified = str(datetime.datetime.now())
qurl = 'http://www.zhihu.com/question/%d' % (self.qid)
r = get(qurl)
if r.status_code != 200:
return False
soup = BeautifulSoup(r.text)
# 标题
self.title = soup.find('h2', class_='zm-item-title').text.strip()
# 内容
self.detail = soup.find('div', id='zh-question-detail').div.text.strip()
# 所属的话题标签
self.tags = [a.string.strip() for a in soup.find_all("a", class_='zm-item-tag')]
# 关注人数
followersCountBlock = soup.find('div', class_='zg-gray-normal')
if followersCountBlock is None or followersCountBlock.strong is None:
# 当”还没有人关注该问题” followersCountBlock.strong is None
self.followersCount = 0
else:
self.followersCount = parseNum(followersCountBlock.strong.text)
self.answers = []
# 回答数目
answersCountBlock = soup.find('h3', id='zh-question-answer-num')
if answersCountBlock is None:
if soup.find('span', class_='count') is not None:
answersCount = 1
else:
answersCount = 0
else:
answersCount = int(answersCountBlock['data-num'])
# 答案部分 每次50个
for block in soup.find_all('div', class_='zm-item-answer'):
if block.find('div', class_='answer-status') is not None:
continue # 忽略建议修改的答案
self.answers.append(self._extractAnswer(block))
if answersCount > 50:
_xsrf = soup.find('input', attrs={'name': '_xsrf'})['value']
otherHeaders = {'Referer': qurl}
for i in range(1, math.ceil(answersCount/50)): # more answers
data = {"_xsrf": _xsrf, "method": 'next', 'params': '{"url_token": %d, "pagesize": 50, "offset": %d}' % (self.qid, i*50)}
r = post('http://www.zhihu.com/node/QuestionAnswerListV2', otherHeaders, data)
for block in r.json()['msg']:
div = BeautifulSoup(block).div
if div.find('div', class_='answer-status') is not None:
continue # 忽略建议修改的答案
self.answers.append(self._extractAnswer(div))
return True
def get_second_type(data_id, offset):
"""
获取二级类别的地址
"""
url = 'https://www.zhihu.com/node/TopicsPlazzaListV2'
params = '{"topic_id": %d,"offset": %d,"hash_id": ""}'
postData = {'method': 'next', 'params': params % (int(data_id), int(offset))}
rst = common.post(url, isjson=True, formdata=postData)
if rst:
return rst['msg']
else:
return ''
def run_tool( tool_id, history_id, params, api_key, galaxy_url, wait=True, sleep_time=None, **kwargs ):
sleep_time = sleep_time or DEFAULT_SLEEP_TIME
tools_url = urljoin( galaxy_url, 'api/tools' )
payload = {
'tool_id': tool_id,
}
if history_id:
payload['history_id'] = history_id
payload[ 'inputs' ] = params
rval = post( api_key, tools_url, payload )
if wait:
outputs = list( rval['outputs'] )
while outputs:
finished_datasets = []
for i, dataset_dict in enumerate( outputs ):
if dataset_is_terminal( dataset_dict['id'], api_key=api_key, galaxy_url=galaxy_url ):
finished_datasets.append( i )
for i in reversed( finished_datasets ):
outputs.pop( 0 )
if wait and outputs:
time.sleep( sleep_time )
return rval
GALAXY_PATH = 'YOUR_GALAXY_PATH'
sys.path.insert(1, os.path.join(GALAXY_PATH, 'scripts/api'))
import common # noqa: E402,I100,I202
# Select "W5 - Metagenomics" from published workflows
workflow_name = 'W5 - Metagenomics'
workflows = common.get(API_KEY, '%s/workflows?show_published=True' % API_URL)
w = [_ for _ in workflows if _['published'] and _['name'] == workflow_name]
assert len(w) == 1
w = w[0]
# Import the workflow to user space
data = {'workflow_id': w['id']}
iw = common.post(API_KEY, '%s/workflows/import' % API_URL, data)
iw_details = common.get(API_KEY, '%s/workflows/%s' % (API_URL, iw['id']))
# Select the "Orione SupMat" library
library_name = 'Orione SupMat'
libraries = common.get(API_KEY, '%s/libraries' % API_URL)
l = [_ for _ in libraries if _['name'] == library_name]
assert len(l) == 1
l = l[0]
# Select the "/Metagenomics/MetagenomicsDataset.fq" dataset
ds_name = '/Metagenomics/MetagenomicsDataset.fq'
contents = common.get(API_KEY, '%s/libraries/%s/contents' % (API_URL, l['id']))
ld = [_ for _ in contents if _['type'] == 'file' and _['name'] == ds_name]
import common
print common.post()
#file
fo = open('1.txt', 'wb')
print "file name:", fo.name
#fo.close()
print "is close:", fo.closed
fo.write("hello python\n")
GALAXY_PATH = 'YOUR_GALAXY_PATH'
sys.path.insert(1, os.path.join(GALAXY_PATH, 'scripts/api'))
import common # noqa: E402
# Select "W5 - Metagenomics" from published workflows
workflow_name = 'W5 - Metagenomics'
workflows = common.get(API_KEY, '%s/workflows?show_published=True' % API_URL)
w = [_ for _ in workflows if _['published'] and _['name'] == workflow_name]
assert len(w) == 1
w = w[0]
# Import the workflow to user space
data = {'workflow_id': w['id']}
iw = common.post(API_KEY, '%s/workflows/import' % API_URL, data)
iw_details = common.get(API_KEY, '%s/workflows/%s' % (API_URL, iw['id']))
# Select the "Orione SupMat" library
library_name = 'Orione SupMat'
libraries = common.get(API_KEY, '%s/libraries' % API_URL)
l = [_ for _ in libraries if _['name'] == library_name]
assert len(l) == 1
l = l[0]
# Select the "/Metagenomics/MetagenomicsDataset.fq" dataset
ds_name = '/Metagenomics/MetagenomicsDataset.fq'
contents = common.get(API_KEY, '%s/libraries/%s/contents' % (API_URL, l['id']))
ld = [_ for _ in contents if _['type'] == 'file' and _['name'] == ds_name]
GALAXY_PATH = 'YOUR_GALAXY_PATH'
sys.path.insert(1, os.path.join(GALAXY_PATH, 'scripts/api'))
import common # noqa: E402,I100,I202
# Select "W5 - Metagenomics" from published workflows
workflow_name = 'W5 - Metagenomics'
workflows = common.get(API_KEY, f"{API_URL}/workflows?show_published=True")
w = [_ for _ in workflows if _['published'] and _['name'] == workflow_name]
assert len(w) == 1
w = w[0]
# Import the workflow to user space
data = {'workflow_id': w['id']}
iw = common.post(API_KEY, f"{API_URL}/workflows/import", data)
iw_details = common.get(API_KEY, f"{API_URL}/workflows/{iw['id']}")
# Select the "Orione SupMat" library
library_name = 'Orione SupMat'
libraries = common.get(API_KEY, f"{API_URL}/libraries")
l = [_ for _ in libraries if _['name'] == library_name]
assert len(l) == 1
l = l[0]
# Select the "/Metagenomics/MetagenomicsDataset.fq" dataset
ds_name = '/Metagenomics/MetagenomicsDataset.fq'
contents = common.get(API_KEY, f"{API_URL}/libraries/{l['id']}/contents")
ld = [_ for _ in contents if _['type'] == 'file' and _['name'] == ds_name]