# coding:utf-8
import requests
from lxml import etree
from queue import Queue
from urllib import parse
import threading
import re
import sys
#reload(sys)
#sys.setdefaultencoding('utf-8')
class Producer(threading.Thread):
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36'
}
def __init__(self, page_queue, txt_queue, *args, **kwargs):
super(Producer, self).__init__(*args, **kwargs)
self.page_queue = page_queue
self.txt_queue = txt_queue
def run(self):
while True:
if self.page_queue.empty():
break
url = self.page_queue.get()
self.url_search(url)
def url_search(self, url):
resp = requests.get(url, headers=self.headers)
text = resp.content.decode('utf-8')
html = etree.HTML(text)
aElements = html.xpath("//div[@class='f13']/a[1]/text()")
# print(quto)
#aElements = list(set(quto))
for aElement in aElements:
self.txt_queue.put(aElement)
class Consumer(threading.Thread):
def __init__(self, page_queue, txt_queue, *args, **kwargs):
super(Consumer, self).__init__(*args, **kwargs)
self.page_queue = page_queue
self.txt_queue = txt_queue
def run(self):
with open('urls.txt', 'w') as f:
while True:
if self.txt_queue.empty() and self.page_queue.empty():
break
#i = re.search("(http|https)://.*?(cn|com|org|)/", self.txt_queue.get().group())
try:
i = re.search(".*?(cn|com|org)/", self.txt_queue.get()).group()
# 正则也可以这样.+?(/|)$
except:
pass
#print("error: "+self.txt_queue.get())
f.write(i + '\n')
self.qc()
def qc(self):
print("clear_ok")
f = open('urls.txt')
quto = list(set(f))
with open('urlsok.txt', 'w') as f:
for i in quto:
f.write(str(i))
#print(quto)
def main():
page_queue = Queue(1000)
txt_queue = Queue(10000)
keyword = input("keyword: ")
page = int(input("page: "))
for i in range(0, page*10, 10):
url = "https://www.baidu.com/s?wd=" + parse.quote(keyword) + "&pn=" + str(i)
page_queue.put(url)
for p in range(1):
t1 = Producer(page_queue, txt_queue)
t1.start()
for s in range(1):
t2 = Consumer(page_queue, txt_queue)
t2.start()
if __name__ == '__main__':
main()
python3的url采集的多线程
最新推荐文章于 2020-12-07 13:32:03 发布