思路是 先构造url列表 all_url
然后
for i in range(0, len(all_url)):
urlqueue.put(all_url[i])
然后get 做到每次从列表中取出url
现在问题是,range后面 无法写成 0到列表长度
会显示IndexError: list index out of range
意思是 索引错误:列表索引超出范围
而且列表是没有任何问题的,没有空
而且如果列表长度是2000, 那么只能range(0, 1000),这样就无任何报错
这样就很麻烦
下面是代码
import requests
from lxml import html
import time
import threading
from queue import Queue
class Spider(threading.Thread):
def __init__(self, name, urlqueue):
super().__init__()
self.name = name
self.urlqueue = urlqueue
def run(self):
headers = {
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 UBrowser/6.2.4094.1 Safari/537.36'
}
print('线程 :' + self.name + '启动')
while not self.urlqueue.empty():
try:
url = self.urlqueue.get()
rep = requests.get(url, headers = headers, timeout = 5)
time.sleep(1)
if rep.status_code == 200:
print("链接成功")
self.parse(rep)
print(url + " 爬取完成")
except Exception as e:
print("主页::" +url + " 链接失败, 原因::", e)
pass
print('线程 :' + self.name + '结束')
def parse(self, rep):
con = rep.content
sel = html.fromstring(con)
title = sel.xpath('//div[@class="titmain"]/h1/text()')
title = str(title).replace(']', '').replace('[', '').replace("'", '').replace(",", '').replace(r"\r\n", "").replace('"', '').replace(' ', '').replace(r'\xa0', '').replace('?', '').replace('/', '').replace(r'\u3000', ' ')
date = sel.xpath('//div[@class="texttit_m1"]/p/text()')
date = str(date).replace(']', '').replace('[', '').replace("'", '').replace(r'\u3000', ' ')
if len(date) > 20:
file_name = title + ".txt"
a = open(file_name, "w+", encoding='utf-8')
a.write('\n' + str(title) + '\n' + '\n' + str(date))
print(file_name + '保存成功')
a.close
else:
pass
if name == '__main__':
with open('未爬取url.txt') as f:
data = f.readline()
#读取数据行
james = data.strip().split(',')
#将数据转换为列表
all_url = []
for jame in james:
a=eval(jame)
#去除ifu两端引号
all_url.append(a)
print(len(all_url))
start = time.time()
urlqueue = Queue()
threadNum = 3 #线程数量
for i in range(0, 1468):
urlqueue.put(all_url[i]) #问题在这里
del all_url[i]
threads = []
for i in range(1, threadNum+1):
thread = Spider("线程" + str(i), urlqueue)
thread.start()
threads.append(thread)
for thread in threads:
thread.join()
with open('未爬取url.txt', 'w+') as b:
b.write('\n'.join([str(all_url)]))
b.write('\n' + '=' *50 + '\n')
b.close
print(' 未爬取url 保存完成')
end = time.time()
print("-------------------------------")
print("下载完成. 用时{}秒".format(end-start))
另外 url是从txt读的 不知道怎么传上来, 最后构造的all_url列表是肯定没有问题的