def RK_LASD(x, pt):
name = 'Results/RK2_201' + str(x) + '.xls'
print('Writing to ' + name + ' ... ...')
initExcel_rk2(name)
url = URL + str(x) + '_'
for i in range(4):
url1 = url + str(i) + '.html'
html = mr.getOnePage(url1, 'utf-8')
pattern = re.compile(pt[i], re.S)
result = re.findall(pattern, html)
if i == 0:
t = 3
l = len(result[0])
for item in result:
for j in range(l):
mr.writeToExcel(name, t, j, item[j])
print(t - 2)
t += 1
else:
t = 3
l = len(result[0])
k = RC2[i] + 1
for item in result:
for j in range(l):
mr.writeToExcel(name, t, j + k, item[j])
print(t - 2)
t += 1
def QS0():
for i in range(11):
url = 'https://www.universityrankings.ch/results?ranking=QS®ion=Asia&year=20' + str(
10 + i) + '&q=China+'
html = mr.getOnePage(url, 'utf-8')
pattern = re.compile(PATTERN, re.S)
result = re.findall(pattern, html)
url = 'https://www.universityrankings.ch' + result[0]
file_name = 'QS20' + s + '.csv'
mr.saveOneFile(file_name, url)
def XYH2017():
name = 'Results/XYH2017-2018.xls'
print('Writing to ' + name + ' ... ...')
mr.initExcel(ROW2017, name)
url = 'https://www.dxsbb.com/news/1383.html'
html = mr.getOnePage(url, 'gbk')
pattern = re.compile(
'<tr height="19"><td x:num="(.*?)</td><td>(.*?)</td><td>(.*?)</td><td>(.*?)</td><td x:num="(.*?)</td></tr>',
re.S)
result = re.findall(pattern, html)
t = 1
pattern1 = re.compile("[\u4e00-\u9fa5]+", re.S)
pattern2 = re.compile("\d+\.?\d*", re.S)
for item in result:
for i in range(5):
if i == 1:
r = re.findall(pattern1, item[i])
mr.writeToExcel(name, t, i, "".join(r))
elif i == 0 or i == 4:
r = re.findall(pattern2, item[i])
mr.writeToExcel(name, t, i, r[0])
else:
mr.writeToExcel(name, t, i, item[i])
print(t)
t += 1
def Times(x):
name = 'Results/Times201' + str(x) + '.xls'
print('Writing to ' + name + ' ... ...')
mr.initExcel(ROW, name)
url = URL1 + str(x) + URL2
html = mr.getOnePage(url, 'utf-8')
pattern = re.compile(PATTERN1, re.S)
result = re.findall(pattern, html)
t = 1
l = len(result[0])
for item in result:
for i in range(l):
mr.writeToExcel(name, t, i, item[i])
print(t)
t += 1
url = URL1 + str(x) + URL3
html = mr.getOnePage(url, 'utf-8')
pattern = re.compile(PATTERN2, re.S)
result = re.findall(pattern, html)
t = 1
l = len(result[0])
for item in result:
for i in range(l):
mr.writeToExcel(name, t, i + 6, item[i])
print(t)
t += 1
def RK_ZHDX(x, row, pt):
name = 'Results/RK201' + str(x) + '.xls'
print('Writing to ' + name + ' ... ...')
mr.initExcel(row, name)
url = URL + str(x) + '.html'
html = mr.getOnePage(url, 'utf-8')
pattern = re.compile(pt, re.S)
result = re.findall(pattern, html)
t = 1
l = len(result[0])
for item in result:
for i in range(l):
mr.writeToExcel(name, t, i, item[i])
print(t)
t += 1
def Scholars():
count = [0, 0, 0]
url = 'http://www.nenu.edu.cn/576/list.htm'
global driver # global driver
fireFoxOptions = webdriver.FirefoxOptions()
fireFoxOptions.set_headless()
driver = webdriver.Firefox(firefox_options=fireFoxOptions)
# driver = webdriver.Firefox()
driver.get(url)
elements = getEleById('wp_content_w8_0')
elements = elements.text
driver.close()
del driver
count[0] = mr.parse2(elements, '院士', '荣誉教授')
count[1] += parse3(elements, '教育部“长江学者奖励计划”特聘教授', '教育部“长江学者奖励计划”青年学者')
count[1] += parse3(elements, '教育部“长江学者奖励计划”青年学者', '教育部“长江学者和创新团队发展计划”带头人')
count[1] += parse3(elements, '教育部“长江学者和创新团队发展计划”带头人', '中国科学院“百人计划”')
count[2] += parse3(elements, '国家“万人计划”哲学社会科学领军人才', '国家“万人计划”科技创新领军人才')
count[2] += parse3(elements, '国家“万人计划”科技创新领军人才', '国家“万人计划”教学名师')
count[2] += parse3(elements, '国家“万人计划”教学名师', '国家杰出青年科学基金获得者')
count[2] += parse3(elements, '国家“万人计划”青年拔尖人才', '国家优秀青年科学基金获得者')
print(count)
writeToExcel(4, count[0])
writeToExcel(5, count[1])
writeToExcel(7, count[2])
def YangtzeRiverScholars():
global count_3
url = 'http://www.math.lb.pku.edu.cn/jsdw/rcjh/index.htm'
html = mr.getOnePage(url)
for item in parseOnePage_YangtzeRiverScholars(html):
print(item)
# writeToFile(YANG, item)
count_3 += 1
def Academician(offset):
global count_2
url = 'http://www.math.lb.pku.edu.cn/jsdw/zgkxyys/index' + offset + '.htm'
html = mr.getOnePage(url)
for item in parseOnePage_Academician(html):
print(item)
# writeToFile(ACA, item)
count_2 += 1
def Library():
url = 'http://lib.csu.edu.cn/bgjs.jhtml'
html = mr.getOnePage(url)
pattern = re.compile('纸质文献总量(.*?)万余册', re.S)
item = re.findall(pattern, html)[0]
count1 = int(float(item) * 10000)
print('中外文藏书合计: ' + str(count1))
writeToExcel(37, count1)
def Library():
url = 'http://www.lib.sdu.edu.cn/page/about.html'
html = mr.getOnePage(url)
pattern = re.compile('馆藏纸质文献(.*?)万余册', re.S)
item = re.findall(pattern, html)[0]
count1 = int(float(item) * 10000)
print('中外文藏书合计: ' + str(count1))
writeToExcel(37, count1)
def RecruitmentProgram():
global count_4
url = 'http://www.math.lb.pku.edu.cn/jsdw/rcjh/index.htm'
html = mr.getOnePage(url)
for item in parseOnePage_RecruitmentProgram(html):
print(item)
# writeToFile(REC, item)
count_4 += 1
def Scholars():
url = 'http://math.jlu.edu.cn/szdw/spys.htm'
html = mr.getOnePage(url)
pattern = re.compile('中国科学院院士', re.S)
items = re.findall(pattern, html)
count = len(items)
print('院士数量: ' + str(count))
writeToExcel(4, count)
def Professor():
count = [0, 0, 0]
departments = ['sxyyysxx', 'xxyjskxx', 'glytjxx', 'gdsxjxyyjzx']
for dep in departments:
c = parseOnePage_Professor(dep)
print(c)
count = mr.listAdd(count, c)
print(count)
for i, item in enumerate(count):
writeToExcel(i + 1, item)
def Scholars():
url = 'http://math.bnu.edu.cn/jzg/rcjh/index.htm'
html = mr.getOnePage(url)
pattern = re.compile('长江学者特聘教授：(.*?)<br />', re.S)
items = re.findall(pattern, html)[0]
pattern = re.compile('([\u4E00-\u9FA5][\u4e00-\u9fa5\\s][\u4e00-\u9fa5])',
re.S)
count = len(re.findall(pattern, items))
print('长江学者人数: ' + str(count))
writeToExcel(5, count)
def main(): mr.initExcel() papers.papers() Peking_University.PKU() Sichuan_University.SCU() Fudan_University.FU() Central_South_University.CSU() Sun_Yat-sen_University.SYSU() Shandong_University.SDU() University_of_Science_and_Technology_of_China.USTC() Shanghai_Jiao_Tong_University.SJTU() Northest_Normal_University.NENU() Jilin_University.JLU() Nankai_University.NKU() Capital_Normal_University.CNU() Beijing_Normal_University.BNU() Tsinghua_University.THU() Awards.AWD() Others.OTH()
def Library():
global count_8
url = 'http://www.math.lb.pku.edu.cn/kxyj/ytsg/index.htm'
html = mr.getOnePage(url)
pattern = re.compile(
'现有纸版文献.*?"font-size:16px">(.*?)</span>.*?外文期刊.*?"font-size:16px">(.*?)</span>.*?中文期刊.*?"font-size:16px">(.*?)</span>',
re.S)
item = re.findall(pattern, html)[0]
count_8.append(item[0])
count_8.append(item[1] + item[2])
def parseOnePage_Professor(dep):
positions = ['js', 'fjs', 'js1']
count = [0, 0, 0]
for i, pos in enumerate(positions):
url = 'http://math.csu.edu.cn/szdw/' + dep + '/' + pos + '.htm'
html = mr.getOnePage(url)
pattern = re.compile('font-size:9pt', re.S)
items = re.findall(pattern, html)
count[i] = int(len(items) / 2)
return count
def Library():
url = 'http://lib.ustc.edu.cn/%e6%9c%ac%e9%a6%86%e6%a6%82%e5%86%b5/%e6%9c%ac%e9%a6%86%e7%ae%80%e4%bb%8b/'
html = mr.getOnePage(url)
pattern = re.compile('实体馆藏中外文书刊(.*?)万册.*?中外文电子期刊近(.*?)万种', re.S)
item = re.findall(pattern, html)[0]
count1 = int(float(item[0]) * 10000)
print('中外文藏书合计: ' + str(count1))
writeToExcel(37, count1)
count2 = int(float(item[1]) * 10000)
print('中外文期刊种类: ' + str(count2))
writeToExcel(40, count2)
def Professors():
count = [0, 0, 0]
url = 'http://math.ustc.edu.cn/new/teachers.php'
global driver
fireFoxOptions = webdriver.FirefoxOptions()
fireFoxOptions.set_headless()
driver = webdriver.Firefox(firefox_options=fireFoxOptions)
# driver = webdriver.Firefox()
driver.get(url)
element = getEleByXpath(
'/html/body/table[3]/tbody/tr/td[3]/table[2]/tbody/tr[3]/td')
element = element.text
driver.close()
del driver
count[0] = mr.parse2(element, '教 授', '访问教授')
count[1] = mr.parse2(element, '副教授', '特任副研究员')
count[2] = mr.parse2(element, '讲师', '博士后')
print(count)
for i, item in enumerate(count):
writeToExcel(i + 1, item)
def Library():
url = 'http://www.library.nenu.edu.cn/Menu/AboutUs/BGGK/TSGJJ.aspx'
html = mr.getOnePage(url)
pattern = re.compile(
'藏书总量约.*?(\d+\.\d+).*?万册。图书.*?电子期刊.*?>(\d+)</span>.*?种，订购', re.S)
items = re.findall(pattern, html)[0]
count1 = int(float(items[0]) * 10000)
print('中外文藏书合计: ' + str(count1))
writeToExcel(37, count1)
print('中外文期刊种类: ' + items[1])
writeToExcel(40, int(items[1]))
def Library():
url = 'http://www.library.fudan.edu.cn/60/list.htm'
html = mr.getOnePage(url)
pattern = re.compile(
'馆藏纸本文献资源约</span><span lang="EN-US" style="color:#333333;">(.*?)</span>.*?中文报刊</span><span lang="EN-US" style="color:#333333;">(.*?)</span>.*?外文报刊</span><span lang="EN-US" style="color:#333333;">(.*?)</span>',
re.S)
items = re.findall(pattern, html)[0]
count1 = int(float(items[0]) * 10000)
print('中外文藏书合计: ' + str(count1))
writeToExcel(37, count1)
count2 = int(items[1]) + int(items[2])
print('中外文期刊种类: ' + str(count2))
writeToExcel(40, count2)
def Library():
url = 'http://lib.tsinghua.edu.cn/about/collection.html'
html = mr.getOnePage(url)
pattern = re.compile('实体馆藏总量约(.*?)万册（件）.*?各类数据库(\d+)个；电子期刊(.*?)万种', re.S)
items = re.findall(pattern, html)[0]
count1 = int(float(items[0]) * 10000)
print('中外文藏书合计: ' + str(count1))
writeToExcel(37, count1)
count2 = int(float(items[2]) * 10000)
print('中外文期刊种类: ' + str(count2))
writeToExcel(40, count2)
print('购买数据库数量: ' + items[1])
writeToExcel(39, int(items[1]))
def Projects():
count = [0, 0]
url = 'http://www.nenu.edu.cn/273/list.htm'
html = mr.getOnePage(url)
count[0] += parse4(html, '由国家社科基金资助设立的重大项目：', '由教育部社科司资助设立的重大课题：')
count[0] += parse4(html, '由国家自然科学基金资助的、面向世界科学前沿的重大基础研究项目，如：',
'由科技部资助的以国家重大需求为导向的重大科学问题研究项目（含课题），如：')
count[1] += parse4(html, '由教育部社科司资助设立的重大课题：', '科技项目')
count[1] += parse4(html, '由科技部资助的以国家重大需求为导向的重大科学问题研究项目（含课题），如：', '')
print('国家科研项目数', count[0])
writeToExcel(25, count[0])
print('省部科研项目数', count[1])
writeToExcel(26, count[1])
def Library():
url = 'http://lib.jlu.edu.cn/portal/about/about.aspx'
html = mr.getOnePage(url)
pattern = re.compile('各类纸质书刊(\d+)万册，其中.*?订购中文期刊(\d+)种，外文期刊(\d+)种，报.*?西文文献数据库(\d+)种，中文数据库(\d+)种，中', re.S)
items = re.findall(pattern, html)[0]
count1 = int(float(items[0]) * 10000)
print('中外文藏书合计: ' + str(count1))
writeToExcel(37, count1)
count2 = int(items[1]) + int(items[2])
print('中外文期刊种类: ' + str(count2))
writeToExcel(40, count2)
count3 = int(items[3]) + int(items[4])
print('购买数据库数量: ' + str(count3))
writeToExcel(39, count3)
def Library():
url = 'http://www.lib.bnu.edu.cn/content/guan-chang-ji-yu'
html = mr.getOnePage(url)
pattern = re.compile(
'纸本文献总量达(.*?)万余册，中外文全文电子期刊(\d+)万余种，中外文.*?引进中外文数据库(\d+)个，自', re.S)
items = re.findall(pattern, html)[0]
count1 = int(float(items[0]) * 10000)
print('中外文藏书合计: ' + str(count1))
writeToExcel(37, count1)
count2 = int(float(items[1]) * 10000)
print('中外文期刊种类: ' + str(count2))
writeToExcel(40, count2)
print('购买数据库数量: ' + items[2])
writeToExcel(39, int(items[2]))
def ResearchAward():
global count_5, count_6, count_7
url = 'http://www.math.lb.pku.edu.cn/kxyj/kyjl/index.htm'
html = mr.getOnePage(url)
for item in parseOnePage_ResearchAward_1(html):
print(item)
# writeToFile(RES, item)
count_5 += 1
for item in parseOnePage_ResearchAward_2(html):
print(item)
# writeToFile(RES, item)
count_6 += 1
for item in parseOnePage_ResearchAward_3(html):
print(item)
# writeToFile(RES, item)
count_7 += 1
def Professor(offset):
global count_1
url = 'http://www.math.lb.pku.edu.cn/jsdw/js_20180628175159671361/index' + str(
offset) + '.htm'
html = mr.getOnePage(url)
for item in parseOnePage_Professor(html):
print(item)
# writeToFile(PRO, item)
if item['position'] == '教授':
count_1[0] += 1
elif item['position'] == '副教授':
count_1[1] += 1
elif item['position'] == '讲师':
count_1[2] += 1
else:
count_1[3] += 1
def Professor():
url = 'http://sms.nankai.edu.cn/5542/list.htm'
html = mr.getOnePage(url)
pattern = re.compile(
'数学学科现有教师(\d+)人，教授(\d+)人、博士.*?博士学位的(\d+)人。其中，中国科学院院士(\d+)人、第三', re.S)
items = re.findall(pattern, html)[0]
count1 = items[1]
print('教授数量: ' + str(count1))
writeToExcel(1, count1)
count2 = int(items[2]) / int(items[0])
count2 = '%.2f%%' % (count2 * 100)
print('教师博士数量: ' + str(count2))
writeToExcel(8, count2)
count3 = items[3]
print('院士数量: ' + str(count3))
writeToExcel(4, count3)
def ResearchAward():
count = [0, 0, 0]
url = 'http://www.nenu.edu.cn/275/list.htm'
html = mr.getOnePage(url)
pattern = re.compile(
'学术专著(\d+)部，获得省部级科研奖励(\d+)项。6部著.*?文库》；(\d+)项成果获得全国高等.*?奖2项）；(\d+)项成果获全国教育',
re.S)
items = re.findall(pattern, html)[0]
count[0] = int(items[2]) + int(items[3])
count[1] = int(items[1])
count[2] = int(items[0])
print('国家奖', count[0])
writeToExcel(9, count[0])
print('省部级奖', count[1])
writeToExcel(10, count[1])
print('学术专著', count[2])
writeToExcel(19, count[2])
def WSL2(row, x, url, pt):
name = 'Results/WSL201' + str(x) + '.xls'
print('Writing to ' + name + ' ... ...')
mr.initExcel(row, name)
url = 'https://www.dxsbb.com/news/' + url
html = mr.getOnePage(url, 'gbk')
pattern = re.compile(pt, re.S)
result = re.findall(pattern, html)
t = 1
l = len(result[0])
pattern1 = re.compile("[\u4e00-\u9fa5]+", re.S)
for item in result:
for i in range(l):
if i == 1:
r = re.findall(pattern1, item[i])
mr.writeToExcel(name, t, i, "".join(r))
else:
mr.writeToExcel(name, t, i, item[i])
print(t)
t += 1