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()
#!/usr/bin/python
# -*-coding:UTF-8-*-
# encoding=utf8
from com.office.util.excelUtil import write
from com.office.util.wordUtil import readDocx
content = readDocx("/Users/yangjie/Downloads/qq/(最完整版)胡希恕讲伤寒论.docx")
lines = content.split(u"。")
resultData = []
for line in lines:
resultData.append([line])
write(resultData, "/Users/yangjie/Downloads/qq/(最完整版)胡希恕讲伤寒论.xls")
#!/usr/bin/python
# -*-coding:UTF-8-*-
# encoding=utf8
import matplotlib.pyplot as plt
import numpy as np
from com.office.util.excelUtil import write
plt.figure(figsize=(9, 6), dpi=100)
n = 100
#rand 均匀分布和 randn高斯分布
r = []
for i in range(6):
x = np.random.randn(1, n)
r.append(x[0])
write(r, "scatterplot.xls")
print x
y = np.random.randn(1, n)
print y
T = np.arctan2(x, y)
print T
plt.scatter(x, y, c=T, s=25, alpha=0.4, marker='o')
#T:散点的颜色
#s：散点的大小
#alpha:是透明程度
plt.show()
)
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
else:
driver.get("http://www.ncbi.nlm.nih.gov/pccompound")
mylists.reverse()
for key in mylists:
if key in pubChem.recorddata:
print "chuliguo"
continue
else:
try:
key = key[0]
print "处理", key
getchemID(key)
write(result, pubChem.resultPathname)
write(pubChem.recorddata, pubChem.recordPathname)
except Exception, e:
import traceback
print traceback.format_exc()
print "3", e
if rowDate[2] != "":
cacheline = []
cacheline.append(rowDate[2])
if rowDate[3] != "":
lastSrc = rowDate[3]
cacheline.append(lastSrc)
cache.append(cacheline)
resultDate = []
for rowDate in srcDate:
newLine = []
newLine.append(rowDate[0])
if rowDate[1] != "":
newLine.append(rowDate[1])
newLine.append("TCMID")
else:
if len(cache) != 0:
takeCache = cache[0]
cache.remove(takeCache)
newLine.extend(takeCache)
resultDate.append(newLine)
for cacheData in cache:
newLine = []
newLine.append("")
newLine.extend(cacheData)
resultDate.append(newLine)
print resultDate
write(resultDate, "六神曲_res.xls")
#!/usr/bin/python
#-*-coding:UTF-8-*-
# encoding=utf8
from com.office.util.excelUtil import write
resultDate = []
for i in range(3):
resultDate.append(range(3))
print resultDate
write(resultDate, "num.xls")
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:
driver.find_element_by_xpath(
"//a[@id='EntrezSystem2.PEntrez.PubMed.Pubmed_ResultsPanel.Entrez_Pager.Page' and @sid='3']"
).send_keys(Keys.ENTER)
print "下一页"
import time
time.sleep(1)
except Exception, e:
print "已到尾页"
break