def upenn_scraper(name):
print('Retrieving ' + name + "'s email...")
cache = Cache()
try:
email = cache[name]
return email
except KeyError:
pass
first_name, last_name = split_name(name)
query_link = DIRECTORIES.get('upenn')
driver = get_driver()
driver.delete_all_cookies()
driver.get(query_link)
driver.implicitly_wait(5)
driver.find_element_by_css_selector('input[name="lastName"]').send_keys(
last_name)
driver.find_element_by_xpath('//tr[4]//td//input').send_keys(first_name)
driver.find_element_by_css_selector('form a.submitButton').click()
driver.implicitly_wait(5)
try:
email = driver.find_element_by_xpath(
'//tr[contains(@class, "lookupbody")]//a[contains(@href, "mailto")]'
)
email = email.text
print(email)
except selenium.common.exceptions.NoSuchElementException:
email = None
driver.delete_all_cookies()
driver.quit()
if email is not None:
cache[name] = email
return email
def michigan_scraper(name):
print('Retrieving ' + name + "'s email...")
cache = Cache()
try:
email = cache[name]
return email
except KeyError:
pass
name = name.replace(" ", "%20")
query_link = DIRECTORIES.get('michigan')
query_link = query_link.format(name)
driver = get_driver()
driver.get(query_link)
driver.implicitly_wait(5)
try:
driver.find_element_by_xpath(
'//div[@id="peopleContent"]//table[@class="searchResults"]//tbody//tr[1]//td[1]//a[1]'
).click()
driver.implicitly_wait(3)
email = driver.find_element_by_xpath(
'//div[contains(@class, "wrapEmail")]//a[contains(@href, "mailto")]'
)
email = email.text
print(email)
except selenium.common.exceptions.NoSuchElementException:
email = None
driver.quit()
if email is not None:
cache[name] = email
return email
def delaware_scraper(name):
print('Retrieving ' + name + "'s email...")
first_name, last_name = split_name(name)
cache = Cache()
try:
email = cache[name]
return email
except KeyError:
pass
query_link = DIRECTORIES.get('delaware')
driver = get_driver()
driver.get(query_link)
driver.implicitly_wait(5)
driver.find_element_by_id('lastName').send_keys(
last_name)
driver.find_element_by_id('firstName').send_keys(
first_name)
driver.find_element_by_css_selector('form button[type="submit"]').click()
driver.implicitly_wait(5)
time.sleep(3)
try:
email = driver.find_element_by_xpath('//div[contains(@role, "main")]//a[contains(@href, "mailto")]')
email = email.text
print(email)
except selenium.common.exceptions.NoSuchElementException:
email = None
driver.quit()
email = email if email else None
cache[name] = email
return email
def princeton_scraper(name):
print('Retrieving ' + name + "'s email...")
cache = Cache()
try:
email = cache[name]
return email
except KeyError:
pass
query_link = DIRECTORIES.get('princeton')
driver = get_driver()
driver.get(query_link)
driver.implicitly_wait(5)
time.sleep(2)
driver.find_element_by_id('edit-search').send_keys(name + Keys.RETURN)
# pg_loaded = WebDriverWait(driver, 30).until(
# EC.presence_of_element_located((By.ClassName, "results")))
time.sleep(3)
driver.implicitly_wait(3)
driver.find_element_by_id('people-label').click()
tree = fromstring(driver.page_source)
email = tree.xpath(
'//div[contains(@class, "people-search-email")]/a/text()')
driver.quit()
email = email[0] if email else None
if email is not None:
cache[name] = email
return email
def oak_ridge_scraper(name):
print('Retrieving ' + name + "'s email...")
query_link = DIRECTORIES.get('oak ridge')
name = name.replace(" ", "+")
cache = Cache()
try:
email = cache[name]
return email
except KeyError:
pass
query_link = query_link.format(name)
driver = get_driver()
driver.get(query_link)
driver.implicitly_wait(5)
driver.find_element_by_css_selector('td.views-field-nothing a:nth-child(1)').click()
driver.implicitly_wait(5)
try:
email = driver.find_element_by_xpath('//div[contains(@class, "staff-profile-contact-info")]//a[contains(@href, "mailto")]')
email = email.text
print(email)
except NoSuchElementException:
email = None
driver.quit()
if email is not None:
cache[name] = email
return email
def drexel_scraper(name):
print('Retrieving ' + name + "'s email...")
query_link = DIRECTORIES.get('drexel')
name = name.replace(" ", "%20")
cache = Cache()
try:
email = cache[name]
return email
except KeyError:
pass
query_link = query_link.format(name)
driver = get_driver()
driver.get(query_link)
driver.implicitly_wait(5)
time.sleep(3)
tree = fromstring(driver.page_source)
email = tree.xpath(
'//tr[@class="result-row"]//span[@class="email-address"]//a[contains(@href, "mailto")]/text()'
)
print(email)
driver.quit()
email = email[0] if email else None
if email is not None:
cache[name] = email
return email
def temple_scraper(name):
print('Retrieving ' + name + "'s email...")
cache = Cache()
try:
email = cache[name]
return email
except KeyError:
pass
first_name, last_name = split_name(name)
query_link = DIRECTORIES.get('temple')
driver = get_driver()
driver.delete_all_cookies()
driver.get(query_link)
driver.implicitly_wait(5)
driver.find_element_by_id('templeedusn').send_keys(
last_name)
driver.find_element_by_id('templeedugivenname').send_keys(
first_name)
driver.find_element_by_css_selector('form input.Search').click()
driver.implicitly_wait(3)
try:
email = driver.find_element_by_xpath('//div[contains(@id, "Div_Column_02")]//a[contains(@href, "mailto")]')
email = email.text
print(email)
except selenium.common.exceptions.NoSuchElementException:
email = None
driver.delete_all_cookies()
driver.quit()
if email is not None:
cache[name] = email
return email
def minnesota_scraper(name):
print('Retrieving ' + name + "'s email...")
query_link = DIRECTORIES.get('minnesota')
name = name.replace(" ", "+")
cache = Cache()
try:
email = cache[name]
return email
except KeyError:
pass
query_link = query_link.format(name)
driver = get_driver()
driver.get(query_link)
driver.implicitly_wait(5)
time.sleep(3)
tree = fromstring(driver.page_source)
email = tree.xpath(
'//table[contains(@class, "result__single-person")]//a[contains(@href, "mailto")]/text()'
)
print(email)
driver.quit()
email = email[0] if email else None
if email is not None:
cache[name] = email
return email
def rutgers_scraper(name):
print('Retrieving ' + name + "'s email...")
cache = Cache()
try:
email = cache[name]
return email
except KeyError:
pass
query_link = DIRECTORIES.get('rutgers')
driver = get_driver()
driver.get(query_link)
driver.implicitly_wait(5)
driver.find_element_by_id('q').send_keys(name + Keys.RETURN)
wait(driver, 30).until(
EC.frame_to_be_available_and_switch_to_it(
driver.find_element_by_tag_name("iframe")))
time.sleep(3)
try:
email = driver.find_element_by_xpath(
'//div[contains(@id, "content")]//dd//a[contains(@href, "mailto")]'
)
email = email.text
print(email)
except selenium.common.exceptions.NoSuchElementException:
email = None
driver.quit()
email = email[0] if email else None
if email is not None:
cache[name] = email
return email
def virginia_tech_scraper(name):
print('Retrieving ' + name + "'s email...")
cache = Cache()
try:
email = cache[name]
return email
except KeyError:
pass
query_link = DIRECTORIES.get('virginia tech')
driver = get_driver()
driver.get(query_link)
driver.implicitly_wait(5)
time.sleep(3)
driver.find_element_by_id('vt_search_box').send_keys(name + Keys.RETURN)
# pg_loaded = WebDriverWait(driver, 30).until(
# EC.presence_of_element_located((By.ClassName, "results")))
time.sleep(2)
driver.implicitly_wait(5)
#driver.find_element_by_id('people-label').click()
tree = fromstring(driver.page_source)
persons = tree.xpath(
'//div[@id="results"]//div[contains(@class, "vt-person")]')
for person in persons:
vt_name = person.xpath('//a[@class="vt-c-name"]/text()')
if vt_name and all(
[n in vt_name[0].lower() for n in name.lower().split(' ')]):
email = person.xpath('//li[@class="vt-cl-email"]/a/text()')
print(email)
print()
break
else:
email = None
time.sleep(2)
driver.quit()
email = email[0] if email else None
if email is not None:
cache[name] = email
return email
def stony_brook_scraper(name):
print('Retrieving ' + name + "'s email...")
cache = Cache()
try:
email = cache[name]
return email
except KeyError:
pass
query_link = DIRECTORIES.get('stony brook')
name = name.replace(" ", "%20")
query_link = query_link.format(name)
driver = get_driver()
driver.get(query_link)
driver.implicitly_wait(5)
time.sleep(3)
tree = fromstring(driver.page_source)
email = tree.xpath('//tr[@class="data"]//a[@class="email"]/text()')
print(email)
driver.quit()
email = email[0] if email else None
if email is not None:
cache[name] = email
return email
