ink_Ocelot 发表于 2020-5-3 21:13:57

一个语法问题

本帖最后由 ink_Ocelot 于 2020-5-3 21:13 编辑

import urllib.request
import re
import time

def open_url(url):
    req = urllib.request.Request(url)
    req.add_header('User-Agent','Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:75.0) Gecko/20100101 Firefox/75.0')
    page = urllib.request.urlopen(req)
    html = page.read().decode('utf-8')

    return html

def get_ip(html):

    #r'((?\d?\d│2\d│25)\.{3})((?\d?\d│2\d│25)'
    #r'(?:(?:?\d?\d|2\d|25)\.){3}(?:?\d?\d|2\d|25)'

    p = r'(?:(?:?\d?\d|2\d|25)\.){3}(?:?\d?\d|2\d|25)'
    iplist = re.findall(p,html)

#    for each in iplist:
#      print(each)

#    for each in iplist:
#      print (each)

    for each in iplist:
      exec('ipwrite.write(\'' + each + '\n\')'

if __name__ == '__main__':
    page_num = int(input('输入获取IP数量(以页面计)：')) + 1
    exec('ipwrite = open(\'IP:page1-page' + str(page_num - 1) + '.txt\',\'w\')')
    for i in range(1,page_num):
      exec('url = \'https://www.xicidaili.com/nt/' + str(i) + '\'')
      get_ip(open_url(url))
    ipwrite.close()
    print ('IP爬取完成！')
    time.sleep (5)



这个代码一直提示SyntaxError: invalid syntax
标红if __name__ == '__main__':中的':'
各位大佬知道这个问题怎么解决吗？

zltzlt 发表于 2020-5-3 21:19:01

这样试试：

import urllib.request
import re
import time

def open_url(url):
    req = urllib.request.Request(url)
    req.add_header('User-Agent','Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:75.0) Gecko/20100101 Firefox/75.0')
    page = urllib.request.urlopen(req)
    html = page.read().decode('utf-8')

    return html

def get_ip(html):

    #r'((?\d?\d│2\d│25)\.{3})((?\d?\d│2\d│25)'
    #r'(?:(?:?\d?\d|2\d|25)\.){3}(?:?\d?\d|2\d|25)'

    p = r'(?:(?:?\d?\d|2\d|25)\.){3}(?:?\d?\d|2\d|25)'
    iplist = re.findall(p,html)

#    for each in iplist:
#      print(each)

#    for each in iplist:
#      print (each)

    for each in iplist:
      exec('ipwrite.write(\' + each + \'\n\')')

if __name__ == '__main__':
    page_num = int(input('输入获取IP数量(以页面计)：')) + 1
    exec('ipwrite = open(\'IP:page1-page' + str(page_num - 1) + '.txt\',\'w\')')
    for i in range(1,page_num):
      exec('url = \'https://www.xicidaili.com/nt/' + str(i) + '\'')
      get_ip(open_url(url))
    ipwrite.close()
    print ('IP爬取完成！')
    time.sleep (5)

qiuyouzhi 发表于 2020-5-3 21:20:02

应该好好锻炼DEBUG技巧了...
import urllib.request
import re
import time

def open_url(url):
    req = urllib.request.Request(url)
    req.add_header('User-Agent','Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:75.0) Gecko/20100101 Firefox/75.0')
    page = urllib.request.urlopen(req)
    html = page.read().decode('utf-8')

    return html

def get_ip(html):

    #r'((?\d?\d│2\d│25)\.{3})((?\d?\d│2\d│25)'
    #r'(?:(?:?\d?\d|2\d|25)\.){3}(?:?\d?\d|2\d|25)'

    p = r'(?:(?:?\d?\d|2\d|25)\.){3}(?:?\d?\d|2\d|25)'
    iplist = re.findall(p,html)

#    for each in iplist:
#      print(each)

#    for each in iplist:
#      print (each)

    for each in iplist:
      ipwrite.write('' + each + '\n')
      
if __name__ == '__main__':
    page_num = int(input('输入获取IP数量(以页面计)：')) + 1
    exec('ipwrite = open(\'IP:page1-page' + str(page_num - 1) + '.txt\',\'w\')')
    for i in range(1,page_num):
      exec('url = \'https://www.xicidaili.com/nt/' + str(i) + '\'')
      get_ip(open_url(url))
    ipwrite.close()
    print ('IP爬取完成！')
    time.sleep (5)

在28行那个ipwrite里面，我有个疑问，为啥非要用exec？

ink_Ocelot 发表于 2020-5-3 21:34:19

还是返回 SyntaxError: invalid syntax 啊

hrp 发表于 2020-5-3 22:55:16

本帖最后由 hrp 于 2020-5-3 22:56 编辑

ink_Ocelot 发表于 2020-5-3 21:34
还是返回 SyntaxError: invalid syntax 啊

import re
import time
import urllib.request


def open_url(url):
    req = urllib.request.Request(url)
    req.add_header(
      'User-Agent',
      'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:75.0) Gecko/20100101 Firefox/75.0'
    )
    page = urllib.request.urlopen(req)
    html = page.read().decode('utf-8')
    print(html)

    return html


def get_ip(html):

    #r'((?\d?\d│2\d│25)\.{3})((?\d?\d│2\d│25)'
    #r'(?:(?:?\d?\d|2\d|25)\.){3}(?:?\d?\d|2\d|25)'

    p = r'(?:(?:?\d?\d|2\d|25)\.){3}(?:?\d?\d|2\d|25)'
    iplist = re.findall(p, html)

    #    for each in iplist:
    #      print(each)

    #    for each in iplist:
    #      print (each)

    for each in iplist:
      # exec('ipwrite.write(\'' + each + '\n\')')   # 最初报错的原因是这里少个回头的小括号，但还有其他问题。
      ipwrite.write(each + '\n')# 是不是想这么写？


if __name__ == '__main__':
    page_num = int(input('输入获取IP数量(以页面计)：'))
    ipwrite = open('IP-page1-page' + str(page_num) + '.txt', 'w') # 在win中冒号不能用作文件名！
    for i in range(1, page_num + 1):
      url = 'https://www.xicidaili.com/nt/' + str(i)# 你是不是想这么写？
      get_ip(open_url(url))
    ipwrite.close()
    print('IP爬取完成！')
    time.sleep(5)
页: [1]
查看完整版本: 一个语法问题