def dealWithPage(page_num):
page = urlparse.urljoin(url_prefix, str(page_num))
question_index_filename = 'q_index'
try:
question = Question(page)
except:
print 'Question Get Error.'
return
f = codecs.open(question_index_filename + '.txt', 'a')
f.write(str(page_num) + '\r\n')
f.close()
question_folder = 'Zhihu/Question_' + str(page_num)
question_filename = 'q'
if (not os.path.exists(question_folder)):
os.makedirs(question_folder)
f = codecs.open(os.path.join(question_folder, question_filename + '.txt'),
'w')
f.write(question.get_title() + '\r\n|||\r\n')
f.write(question.get_detail() + '\r\n|||\r\n')
for topic in question.get_topics():
f.write(topic + '\t')
f.write('\r\n|||\r\n')
f.write(str(question.get_visit_times()) + '\r\n|||\r\n')
f.write(str(question.get_followers_num()) + '\r\n|||\r\n')
f.write(str(question.get_answers_num()) + '\r\n|||\r\n')
f.close()
answers = question.get_all_answers()
for answer in answers:
ansURL = answer.answer_url
ans = Answer(ansURL)
answer_folder = os.path.join(question_folder, 'Answer')
answer_filename = str(ansURL.split('/')[-1])
answer_index_filename = 'a_index'
f = codecs.open(answer_index_filename + '.txt', 'a')
f.write(str(page_num) + '|||' + str(answer_filename) + '\r\n')
f.close()
if (not os.path.exists(answer_folder)):
os.makedirs(answer_folder)
f = codecs.open(os.path.join(answer_folder, answer_filename + '.txt'),
'w')
try:
f.write(ans.get_content().find('body').get_text().strip().encode(
"gbk", 'ignore') + '\r\n|||\r\n')
f.write(ans.get_author().get_user_id() + '\r\n|||\r\n')
f.write(str(ans.get_upvote()) + '\r\n|||\r\n')
except:
print 'TimeOut Occurred.'
f.close()
f = codecs.open(
os.path.join(answer_folder, answer_filename + '.txt'), 'w')
f.write('None')
f.close()
continue
f.close()
# -*- coding: utf-8 -*-
from zhihu import Question
from zhihu import Answer
from zhihu import User
from zhihu import Collection
import requests
url = "https://www.zhihu.com/question/19550321/answer/14240492"
ans = Answer(url)
print ans.get_content().find('body').get_text()
input()
