春运又到了，献上更新版抓黄牛脚本。

好不容易搞定了火车票（当然不是通过酷讯或者黄牛），把去年写过的抓黄牛脚本重写了一下，提供给各位还在等待购买火车票的 Programmer 使用。说是抓黄牛，自然还包括普通转票者。原理还是通过轮询酷讯网站上的内容，但是增加了几个新特性：

• 用 re 提供的正则表达式替换掉了 SGMLParser 提高效率
• 可以轮询多个地址了，比如我到吉安和井冈山都可以，所以我要遍历两个地址
• 可以将转向链接直接打印在屏幕上了
• 提供了 Python 3 的 Package 级支持，但是因为 re 模块变更，正则表达式在 Python 3 里无法运行，暂时没心思更新了。

尽管酷讯推出了秒杀器，不过还是觉得不妥，一是没任何输出，谁知道它是否真的能秒到，二是不跨平台，在 Mac 和 Linux 上暂时无法使用。

Patches are welcome. :-)

#!/usr/bin/python
# encoding: utf-8
#
# Catch the yellow cattles script
#
# Author: Xuqing Kuang [email protected]>
# New features:
# * Use regexp to instead of SGMLParser for performance
# * Polling multiple URL at one time.
# * Print out the redirect URL.
# * Basic packages compatible with Python 3
# TODO:
# * Use one regexp to split the href and text of link
# * Update re package usage to compatible with Python 3
import time

import os

import re
try:

import urllib2 as urllib

except ImportError: # Python 3 compatible

import urllib.request, urllib.error
urls = (

&quothttp://piao.kuxun.cn/beijing-jinggangshan/&quot,

&quothttp://piao.kuxun.cn/beijing-jian/&quot,
)
keyword = &apos3张&apos

sequence = 60
class TrainTicket(object):

&quot&quot&quot

Catch the yellow cattle

&quot&quot&quot

def init(self, urls, keyword, sequence = 60):

self.urls = urls

self.keyword = keyword

self.sequence = sequence

self.cache=[]

self.html = &apos&apos

self.links = []

if hasattr(urllib, &aposbuild_opener&apos):

self.opener = urllib.build_opener()

else: # Python 3 compatible

self.opener = urllib.request.build_opener()

self.result = []

self.re_links = re.compile(&apos&lta.?href=.?&lt/a&gt&apos, re.I)

# self.re_element = re.compile(&apos&apos, re.I) # Hardcode at following

self.requests = []

for url in urls:

if hasattr(urllib, &aposRequest&apos):

request = urllib.Request(url)

else: # Python 3 compatible

request = urllib.request.Request(url)
        request.add_header(&aposUser-Agent&apos, &aposMozilla/5.0&apos)
        self.requests.append(request)

def get_page(self, request):
    &quot&quot&quot
    Open the page.
    &quot&quot&quot
    try:
        self.html = self.opener.open(request).read()
    except urllib.HTTPError:
        return False
    return self.html

def get_links(self, html = &apos&apos):
    &quot&quot&quot
    Process the page, get all of links
    &quot&quot&quot
    if not html:
        html = self.html
    self.links = self.re_links.findall(html)
    return self.links

def get_element(self, link = &apos&apos):
    &quot&quot&quot
    Process the link generated by self.get_links().
    Return list of the href and text
    &quot&quot&quot
    # FIXME: have no idea how to split the href and text with one regex
    # So use two regex for temporary solution
    href = re.findall(&apos(?&lt=href=&quot).*?(?=&quot)&apos, link) # Get the href attribute
    if not href:                                   # Process the no href attr
        href = [&apos&apos]
    text = re.split(&apos(&lt.*?&gt)&apos, link)[2]            # Get the text of link a.
    href.append(text)                              # Append to the list.
    return href

def get_ticket(self, request = None):
    &quot&quot&quot
    Generate the data structure of tickets for each URL.
    &quot&quot&quot
    if not request:
        request = self.requests[0]

    self.get_page(request)
    self.get_links()

    i = 0
    while i &lt len(self.links):
        link = self.get_element(self.links[i])
        if not link:
            continue
        url = link[0]
        name = link[1]
        if name and name.find(keyword) &gt= 0 and url not in self.cache:
            self.result.append((
                i, name, url,
            ))
            self.cache.append(url)
        i += 1
    return self.result

def print_tickets(self):
    &quot&quot&quot
    Process all of URLS and print out the tickets information.
    &quot&quot&quot
    while 1:
        self.result = []
        try:
            print(&aposBegin retrive&apos)
            for request in self.requests:
                print(&aposBegin scan %s&apos % request.get_full_url())
                self.get_ticket(request)
                print(&aposFound %s urls.&apos % len(self.links))
                for r in self.result:
                    print(&aposIndex: %s\nName: %s\nURL: %s\n&apos % (
                        r[0], r[1], r[2]
                    ))
            print(&aposScan finished, begin sleep %s seconds&apos % self.sequence)
            time.sleep(self.sequence)
        except KeyboardInterrupt:
            exit()
        except:
            raise

if name == &apos__main__&apos:

tt = TrainTicket(urls, keyword, sequence)

tt.print_tickets()

版权所有丨转载请注明出处：https://kxq.io/archives/春运又到了献上更新版抓黄牛脚本