mechanize (1)

import re
import mechanize

（1）实例化一个浏览器对象
br = mechanize.Browser()
（2）打开一个网址
br.open("http://www.example.com/")
（3）该网页下的满足text_regex的第2个链接
# follow second link with element text matching regular expression
response1 = br.follow_link(text_regex=r"cheese\s*shop", nr=1)
assert br.viewing_html()
（4）网页的名称
print br.title()
（5）将网页的网址打印出来
print response1.geturl()
（6）网页的头部
print response1.info()  # headers
（7）网页的body
print response1.read()  # body

(8)选择body中的name =" order"的FORM
br.select_form(name="order")
# Browser passes through unknown attributes (including methods)
# to the selected HTMLForm.
(9)为name = cheeses的form赋值
br["cheeses"] = ["mozzarella", "caerphilly"]  # (the method here is __setitem__)
# Submit current form.  Browser calls .close() on the current response on
# navigation, so this closes response1
（10）提交
response2 = br.submit()

# print currently selected form (don‘t call .submit() on this, use br.submit())
print br.form
（11）返回
response3 = br.back()  # back to cheese shop (same data as response1)
# the history mechanism returns cached response objects
# we can still use the response, even though it was .close()d
response3.get_data()  # like .seek(0) followed by .read()
（12）刷新网页
response4 = br.reload()  # fetches from server

（13）这可以列出该网页下所有的Form
for form in br.forms():
　　print form
# .links() optionally accepts the keyword args of .follow_/.find_link()
for link in br.links(url_regex="python.org"):
print link
    br.follow_link(link)  # takes EITHER Link instance OR keyword args
    br.back()

br = mechanize.Browser()
# Explicitly configure proxies (Browser will attempt to set good defaults).
# Note the userinfo ("joe:password@") and port number (":3128") are optional.
br.set_proxies({"http": "joe:password@myproxy.example.com:3128",
"ftp": "proxy.example.com",
 })
# Add HTTP Basic/Digest auth username and password for HTTP proxy access.
# (equivalent to using "joe:password@..." form above)
br.add_proxy_password("joe", "password")

# Add HTTP Basic/Digest auth username and password for website access.
br.add_password("http://example.com/protected/", "joe", "password")

# Don‘t handle HTTP-EQUIV headers (HTTP headers embedded in HTML).
br.set_handle_equiv(False)

# Ignore robots.txt.  Do not do this without thought and consideration.
br.set_handle_robots(False)

# Don‘t add Referer (sic) header
br.set_handle_referer(False)

# Don‘t handle Refresh redirections
br.set_handle_refresh(False)

# Don‘t handle cookies
br.set_cookiejar()

# Supply your own mechanize.CookieJar (NOTE: cookie handling is ON by
# default: no need to do this unless you have some reason to use a
# particular cookiejar)
br.set_cookiejar(cj)

# Log information about HTTP redirects and Refreshes.
br.set_debug_redirects(True)

# Log HTTP response bodies (ie. the HTML, most of the time).
br.set_debug_responses(True)

# Print HTTP headers.
br.set_debug_http(True)

# To make sure you‘re seeing all debug output:
logger = logging.getLogger("mechanize")
logger.addHandler(logging.StreamHandler(sys.stdout))
logger.setLevel(logging.INFO)

# Sometimes it‘s useful to process bad headers or bad HTML:
response = br.response()  # this is a copy of response
headers = response.info()  # currently, this is a mimetools.Message
headers["Content-type"] = "text/html; charset=utf-8"
response.set_data(response.get_data().replace("<!---", "<!--"))
br.set_response(response)