def test_importcheck_thread_safety(self, datapath):
# see gh-16928
class ErrorThread(threading.Thread):
def run(self):
try:
super(ErrorThread, self).run()
except Exception as e:
self.err = e
else:
self.err = None
# force import check by reinitalising global vars in html.py
reload(pandas.io.html)
filename = datapath('io', 'data', 'valid_markup.html')
helper_thread1 = ErrorThread(target=self.read_html, args=(filename,))
helper_thread2 = ErrorThread(target=self.read_html, args=(filename,))
helper_thread1.start()
helper_thread2.start()
while helper_thread1.is_alive() or helper_thread2.is_alive():
pass
assert None is helper_thread1.err is helper_thread2.err
import sys
import time
import urllib
import numpy as np
from bs4 import BeautifulSoup
from openpyxl import Workbook
from pandas.compat import reload
reload(sys)
# Some User Agents
hds = [{'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.1.6) Gecko/20091201 Firefox/3.5.6'}, \
{
'User-Agent': 'Mozilla/5.0 (Windows NT 6.2) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.12 Safari/535.11'}, \
{'User-Agent': 'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.2; Trident/6.0)'}]
def book_spider(book_tag):
page_num = 0
book_list = []
try_times = 0
while (1):
url = 'http://www.douban.com/tag/' + urllib.request.quote(
book_tag) + '/book?start=' + str(page_num * 15)
#time.sleep(np.random.rand() * 5)
# Last Version
try:
req = urllib.request.Request(url, headers=hds[page_num % len(hds)])
source_code = urllib.request.urlopen(req).read()
