getBirthday.py 文件源码

def getFriendsBirthdays(birthdays,friendsDict,s): 

# --------- Getting Birthday Info -----------
    relatStrainer = SoupStrainer(text=re.compile("Birthday"))
    relatExt = "/about"
    relatExtBeta = "&sk=about"
    fbook = "https://facebook.com"  

    #***** Note: will have to perform additional string methods because scraping from main page
    for friend in friendsDict: 
        if (friendsDict[friend].find("php") != -1):
            relatURL = fbook + friendsDict[friend] + relatExtBeta
        else:
            relatURL = fbook + friendsDict[friend] + relatExt

        relatInfo = s.get(relatURL)
        soup = BeautifulSoup(relatInfo.text,"lxml",parse_only=relatStrainer)

        subString = soup.find(text=re.compile("Birthday"))

        if (subString != None):
            # Cut off everthing before Birthday
            stringIndex = subString.find('Birthday')
            subString = subString[stringIndex:]

            # Cut off the prefix to get the birthdate and everything after
            stringIndex = subString.find('<div>')
            subString = subString[(stringIndex+5):]

            # Get rid of everything after the birthday
            stringIndex = subString.find('</div>')
            subString = subString[:stringIndex]

            # Standardize the birthday date by cutting off the year if there is one
            commaIndex = subString.find(',')
            if (commaIndex != -1):
                subString = subString[:commaIndex]

            if (subString in birthdays):
                birthdays[subString].append(friend)
            else:
                birthdays[subString] = [friend]

            print friend + " has birthday " + subString
    return