-
-
Save magnunleno/68346ed0013a9012cda7b1e407da62cd to your computer and use it in GitHub Desktop.
Scrapping das propostas no site da pybr 12
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
import re | |
from bs4 import BeautifulSoup | |
from requests import get | |
from collections import defaultdict | |
assuntos_re = re.compile(r"\[(.*)\]") | |
res = get('http://speakerfight.com/events/python-brasil12-apresentacoes/') | |
soup = BeautifulSoup(res.content, 'html.parser') | |
div_event_proposals = soup.find('div', id='event-proposals') | |
propostas = div_event_proposals.find_all(attrs={'class': 'panel-body'}) | |
data = defaultdict(list) | |
topicos = defaultdict(list) | |
for p in propostas: | |
titulo = p.h3.a.text.strip() | |
autor = p.find('p', attrs={'class': 'proposal-metadata'}).a.text | |
print(autor) | |
print(' ', titulo) | |
data[autor].append(titulo) | |
assuntos = assuntos_re.findall(titulo) | |
if assuntos: | |
assuntos = map(str.strip, assuntos[0].split(',')) | |
for assunto in assuntos: | |
topicos[assunto].append(assuntos_re.sub("", titulo).strip()) | |
else: | |
topicos['Sem assunto'].append(titulo) | |
data = sorted(data.items(), key=lambda x:len(x[1]), reverse=True) | |
print("\nPalestrantes com mais palestras...") | |
for k,v in data: | |
print("{}: {} palestras".format(k, len(v))) | |
for i in v: | |
print(" {}".format(i)) | |
print("") | |
print(topicos) | |
print("\nResumo de topicos...") | |
for k, v in topicos.items(): | |
print("[{}]".format(k)) | |
for i in v: | |
print(" ", i) | |
print("") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment