swdriver = webdriver.Chrome(chrome_options=chromeOptions)
swdriver.get(url)
#finding where the table lives and getting a list of the elements
table_body_elements = swdriver.find_elements_by_xpath(
"/html/body/div[4]/div/div/table/tbody/tr")
print('Found {} sound file links on this page... \n'.format(
len(table_body_elements) - 1))
print("Scraping for URL pairs...")
progress = ProgressBar(len(table_body_elements) - 1, fmt=ProgressBar.FULL)
sound_metadata_url_pairs = []
#grabbing the urls for each sound and metadata occuring on the table in the page
for row in table_body_elements[1:]:
progress.current += 1
progress.__call__()
#grabbing the href for the sound file
sound_el = row.find_elements_by_xpath(".//td[4]/a")[0]
#print("Found sound data at: {}".format(download_el.get_attribute("href")))
temp_sound_url = str(sound_el.get_attribute("href"))
#each file in the watkins db has a unique identifyer, here's one way to grab it:
temp_file_id = str(temp_sound_url).split("/")[-1].split(".")[0]
#grabbing the href for the metadata for the .wav file (has the same format for all, with replaced id)
temp_metadata_url = "https://cis.whoi.edu/science/B/whalesounds/metaData.cfm?RN={}".format(
temp_file_id)
sound_metadata_url_pairs.append([temp_sound_url, temp_metadata_url])
