woxikon_de_lookup.py 文件源码

def obtainGroups(webcontent, groupNum):
    synonym_list = []
    for group in range(groupNum):
        while not re.search("synonyms-list-group", webcontent.readline(), re.UNICODE):
            continue
        meaning = re.search("Meaning: <b>([^<]+)</b>", webcontent.readline(), re.UNICODE).group(1)
        webcontent.readline() # </div> line
        webcontent.readline() # synonyms-list_content line
        sublist = webcontent.readline().split(',')
        subSynList = []
        for wordContainer in sublist:
            potential_synonym = re.search("<a href=[^>]+>([^<]+)</a>", wordContainer, re.UNICODE)
            if potential_synonym:
                subSynList.append(potential_synonym.group(1))
        synonym_list.append([meaning, subSynList])
    return synonym_list