Das deutsche Python-Forum

Code: Alles auswählen

import urllib2
from BeautifulSoup import BeautifulSoup

soup = BeautifulSoup(urllib2.urlopen(' URL ').read())
tables = soup.findAll("table", { TABEIG })
print tables

Code: Alles auswählen

import urllib2
from BeautifulSoup import BeautifulSoup

soup = BeautifulSoup(urllib2.urlopen(' URL ').read())
tables = soup.findAll("table", { TABEIG })
table = tables[1]
#f = open('/home/jochen/sistest', 'w')
#f.write(table.read())
#f.close()
for row in table.findAll('tr')[1:]:		
	col = row.findAll('td')    	
	Team = row.findAll('a')	
	try:
		col[1]
	except:
		continue
	Platz = col[1].string
	Mannschaft = Team[0].string
	Spiele = col[3].string
	Siege = col[4].string
	Unentschieden = col[5].string
	Niederlagen = col[6].string
	Tore = col[7].string
	Tordiff = col[8].string
	Punkte = col[9].string
	Zeile = (Platz, Mannschaft, Spiele, Siege, Unentschieden, Niederlagen, Tore, Tordiff, Punkte)
	print Zeile

Code: Alles auswählen

url = "http://sis-handball.de/foobar"

Code: Alles auswählen

import mechanize
from BeautifulSoup import BeautifulSoup

br = mechanize.Browser()
br.addheaders = [('User-agent', 'Mozilla/5.0 (X11; U; Linux i686; de; rv:1.9.1.2) Gecko/20090729 Firefox/3.5.2')]
url = 'http://www.sis-handball.de/web/Default.aspx?view=Tabelle&Liga=001510504503503000000000000000000003000'
soup = BeautifulSoup(br.open(url).read())
tabeig = {
	"cellpadding" : "0",
	"cellspacing" : "0",
	"style" : STYLE
	}
tables = soup.findAll("table", tabeig)
table = tables[1]
for row in table.findAll('tr')[1:]:		
	col = row.findAll('td')
	Team = row.findAll('a')	
	try:
		col[1]
	except IndexError:
		continue
	Zeile = {	
		'Platz' : col[1].string,
		'Mannschaft' : Team[0].string,
		'Spiele' : col[3].string,
		'Siege' : col[4].string,
		'Unentschieden' : col[5].string,
		'Niederlagen' : col[6].string,
		'Tore' : col[7].string,
		'Tordiff' : col[8].string,
		'Punkte' : col[9].string
		}	
	print Zeile

Code: Alles auswählen

"style" : "font-family:Lucida Sans, Verdana, Arial;color: #272829; "
                   "font-size: 14px; text-align:center; margin-left: auto; "
                   "margin-right: auto; width: 95%; margin-top: 5px; "
                   "margin-bottom: 5px;" }

Code: Alles auswählen

In [1]: keys = ("Platz", "Mannschaft", "Spiele")

In [3]: col = [1, "b", 42]

In [4]: zip(keys, col)
Out[4]: [('Platz', 1), ('Mannschaft', 'b'), ('Spiele', 42)]

In [5]: dict(zip(keys, col))
Out[5]: {'Mannschaft': 'b', 'Platz': 1, 'Spiele': 42}

Code: Alles auswählen

import mechanize
from BeautifulSoup import BeautifulSoup

br = mechanize.Browser()
br.addheaders = [('User-agent', 'Mozilla/5.0 '
    '(X11; U; Linux i686; de; rv:1.9.1.2) '
    'Gecko/20090729 Firefox/3.5.2')]
url = 'http://www.sis-handball.de/web/Default.aspx?view=Tabelle&Liga=001510504503503000000000000000000003000'
soup = BeautifulSoup(br.open(url).read())
tabeig = {
    "cellpadding" : "0",
    "cellspacing" : "0",
    "style" : "font-family:Lucida Sans, Verdana, Arial;color: #272829; "
        "font-size: 14px; text-align:center; margin-left: auto; "
        "margin-right: auto; width: 95%; margin-top: 5px; "
        "margin-bottom: 5px;"
    }
tables = soup.findAll("table", tabeig)
table = tables[1]
for row in table.findAll('tr')[1:]:		
    col = row.findAll('td')
    team = row.findAll('a')	
    try:
        col[1]
    except IndexError:
        continue
    zeile = {	
        'Platz' : int(col[1].string),
        'Mannschaft' : team[0].string,
        'Spiele' : col[3].string,
        'Siege' : int(col[4].string),
        'Unentschieden' : int(col[5].string),
        'Niederlagen' : int(col[6].string),
        'Tore' : col[7].string,
        'Tordiff' : int(col[8].string),
        'Punkte' : col[9].string
    }
    print zeile

Code: Alles auswählen

import re
import sys
import urllib2, urllib
import json
from plugin import *

try:
   from imdb import IMDb
   import imdb.helpers
except ImportError:
   raise NecessaryModuleNotFound("Oops! Unable to locate the IMDb library. Please install IMDbPy. e.g. (sudo easy_install IMDbPy) or (sudo apt-get install python-imdbpy)")

class nurf_imdb(Plugin):

    @register("de-DE", "(Film)* ([\w ]+)") 
    def get_director(self, speech, language,  regex):
        if language == "de-DE":
            MovieTitle = regex.group(regex.lastindex).strip()
            ia = IMDb()
            search_result = ia.search_movie(MovieTitle)
            if not search_result:
                self.say("Leider keinen Film gefunden mit: " + MovieTitle)
                self.complete_request()
                
            else:
                movie_info = search_result[0]
                ia.update(movie_info)    
                MovieRating = movie_info['rating']
		
		try:
		    mpaalala = movie_info['mpaa']
		    mpaalala = re.match("Rated ([\w ]+) for", mpaalala, re.IGNORECASE)
		    mpaalala = mpaalala.group(1).strip()
		    if mpaalala == 'R':
			mpaalala = 'ab 16, '
		    if mpaalala == 'PG':
			mpaalala = 'ab 6, '
		    if mpaalala == 'PG-13, ':
			mpaalala = 'ab 12'
		    if mpaalala == 'NC-17, ':
			mpaalala = 'ab 18, '
		    if mpaalala == 'G':
			mpaalala = 'ab 0, '
		except:
		    mpaalala = ''
		self.say(movie_info['title'] + " (" + str(movie_info['year']) + ", " + mpaalala + "Wertung: "+  str(MovieRating) +") ")
                self.complete_request()