def test_proxy_fetch():
p = common.proxy.Proxy('proxies.dat')
proxies_list = p.get_from_file()
page = common.page.Page('http://baike.baidu.com/subview/3077/11247674.htm')
html = page.proxy_fetch(proxies_list)
html = html.decode('utf-8', 'ignore')
html = html.encode('gbk', 'ignore')
html = html.decode('gbk', 'ignore')
print(html)
def test_proxy_fetch():
p = common.proxy.Proxy('proxies.dat')
proxies_list = p.get_from_file()
page = common.page.Page(
'http://baike.baidu.com/subview/3077/11247674.htm')
html = page.proxy_fetch(proxies_list)
html = html.decode('utf-8', 'ignore')
html = html.encode('gbk', 'ignore')
html = html.decode('gbk', 'ignore')
print(html)
def fetch(self, min_id, max_id):
for page_id in range(min_id, max_id):
# 获取
page_id = str(page_id)
url = 'http://baike.baidu.com/view/' + page_id + '.htm'
page = common.page.Page(url)
html = page.proxy_fetch(self.proxies_queue)
if html:
# 转码
html = html.decode('utf-8', 'ignore')
html = html.encode('gbk', 'ignore')
html = html.decode('gbk', 'ignore')
# 写出
outfile = 'd:/test/baikefile/' + page_id + '.html'
f = open(outfile, 'w')
f.write(html)
f.close()
logging.debug('写入完成 %s' % page_id)
logging.info('子任务完成 ' + str(min_id) + "~" + str(max_id))
def fetch(self, min_id, max_id):
for page_id in range(min_id, max_id):
# 获取
page_id = str(page_id)
url = 'http://baike.baidu.com/view/' + page_id + '.htm'
page = common.page.Page(url)
html = page.proxy_fetch(self.proxies_queue)
if html:
# 转码
html = html.decode('utf-8', 'ignore')
html = html.encode('gbk', 'ignore')
html = html.decode('gbk', 'ignore')
# 写出
outfile = 'd:/test/baikefile/' + page_id + '.html'
f = open(outfile, 'w')
f.write(html)
f.close()
logging.debug('写入完成 %s' % page_id)
logging.info('子任务完成 '+str(min_id)+"~"+str(max_id))
