Upload some example code

Author: 0xyd

get.py

@@ -0,0 +1,41 @@
+'''
+    Performance Comparison between requests and pycurl
+'''
+import time
+import requests
+import pycurl
+from io import BytesIO
+
+def pycurl_get():
+    b = BytesIO()
+    c = pycurl.Curl()
+    c.setopt(c.URL, 'https://httpbin.org/ip')
+    c.setopt(c.WRITEDATA, b)
+    c.perform()
+    c.close()
+    body = b.getvalue()
+    print('pycurl_get: %s' % body.decode('utf8'))
+
+def requests_get():
+    r = requests.get('https://httpbin.org/ip')
+    print('requests_get: %s' % r.text)
+
+def main():
+    start_time = time.time()
+    for i in range(100):
+        requests_get()
+    end_time = time.time()
+    request_time = end_time - start_time
+    
+    start_time = time.time()
+    for i in range(100):
+        pycurl_get()
+    end_time = time.time()
+    pycurl_time = end_time - start_time
+
+    print('The requests_get takes %f' % request_time)
+    print('The pycurl_get takes %f' % pycurl_time)
+
+
+if __name__ == '__main__':
+    main()    

get_headers.py

@@ -0,0 +1,60 @@
+from io import BytesIO
+import requests
+import pycurl
+
+headers = {}
+def header_function(header_line):
+    # HTTP standard specifies that headers are encoded in iso-8859-1.
+    # On Python 2, decoding step can be skipped.
+    # On Python 3, decoding step is required.
+    header_line = header_line.decode('iso-8859-1')
+
+    # Header lines include the first status line (HTTP/1.x ...).
+    # We are going to ignore all lines that don't have a colon in them.
+    # This will botch headers that are split on multiple lines...
+    if ':' not in header_line:
+        return
+
+    # Break the header line into header name and value.
+    name, value = header_line.split(':', 1)
+
+    # Remove whitespace that may be present.
+    # Header lines include the trailing newline, and there may be whitespace
+    # around the colon.
+    name = name.strip()
+    value = value.strip()
+
+    # Header names are case insensitive.
+    # Lowercase name here.
+    name = name.lower()
+
+    # Now we can actually record the header name and value.
+    headers[name] = value
+
+def main():
+    # Try Requests
+    print('Use requests to get Google')
+    res = requests.get('https://www.google.com')
+    print('check headers')
+    print(res.headers)
+    print('check content:')
+    print(res.text)
+    print('-' * 20)
+    # Try pycurl
+    print('Use pycurl to get Google')
+    b = BytesIO()
+    c = pycurl.Curl()
+    c.setopt(c.URL, 'https://www.google.com')
+    c.setopt(c.HEADERFUNCTION, header_function)
+    c.setopt(c.WRITEDATA, b)
+    c.perform()
+    print('check headers:')
+    print(headers)
+    print('check content:')
+    print(b.getvalue())
+    print('-' * 20)
+
+if __name__ == '__main__':
+    main()
+
+

get_with_cookies.py

@@ -0,0 +1,34 @@
+import pycurl
+import requests
+from io import BytesIO
+from http.cookies import BaseCookie
+
+def decode_cookie(raw_cookie):
+    cookie = BaseCookie()
+    cookie.load(raw_cookie)
+    decoded_cookie = {}
+    for c, v in cookie.items():
+        decoded_cookie[c] = v.value
+    return decoded_cookie
+
+def requests_cookie_get():
+    s = requests.session()
+    decoded_cookie = decode_cookie('PUT ur raw cookie here.')
+    res = s.get('https://www.google.com.tw/', cookies=decoded_cookie)
+    res = s.get('https://www.google.com.tw/')
+    print(res.text)
+
+def requests_pycurl_get():
+    b = BytesIO()
+    c = pycurl.Curl()
+    c.setopt(pycurl.URL, 'https://www.google.com.tw/')
+    c.setopt(pycurl.COOKIE, 'Put Ur RAW Cookie here')
+    c.setopt(pycurl.WRITEDATA, b)
+    c.perform()
+
+def main():
+    requests_cookie_get()
+    requests_pycurl_get()
+
+if __name__ == '__main__':
+    main()