擅长:python、mysql、java
<pre><code>import mechanicalsoup
import urllib
url = 'http://imaging.occeweb.com/imaging/UIC1012_1075.aspx'
Form = '1012'
API = '15335187'
browser = mechanicalsoup.StatefulBrowser(
user_agent='Mozilla/5.0'
)
browser.open(url)
# Fill-in the search form
browser.select_form('form#Form1')
browser["txtIndex7"] = Form
browser["txtIndex2"] = API
browser.submit_selected("Button1")
# Display the results
for tr in browser.get_current_page().select('table#DataGrid1 tr')[2:]:
try:
pdf_url = tr.select('td')[0].find('a').get('href')
except:
print('Pdf not found')
else:
pdf_id = tr.select('td')[0].text
response = urllib.urlopen(pdf_url) # for python 2.7, for python 3. urllib.request.urlopen()
pdf_str = "C:\\Data\\"+pdf_id+".pdf"
file = open(pdf_str, 'wb')
file.write(response.read())
file.close()
print('Pdf '+pdf_id+' saved')
</code></pre>