Python Browser.form['q']方法代码示例

# 需要导入模块: from mechanize import Browser [as 别名]
# 或者: from mechanize.Browser import form['q'] [as 别名]
    def __init__(self):
        '''
        Setting start urls dynamically using mechanize
        '''

        product_list = ['micromax', 'apple']
        br = Browser()
        br.set_handle_robots( False )
        br.addheaders = [('User-agent', 'Firefox')]

        for pl in product_list:
            br.open("http://www.flipkart.com/")
            br.select_form(nr=1)
            br.form['q'] = pl
            self.resp = br.submit()
            self.start_urls.append(self.resp.geturl())

# 需要导入模块: from mechanize import Browser [as 别名]
# 或者: from mechanize.Browser import form['q'] [as 别名]
def get_product_url(item_list):
	"""
	Return the url for each item in item_list from flipkart.
	"""

	url_list = []
	br = Browser() #get the browser instance
	br.set_handle_robots(False) #ignore robot.txt
	br.addheaders = [('User-agent', 'Firefox')] # setting browser agent
	br.open("http://www.flipkart.com/") # open url

	for item in item_list:
		br.select_form(nr=1) #select form using postion, as form name is nor available
		br.form['q'] = item # set item to be searched
		br.submit()
		url_list.append(br.geturl())

	return url_list

# 需要导入模块: from mechanize import Browser [as 别名]
# 或者: from mechanize.Browser import form['q'] [as 别名]
def searchByGoogle(ean=None, short=False):
    br = Browser()
    br.set_handle_robots(False)
    br.addheaders = [('User-agent','Firefox'),]
    br.open('http://www.google.com')
    br.select_form('f')
    query = str(ean) #" ".join([ str(ii) for ii in (ean,title,interpret) if ii ])
    br.form['q'] = "%s site:.audio3.cz" % (query,)
    br.submit()
    results = []
    audio3LinkRe = re.compile("http://www.audio3.cz/goods.asp\?.*gid=(.*)")
    searchResults = []
    if short:
	data = br.response().read()
	soup = BeautifulSoup(unicode(data,'cp1250'))
	resultSection = soup.find('div',{'id':'res'})
	results = resultSection.findAll('li',{'class':'g'})
	for result in results:
	    links = result.findAll('a',{})
	    for ll in links:
		reresult = audio3LinkRe.search(ll.get('href'))
		if reresult:
		    gid = reresult.group(1)
		    desc = "".join(map(str,result.contents))
		    searchResults.append((gid,desc))
		pass
	    pass
	pass
    else:
	for link in br.links():
	    siteMatch = audio3LinkRe.search( link.url )
	    if siteMatch:
		audio3detail = br.follow_link(link).get_data()
		soup = BeautifulSoup(unicode(audio3detail, 'cp1250'))
		img = soup.find('div',{'id':'img'})
		desc = soup.find('ul',{'id':'desc'})
		res = (siteMatch.group(1),"<style type='text/css'>.saleprice{color:red;font-weight:bold}</style><div style='float:left;margin-right:3em;'>%s</div><div>%s</div><a href='%s'>original link</a><hr/>" % (str(img),str(desc),link.url))
		searchResults.append(res)
	    pass
	pass
    return (searchResults,None)

# 需要导入模块: from mechanize import Browser [as 别名]
# 或者: from mechanize.Browser import form['q'] [as 别名]
from mechanize import Browser

br = Browser() #get the browser instance
br.set_handle_robots(False) #ignore robot.txt
br.addheaders = [('User-agent', 'Firefox')] # setting browser agent
br.open("http://www.google.co.in/") # open url
br.select_form('f') #select form
br.form['q'] = 'python' #set input field data to be searched
br.submit()

for link in br.links():
	print link.text

# 需要导入模块: from mechanize import Browser [as 别名]
# 或者: from mechanize.Browser import form['q'] [as 别名]
def searchTitle(rawtitle):
	br = Browser()
	# Ignore robots.txt
	br.set_handle_robots( False )
	# Google demands a user-agent that isn't a robot
	br.addheaders = [('User-agent', 'Firefox')]
	
	br.open( "http://www.google.com " )
	br.select_form( 'f' )
	s='imdb'+' + '+' '.join(re.compile('[\.]').split(rawtitle))
	br.form[ 'q' ] = s
	br.submit()

	resp = None
	for link in br.links():
		siteMatch = re.compile( 'www.imdb.com/title/tt[0-9]*/$' ).search( link.url )
		if siteMatch:
		    resp = br.follow_link( link )
		    print link.url
		    break

	soup = BeautifulSoup(resp.get_data())
	
	title = re.sub(' - IMDb','',soup.find('title').string)
	title = re.sub('\([0-9]*\)','',title)
	
	return title

# 需要导入模块: from mechanize import Browser [as 别名]
# 或者: from mechanize.Browser import form['q'] [as 别名]
import re
from mechanize import Browser
br = Browser()
 
# Ignore robots.txt
br.set_handle_robots( False )
# Google demands a user-agent that isn't a robot
br.addheaders = [('User-agent', 'Firefox')]
 
# Retrieve the Google home page, saving the response
br.open( "http://google.co.in" )
 
# Select the search box and search for 'foo'
br.select_form( nr=0)
br.form[ 'q' ] = 'satvik gupta'
 
# Get the search results
br.submit()
 
# Find the link to foofighters.com; why did we run a search?
resp = None
for link in br.links():
	print link.text
	print "\n\n"
    # siteMatch = re.compile( 'www.foofighters.com' ).search( link.url )
    # if siteMatch:
    #     resp = br.follow_link( link )
    #     break
 
# Print the site
# content = resp.get_data()

# 需要导入模块: from mechanize import Browser [as 别名]
# 或者: from mechanize.Browser import form['q'] [as 别名]
#!/usr/bin/python
import re 
from mechanize import Browser
br = Browser()

# Ignore robots.txt
br.set_handle_robots( False )
# Google demands a user-agent that isn't a robot
br.addheaders = [('User-agent', 'Firefox')]

# Retrieve the Google home page, saving the response
br.open( "http://google.com" )

# Select the search box and search for 'foo'
br.select_form( 'f' )
br.form[ 'q' ] = 'foo'

# Get the search results
br.submit()

# Find the link to foofighters.com; why did we run a search?
resp = None
for link in br.links():
    siteMatch = re.compile( 'www.foofighters.com' ).search( link.url )
    if siteMatch:
        resp = br.follow_link( link )
        break

# Print the site
content = resp.get_data()
print(content)