def spider(url_list):
# fetcher = MultiHeadersFetch( headers=tuple( { 'Cookie': i } for i in COOKIE))
fetcher = Fetch('/tmp', tuple({'Cookie': i} for i in COOKIE), 2.6,
zhihu_topic_title)
spider = Rolling(fetcher, url_list)
debug = False
debug = True
spider_runner = GSpider(spider, workers_count=1, debug=debug)
spider_runner.start()
global QUESTION_ID_SET
QUESTION_ID_SET = tuple(QUESTION_ID_SET)
with open("question_id.py", "w") as question:
question.write("QUESTION_ID_SET = ")
question.write(pformat(QUESTION_ID_SET))
def spider(url_list):
# fetcher = MultiHeadersFetch( headers=tuple( { 'Cookie': i } for i in COOKIE))
fetcher = Fetch(
'/tmp',
tuple( { 'Cookie': i } for i in COOKIE),
2.6,
zhihu_topic_title
)
spider = Rolling( fetcher, url_list )
debug = False
debug = True
spider_runner = GSpider(spider, workers_count=1, debug=debug)
spider_runner.start()
global QUESTION_ID_SET
QUESTION_ID_SET = tuple(QUESTION_ID_SET)
with open("question_id.py","w") as question:
question.write("QUESTION_ID_SET = ")
question.write(pformat(QUESTION_ID_SET))
debug = False
debug = True
spider_runner = GSpider(spider, workers_count=1, debug=debug)
spider_runner.start()
from operator import itemgetter
if __name__ == '__main__':
# print u'["topic", "\u767e\u5ea6", "\u767e\u5ea6", "http://p1.zhimg.com//e7/5e/e75e39ed2_s.jpg", 413, "5854", "baidu"]'
url_list = []
for t in ZHIHU_TOPIC:
i = t[0]
url_list.append((parse_topic, URL_TEMPLATE%i, i))
spider(url_list)
with open('zhihu_topic_related_data.py', 'w') as topic:
topic.write('#coding:utf-8\n')
topic.write('TOPIC_RELATED = ')
topic.write(pformat(RESULT))
topic.write('TOPIC = ')
topic.write(pformat(TOPIC))
from operator import itemgetter
if __name__ == '__main__':
# print u'["topic", "\u767e\u5ea6", "\u767e\u5ea6", "http://p1.zhimg.com//e7/5e/e75e39ed2_s.jpg", 413, "5854", "baidu"]'
for i in chariter():
print i
raw_input()
raise
url_list = []
for i in set(chariter()):
url_list.append((parse_topic, URL_TEMPLATE%quote(i)))
spider(url_list)
RESULT = RESULT.items()
RESULT.sort(key=itemgetter(0))
result = []
for i in RESULT:
result.append([i[0]])
result[-1].extend(i[1])
result[-1][-1] = list(result[-1][-1])
with open('zhihu_topic_data.py', 'w') as topic:
topic.write('#coding:utf-8\n')
topic.write('ZHIHU_TOPIC = ')
topic.write(pformat(result))
spider_runner = GSpider(spider, debug=debug)
spider_runner.start()
from operator import itemgetter
if __name__ == '__main__':
# print u'["topic", "\u767e\u5ea6", "\u767e\u5ea6", "http://p1.zhimg.com//e7/5e/e75e39ed2_s.jpg", 413, "5854", "baidu"]'
for i in chariter():
print i
raw_input()
raise
url_list = []
for i in set(chariter()):
url_list.append((parse_topic, URL_TEMPLATE % quote(i)))
spider(url_list)
RESULT = RESULT.items()
RESULT.sort(key=itemgetter(0))
result = []
for i in RESULT:
result.append([i[0]])
result[-1].extend(i[1])
result[-1][-1] = list(result[-1][-1])
with open('zhihu_topic_data.py', 'w') as topic:
topic.write('#coding:utf-8\n')
topic.write('ZHIHU_TOPIC = ')
topic.write(pformat(result))
