"class": "main the-content"
}
},
]
for article in articles[0:1]:
###
# Text processing
###
# Create instance of TextProcess class that fetches text from url and filters it
tp = TextProcess(url=article["url"],
filename=article["name"],
content_selector_dict=article["content-selector"])
# Get filtered senteces in list
filtered_sentences = tp.get_filtered_sentences()
###
# Dictionary extraction
###
# Create instance of Dictionary class comparses filtered sentences with those in
# dictionary and creates node and edge list
wt = Dictionary(dictionary_path=article["dictionary_path"])
# Sets node nad edge list. First parameter is fitlered sentences, second is array
# of wanted word types. Words that are not connected to other are set as node list
# those that are connected are stored as edge list
wt.set_words_as_node_and_egde_list(filtered_sentences, [Dictionary.NOUN])
# Creates dictionary array that sets weight to amount of occurences of each pair
wt.set_edge_list_as_weighted_edges()
