利用urllib和xpath爬取电影播放地址 - 精易论坛

from urllib import request
from lxml import etree
from pprint import pprint
class GetMoviePlay:
"""
# 取电影标题 '//*[@id="data_list"]/tr/td[1]/a'
# 取电影页面链接 '//*[@id="data_list"]/tr/td[1]/a/@href'
# 取电影类型 '//*[@id="data_list"]/tr/td[2]/a'
# 取电影地区 '//*[@id="data_list"]/tr/td[3]/p/font'
# 取连载状态 '//*[@id="data_list"]/tr/td[4]/span/font'
# 取更新时间 '//*[@id="data_list"]/tr/td[5]/font'
# 取当前页码详情 '/html/body/div[4]/div[1]/div/text()[1]'
# 获取真实链接 /html/body/div[4]/div[2]/div/div/ul/li[2]/text()
"""
def __init__(self,page):
self.__url = 'http://yongjiuzy.cc/?m=vod-type-id-6-pg-%d.html' % page
self.__name = (
'//*[@id="data_list"]/tr/td[1]/a/text()',
'//*[@id="data_list"]/tr/td[1]/a/@href',
'//*[@id="data_list"]/tr/td[2]/a/text()',
'//*[@id="data_list"]/tr/td[3]/p/font/text()',
'//*[@id="data_list"]/tr/td[4]/span/font/text()',
'//*[@id="data_list"]/tr/td[5]/font/text()',
'/html/body/div[4]/div[1]/div/text()[1]',
'/html/body/div[4]/div[1]/div/div[2]/li[1]/text()[2]',
'/html/body/div[4]/div[2]/div/div/ul/li[2]/text()'
)
@property
def movie_info_dict(self):
res = request.Request(self.__url)
response = request.urlopen(res).read()
response = etree.HTML(response)
# 取电影标题
m_cont_list_tmp = response.xpath(self.__name[0])
m_cont_list = []
# 解析电影标题，只取奇数的主标题
for i in range(len(m_cont_list_tmp)):
if i % 2 == 0:
m_cont_list.append(m_cont_list_tmp[i])
# 取电影页面链接
m_url_list = response.xpath(self.__name[1])
# 拼接url
for i in range(len(m_url_list)):
m_url_list[i] = 'http://yongjiuzy.cc/' + m_url_list[i]
# 取电影类型
m_type_list = response.xpath(self.__name[2])
# 取电影地区 '//*[@id="data_list"]/tr/td[3]/p/font'
m_city_list = response.xpath(self.__name[3])
# 取连载状态 '//*[@id="data_list"]/tr/td[4]/span/font'
m_state_list = response.xpath(self.__name[4])
# 取更新时间 '//*[@id="data_list"]/tr/td[5]/font'
m_time_list = response.xpath(self.__name[5])
# 取当前页码详情 '/html/body/div[4]/div[1]/div/text()[1]'
m_this_page = response.xpath(self.__name[6])
return {'context':m_cont_list,
'url':m_url_list,
'type':m_type_list,
'city':m_city_list,
'state':m_state_list,
'time':m_time_list,
'thisPage':m_this_page
}
def getMovieTrue(self,url):
res = request.Request(url)
response = request.urlopen(res).read()
response = etree.HTML(response)
# 电影名称 /html/body/div[4]/div[1]/div/div[2]/li[1]/text()[2]
m_true_context = response.xpath(self.__name[7])
# 获取真实链接 /html/body/div[4]/div[2]/div/div/ul/li[2]/text()
m_true_url = response.xpath(self.__name[8])
# 返回列表数据
return [m_true_context[0],m_true_url[0]]
if __name__ == '__main__':
a = GetMoviePlay(1) # 初始化一个页码
# 返回了一堆数据，其实我就只要了url
url = a.movie_info_dict['url']
for i in range(len(url)):
info = a.getMovieTrue(url[i])
pprint(info)

复制代码