def doSomething(keyword):
key = keyword
driver.get("https://www.ncbi.nlm.nih.gov/pccompound/?term=" + keyword)
retry(lambda: driver.find_element_by_id("msgportlet"))
try:
msgEle = driver.find_element_by_id("msgportlet")
if "No items found." in msgEle.text:
f3.write(key)
return
except Exception, e:
del e
def doSomething(driver, keyword, tableId, pfi):
key = keyword;
driver.get("https://www.ncbi.nlm.nih.gov/pccompound/?term="+keyword);
retry(lambda:driver.find_element_by_id("msgportlet"));
try:
msgEle = driver.find_element_by_id("msgportlet");
if "No items found." in msgEle.text:
addResult([[key,"None","None","None","None"]])
updateStatus(STATUS_SUCCESS, tableId)
return
except Exception,e:
del e
def processInNewDriver(href):
'''
处理文章链接
'''
print "处理链接", href
driverContent = webdriver.Chrome(executable_path=executable_path)
driverContent.get(href)
retry(lambda: driver.find_element_by_class_name("rprt_all"))
contentEle = driverContent.find_element_by_class_name("rprt_all")
content = contentEle.text
for key in keys:
if content.find(key) != -1:
print "find"
reusltData.append([href, key])
write(reusltData, FILENAME_RESULT)
break
recoreDate.append([href])
driverContent.quit()
def getPro(key,myid):
text=""
retry(lambda:driver.find_element_by_id("local-searchbox"))
driver.find_element_by_id("local-searchbox").send_keys(key)
retry(lambda:driver.find_element_by_class_name("submit"))
driver.find_element_by_class_name("submit").click()
try:
chiTbls=driver.find_elements_by_xpath("//td[@class='gridLayoutCellTitle']/a")
a_text=chiTbls[0].text
print a_text
if a_text.lower()==key.lower():
Url=chiTbls[0].get_attribute("href")
fi=driver.get("http://www.ebi.ac.uk/chebi/"+Url)
chikey=driver.find_elements_by_class_name("chebiDataHeader")
text=chikey[1].text
print text
fi.quit()
except Exception, e:
print e
pass;
def initDriver():
driver = webdriver.Chrome(executable_path=executable_path)
#跳到网址
retry(lambda: driver.get("http://www.ncbi.nlm.nih.gov/pubmed/"))
#填入查询字段
keyword = "Worldviews On Evidence-Based Nursing"
retry(lambda: driver.find_element_by_id("term").clear())
retry(lambda: driver.find_element_by_id("term").send_keys(keyword))
#点击查询按钮
retry(lambda: driver.find_element_by_id("search").click())
return driver
def getchemID(key):
while True:
if driver.current_url == "http://www.ncbi.nlm.nih.gov/pccompound":
chat = driver.find_element_by_id("term")
chat.clear()
chat.send_keys(key)
driver.find_element_by_id("search").click()
try:
retry(lambda: driver.find_element_by_xpath(
"//table[@class='top-summary-items']/tbody/tr/td"))
ID1 = driver.find_element_by_xpath(
"//table[@class='top-summary-items']/tbody/tr/td").text
Moleculars = driver.find_elements_by_xpath(
"//table[@class='top-summary-items']/tbody/tr/td/a")
Molecular1 = Moleculars[1].text
print Molecular1
result.append([key, ID1, Molecular1])
pubChem.recorddata.append([key])
driver.back()
break
except Exception, e:
print "1", e
import traceback
print traceback.format_exc()
try:
retry(lambda: driver.find_elements_by_xpath(
"//div[@class='content']/div/div/div/div/p/a"))
myTagas = driver.find_elements_by_xpath(
"//div[@class='content']/div/div/div/div/p/a")
for myTaga in myTagas:
if key.upper() in myTaga.text.upper():
href = myTaga.get_attribute("href")
drivercontent = webdriver.Chrome(driverPathname)
drivercontent.get(href)
retry(lambda: drivercontent.find_element_by_xpath(
"//table[@class='top-summary-items']/tbody/tr/td"))
ID2 = drivercontent.find_element_by_xpath(
"//table[@class='top-summary-items']/tbody/tr/td"
).text
Moleculars1 = drivercontent.find_elements_by_xpath(
"//table[@class='top-summary-items']/tbody/tr/td/a"
)
Molecular2 = Moleculars1[1].text
result.append([key, ID2, Molecular2])
pubChem.recorddata.append([key])
drivercontent.quit()
return
except Exception, e:
result.append([key, "NA", "NA"])
pubChem.recorddata.append([key])
break
def getchemID(key):
while True:
if driver.current_url == "https://www.ncbi.nlm.nih.gov/pccompound":
chat = driver.find_element_by_id("term")
chat.clear()
chat.send_keys(key)
driver.find_element_by_id("search").click()
try:
retry(lambda: driver.find_element_by_xpath(
"//table[@class='top-summary-items']/tbody/tr/td"))
ID1 = driver.find_element_by_xpath(
"//table[@class='top-summary-items']/tbody/tr/td").text
result.append([key, ID1])
driver.back()
break
except Exception, e:
print e
try:
retry(lambda: driver.find_elements_by_xpath(
"//div[@class='content']/div/div/div/div/p/a"))
myTagas = driver.find_elements_by_xpath(
"//div[@class='content']/div/div/div/div/p/a")
key.upper()
if len(myTagas) == 0:
result.append([key, "NA", "NA"])
break
else:
for myTaga in myTagas:
if key.upper() in myTaga.text.upper():
href = myTaga.get_attribute("href")
drivercontent = webdriver.Chrome(
"/Users/yangjie/Documents/env/python/chromedriver_2.21/chromedriver_mac32/chromedriver"
)
drivercontent.get(href)
retry(lambda: drivercontent.find_element_by_xpath(
"//table[@class='top-summary-items']/tbody/tr/td"
))
ID2 = drivercontent.find_element_by_xpath(
"//table[@class='top-summary-items']/tbody/tr/td"
).text
result.append([key, ID2])
drivercontent.quit()
return
else:
pass
except Exception, e:
result.append([key, "NA"])
print e
break
def doSomething(driver, keyword, tableId, pfi):
driver.switch_to_default_content();
retry(lambda:driver.find_element_by_id("txt_1_value1").clear())
retry(lambda:driver.find_element_by_id("txt_1_value1").send_keys(keyword))
retry(lambda:driver.find_element_by_id("btnSearch").click())
time.sleep(0.1)
while True:
waitDlgEle = driver.find_element_by_id("Search__Waiting")
style = waitDlgEle.get_attribute("style");
if -1 == str(style).find("display: none;"):
time.sleep(0.1);
else:
break
driver.switch_to_frame("iframeResult")
driver.find_element_by_class_name("brief_downloadIcon").send_keys(Keys.ENTER)
time.sleep(0.1)
if len(driver.window_handles) == 2:
driver.switch_to_window(driver.window_handles[1]);
driver.close()
driver.switch_to_window(driver.window_handles[0]);
time.sleep(0.1)
driver.switch_to_frame("iframeResult")
aEle = driver.find_element_by_xpath("//a[@class='fz14']")
if keyword in aEle.text:
aEle.click();
driver.switch_to_window(driver.window_handles[1]);
aLinkEles = driver.find_elements_by_xpath("//div[@id='QK_nav']/ul/li/a");
for aLinkEle in aLinkEles:
aLinkEle.parent
print aLinkEle.text;
if aLinkEle.text == u"CAJ下载":
aLinkEle.send_keys(Keys.ENTER);
break;
driver.find_element_by_link_text(u"CAJ下载").send_keys(Keys.ENTER)
try:
result = driver.find_element_by_id("ChDivSummary").text;
addResult([[keyword,result,'']])
except:
addResult([[keyword,u'摘要获取失败','']])
driver.close()
driver.switch_to_window(driver.window_handles[0]);
else:
addResult([[keyword,'','']])
updateStatus(STATUS_SUCCESS, tableId)
driver = pfi.driver
while True:
try:
raiseOnError = True
try:
driver.get(URL % quote(keyword))
except KeyError, ke:
addResult([[keyword, "KEYERR", "KEYERR"]])
updateStatus(STATUS_SUCCESS, tableId)
break
time.sleep(0.1)
isFind = True
if driver.title.endswith("NCBI"):
#result_count
if retry(lambda: driver.find_element_by_id("result_sel"),
times=10,
allowError=True,
raiseOnError=raiseOnError):
pass
#success
else:
#error
updateStatus(STATUS_NON, tableId)
pfi.needInitDriver = True
break
isFind = False
retry(lambda: driver.find_elements_by_xpath(
"//div[@class='content']/div/div/div/div/p/a"),
times=10,
allowError=True,
raiseOnError=raiseOnError)
myTagas = driver.find_elements_by_xpath(
@author: yangjie
'''
from com.office.util.codeUtil import forbidCodeErr
import time
from com.office.util.pubUtil import retry
forbidCodeErr()
# #使用第三方库，模拟浏览器登录
from selenium import webdriver
driver = webdriver.Chrome(
executable_path="/Users/jyang/work/env/py/selenium/chromedriver")
driver.get("https://www.mi.com/index.html")
while True:
try:
if r"item.mi.com/product" in driver.current_url:
driver.find_element_by_link_text(u"加入购物车").click()
elif r"static.mi.com/buySuccess" in driver.current_url:
driver.find_element_by_link_text(u"去购物车结算").click()
elif r"static.mi.com/cart/" in driver.current_url:
driver.find_element_by_link_text(u"去结算").click()
elif r"order.mi.com/buy/checkout" in driver.current_url:
retry(lambda: driver.find_element_by_class_name("J_addressItem").
click(),
raiseOnError=True)
retry(lambda: driver.find_element_by_link_text(u"立即下单").click(),
raiseOnError=True)
break
except:
time.sleep(0.01)
continue
def doSomething(driver, keyword, tableId, pfi):
key = keyword;
driver.get("https://www.ncbi.nlm.nih.gov/pccompound/?term="+keyword);
retry(lambda:driver.find_element_by_id("msgportlet"));
try:
msgEle = driver.find_element_by_id("msgportlet");
if "No items found." in msgEle.text:
addResult([[key,"None","None","None","None"]])
updateStatus(STATUS_SUCCESS, tableId)
return
except Exception,e:
del e
try:
retry(lambda:driver.find_element_by_xpath("//table[@class='top-summary-items']/tbody/tr/td"))
resID=driver.find_element_by_xpath("//table[@class='top-summary-items']/tbody/tr/td").text
cs =""
try:
retry(lambda:driver.find_element_by_xpath('//*[@id="Canonical-SMILES"]/div/div[@class="section-content-item"]'))
cs=driver.find_element_by_xpath('//*[@id="Canonical-SMILES"]/div/div[@class="section-content-item"]').text
except Exception,e:
del e
pass
addResult([[key,driver.current_url,resID,cs,""]])
updateStatus(STATUS_SUCCESS, tableId)
return
except Exception,e:
del e
retry(lambda:driver.find_elements_by_xpath("//div[@class='content']/div/div/div/div/p/a"))
myTagas=driver.find_elements_by_xpath("//div[@class='content']/div/div/div/div/p/a")
forbidCodeErr()
from selenium import webdriver
def getPro(key):
url = "http://omim.org/entry/" + key
print url
driver.get(url)
try:
driver.find_element_by_id("donationClose").click()
except Exception, e:
pass
description = ""
clinicalFeatures = ""
try:
retry(lambda: driver.find_element_by_xpath(
"//td[@id='floatingEntryContainer']/table/tbody/tr/td"))
tdEles = driver.find_elements_by_xpath(
"//td[@id='floatingEntryContainer']/table/tbody/tr/td")
for i in range(len(tdEles)):
if tdEles[i].get_attribute("id") == "description":
description = tdEles[i + 1].text
elif tdEles[i].get_attribute("id") == "clinicalFeatures":
clinicalFeatures = tdEles[i + 1].text
except Exception, e:
print e
f2.write(key + "\t" + description + "\r" + clinicalFeatures + "\n")
f1 = open("omim-id", "r").readlines()
f2 = open("omim-description", "a")
driverPathname = "/Users/yangjie/Documents/env/python/chromedriver_2.21/chromedriver_mac32/chromedriver"
profile.update_preferences()
driver = webdriver.Chrome(executable_path="/Users/yangjie/mywork/icode/cloudnms/sky-auto/autouitest/driver/chrome/chromedriver_mac32/chromedriver")
time.sleep(0.1)
driver.get("http://apply.hzcb.gov.cn/apply/app/status/norm/person")
time.sleep(0.1)
qihaoEle = driver.find_element_by_id("issueNumber")
qihaoSelect = Select(qihaoEle)
all_options = qihaoSelect.options;
optStrs = []
for all_option in all_options:
optStrs.append(all_option.text)
print optStrs
for optStr in optStrs[1:]:
print optStr
retry(lambda:Select(driver.find_element_by_id("issueNumber")).select_by_value(optStr))
retry(lambda:driver.find_element_by_xpath('//*[@id="search"]').click())
retry(lambda:driver.find_element_by_class_name("totalcount").text)
total = int(driver.find_element_by_class_name("totalcount").text)
d = {}
lastText = ""
while True:
try:
# 找出当前页的所有名字
trEles = driver.find_elements_by_class_name("content_data") + driver.find_elements_by_class_name("content_data1");
for trEle in trEles:
tdEles = trEle.find_elements_by_tag_name("td");
d[tdEles[0].text] = tdEles[1].text
# 点击下一页
try:
nextEles = driver.find_elements_by_class_name("taiji_pager_item");
from selenium import webdriver
pfi.driver = webdriver.Chrome(executable_path=DIRVER_PATHNAME)
pfi.driver.get(URL)
except Exception, e:
print 'initDriver error', e
updateStatus(STATUS_NON, tableId)
return
pfi.needInitDriver = False
updateStatus(STATUS_IN_PROCESS, tableId)
driver = pfi.driver
while True:
try:
if driver.current_url == URL:
raiseOnError = True
retry(lambda: driver.find_element_by_id("term").clear(),
times=10,
allowError=True,
raiseOnError=raiseOnError)
retry(lambda: driver.find_element_by_id("term").send_keys(
keyword),
times=10,
allowError=True,
raiseOnError=raiseOnError)
retry(lambda: driver.find_element_by_id("search").click(),
times=10,
allowError=True,
raiseOnError=raiseOnError)
time.sleep(0.1)
isFind = True
if driver.title.endswith("NCBI"):
#result_count
if retry(lambda: driver.find_element_by_id("result_sel"),
retry(lambda: driver.find_element_by_class_name("rprt_all"))
contentEle = driverContent.find_element_by_class_name("rprt_all")
content = contentEle.text
for key in keys:
if content.find(key) != -1:
print "find"
reusltData.append([href, key])
write(reusltData, FILENAME_RESULT)
break
recoreDate.append([href])
driverContent.quit()
while True:
retry(lambda: driver.find_elements_by_xpath("//p[@class='title']/a"))
aEles = driver.find_elements_by_xpath("//p[@class='title']/a")
hrefs = []
for aEle in aEles:
href = aEle.get_attribute("href")
if href in matchRecordData:
print "processd ", href
else:
hrefs.append(href)
if 0 == len(hrefs):
print "no new href"
else:
doInThread(processInNewDriver, hrefs, poolNum=4)
write(recoreDate, FILENAME_RECORD)
try:
