接下来很容易就解析出电影的ftp下载链接和磁力链接：
image
理论部分讲解完成后，接下来的Python实现代码如下：
# -*- coding:utf-8 -*-import urllibimport urllib2import reimport requestsimport timeimport requestsimport requests_cache# User-Agent: Mozilla/5.0 (Windows NT 6.1; Win64; x64)# AppleWebKit/537.36 (KHTML, like Gecko)# Chrome/65.0.3325.181 Safari/537.36 OPR/52.0.2871.64requests_cache.install_cache('demo_cache')global fp
url = 'https://www.dy2018.com/html/gndy/dyzz/index.html'# url = 'https://www.dy2018.com/i/99901.html'user_agent = 'Mozilla/5.0 (Windows NT 6.1; Win64; x64)'headers = {'User-Agent': user_agent}try:
r = requests.get(url) print type(r) print r.status_code print r.encoding
html = requests.get(url, headers=headers).text
html = html.encode(r.encoding)
html = html.decode("gbk")
content = html # print content
fp = open(unicode("temp_pachong.txt", 'utf-8'), 'w') # 文件名不乱码
fp.write(content.encode('utf-8'))
fp.close() # <a href="/i/99901.html" class="ulink" title="2018年美国7.6分恐怖片《遗传厄运》BD中英双字">2018年美国7.6分恐怖片《遗传厄运》BD中英双字</a>
pattern = re.compile('<b>.*?<a href="/i/(.*?).html" class="ulink" title="(.*?)">.*?</a>.*?</b>', re.S)
items = re.findall(pattern, content)
fp = open(unicode("电影天堂爬虫.txt",'utf-8'),'w') # 文件名不乱码
localtime=time.strftime('%Y-%m-%d-%H：%M：%S', time.localtime(time.time()))
count=0
fp.write("********************" + localtime +"********************".encode('utf-8') + '\n') print '本页总资源数为：' + str(len(items)) for item in items:
count=count+1
temp=str(count) + ": " + item[1] print temp
fp.write(temp.encode('utf-8')+ '\n')
temp='https://www.dy2018.com/i/' + item[0] + '.html'
print temp #获取下载链接
url = temp
r = requests.get(url)
user_agent = 'Mozilla/5.0 (Windows NT 6.1; Win64; x64)'
headers = {'User-Agent': user_agent}
html = requests.get(url, headers=headers).text
html = html.encode(r.encoding)
html = html.decode("gbk")
content = html # print content
link_temp = re.compile('<td style=".*?"><a href="(.*?)">.*?</a></td>', re.S)
link = re.findall(link_temp, content) print link[0]
fp.write(link[0].encode('utf-8') + '\n')
fp.write("********************" + localtime +"********************".encode('utf-8'))
fp.close()except urllib2.URLError, e: if hasattr(e, "code"): print e.code if hasattr(e, "reason"): print e.reason
fp.close()实际效果如下：
view-source_https____i_99901.html.png
作者：看星星的天空
链接：https://www.jianshu.com/p/e9b5518bcdae
随时随地看视频
