def main():
import urlOpen
text = urlOpen.get_html("http://www.interfax.ru/world/502926")
text = tags_filter(text)
with open("parsed3.html", mode='w', encoding='utf-8') as file:
file.write(text)
max_char, min_char, line_list = get_list_of_lines(text)
for i, c in enumerate(line_list):
level = max_char * 0.4
if c[0] >= level and not c[2].startswith("Copyright"):
print(i, c[0], c[1], c[2])
print("Max chars in line: {}\n"
"Min chars in line {}\n"
"Num of lines {}".format(max_char, min_char, len(line_list)))
text = urlOpen.get_html("http://www.interfax.ru/world/502926")
text = tags_filter(text)
with open("parsed3.html", mode='w', encoding='utf-8') as file:
file.write(text)
max_char, min_char, line_list = get_list_of_lines(text)
for i, c in enumerate(line_list):
level = max_char * 0.4
if c[0] >= level and not c[2].startswith("Copyright"):
print(i, c[0], c[1], c[2])
print("Max chars in line: {}\n"
"Min chars in line {}\n"
"Num of lines {}".format(max_char, min_char, len(line_list)))
if __name__ == "__main__":
# main()
import urlOpen
html_code = urlOpen.get_html("http://ria.ru/world/20160406/1403678547.html")
if html_code:
with open("parsed2.html", mode='w', encoding='utf-8') as file:
file.write(tags_filter_head_and_script(html_code))
text = get_text_from_html(html_code)
with open("parsed3.html", mode='w', encoding='utf-8') as file:
file.write(text)
