使用python实现抓取腾讯视频所有电影的爬虫
作者:疯子程序员 时间:2022-05-09 12:19:03
用python实现的抓取腾讯视频所有电影的爬虫
# -*- coding: utf-8 -*-
import re
import urllib2
from bs4import BeautifulSoup
import string, time
import pymongo
NUM =0 #全局变量,电影数量
m_type = u'' #全局变量,电影类型
m_site = u'qq' #全局变量,电影网站
#根据指定的URL获取网页内容
def gethtml(url):
req = urllib2.Request(url)
response = urllib2.urlopen(req)
html = response.read()
return html
#从电影分类列表页面获取电影分类
def gettags(html):
global m_type
soup = BeautifulSoup(html) #过滤出分类内容
#print soup
#<ulclass="clearfix _group" gname="mi_type" gtype="1">
tags_all = soup.find_all('ul', {'class' :'clearfix _group' ,'gname' :'mi_type'})
#print len(tags_all), tags_all
#print str(tags_all[1]).replace('\n','')
#<a _hot="tag.sub" class="_gtag _hotkey" href="http://v.qq.com/list/1_0_-1_-1_1_0_0_20_0_-1_0.html" title="动作" tvalue="0">动作</a>
re_tags = r'<a _hot=\"tag\.sub\" class=\"_gtag _hotkey\" href=\"(.+?)\" title=\"(.+?)\" tvalue=\"(.+?)\">.+?</a>'
p = re.compile(re_tags, re.DOTALL)
tags = p.findall(str(tags_all[0]))
if tags:
tags_url = {}
#print tags
for tagin tags:
tag_url = tag[0].decode('utf-8')
#print tag_url
m_type = tag[1].decode('utf-8')
tags_url[m_type] = tag_url
else:
print"Not Find"
return tags_url
#获取每个分类的页数
def get_pages(tag_url):
tag_html = gethtml(tag_url)
#divclass="paginator
soup = BeautifulSoup(tag_html) #过滤出标记页面的html
#print soup
#<divclass="mod_pagenav" id="pager">
div_page = soup.find_all('div', {'class' :'mod_pagenav','id' :'pager'})
#print div_page #len(div_page), div_page[0]
#<aclass="c_txt6" href="http://v.qq.com/list/1_2_-1_-1_1_0_24_20_0_-1_0.html" title="25"><span>25</span></a>
re_pages = r'<a class=.+?><span>(.+?)</span></a>'
p = re.compile(re_pages, re.DOTALL)
pages = p.findall(str(div_page[0]))
#print pages
if len(pages) >1:
return pages[-2]
else:
return 1
def getmovielist(html):
soup = BeautifulSoup(html)
#<ulclass="mod_list_pic_130">
divs = soup.find_all('ul', {'class' :'mod_list_pic_130'})
#print divs
for div_htmlin divs:
div_html = str(div_html).replace('\n','')
#print div_html
getmovie(div_html)
def getmovie(html):
global NUM
global m_type
global m_site
re_movie = r'<li><a class=\"mod_poster_130\" href=\"(.+?)\" target=\"_blank\" title=\"(.+?)\"><img.+?</li>'
p = re.compile(re_movie, re.DOTALL)
movies = p.findall(html)
if movies:
conn = pymongo.Connection('localhost',27017)
movie_db = conn.dianying
playlinks = movie_db.playlinks
#print movies
for moviein movies:
#print movie
NUM +=1
print"%s : %d" % ("=" *70, NUM)
values = dict(
movie_title = movie[1],
movie_url = movie[0],
movie_site = m_site,
movie_type = m_type
)
print values
playlinks.insert(values)
print"_" *70
NUM +=1
print"%s : %d" % ("=" *70, NUM)
#else:
# print"Not Find"
def getmovieinfo(url):
html = gethtml(url)
soup = BeautifulSoup(html)
#pack pack_album album_cover
divs = soup.find_all('div', {'class' :'pack pack_album album_cover'})
#print divs[0]
#<a href="http://www.tudou.com/albumplay/9NyofXc_lHI/32JqhiKJykI.html" target="new" title="《血滴子》独家纪录片" wl="1"> </a>
re_info = r'<a href=\"(.+?)\" target=\"new\" title=\"(.+?)\" wl=\".+?\"> </a>'
p_info = re.compile(re_info, re.DOTALL)
m_info = p_info.findall(str(divs[0]))
if m_info:
return m_info
else:
print"Not find movie info"
return m_info
def insertdb(movieinfo):
global conn
movie_db = conn.dianying_at
movies = movie_db.movies
movies.insert(movieinfo)
if __name__ =="__main__":
global conn
tags_url ="http://v.qq.com/list/1_-1_-1_-1_1_0_0_20_0_-1_0.html"
#print tags_url
tags_html = gethtml(tags_url)
#print tags_html
tag_urls = gettags(tags_html)
#print tag_urls
for urlin tag_urls.items():
print str(url[1]).encode('utf-8') #,url[0]
maxpage =int(get_pages(str(url[1]).encode('utf-8')))
print maxpage
for xin range(0, maxpage):
#http://v.qq.com/list/1_0_-1_-1_1_0_0_20_0_-1_0.html
m_url = str(url[1]).replace('0_20_0_-1_0.html','')
movie_url ="%s%d_20_0_-1_0.html" % (m_url, x)
print movie_url
movie_html = gethtml(movie_url.encode('utf-8'))
#print movie_html
getmovielist(movie_html)
time.sleep(0.1)
总结
以上所述是小编给大家介绍的使用python实现抓取腾讯视频所有电影的爬虫,希望对大家有所帮助,如果大家有任何疑问欢迎给我留言,小编会及时回复大家的!
来源:https://blog.csdn.net/qq_40196321/article/details/89190327
标签:python,抓取,爬虫
0
投稿
猜你喜欢
HTML 标签是否匹配检测代码
2010-03-17 20:50:00
python中super()函数的理解与基本使用
2023-07-02 08:00:33
python跳过第一行快速读取文件内容的实例
2022-05-12 12:58:56
Python利用正则表达式从字符串提取数字
2021-03-22 22:52:39
[欣赏] 情景互动广告
2008-08-06 12:59:00
PHP设计模式之观察者模式浅析
2023-05-27 12:20:11
Python asyncio的一个坑
2022-04-06 20:58:28
带农历的JavaScript日期时间js代码
2010-08-01 10:29:00
基于python判断字符串括号是否闭合{}[]()
2022-03-25 15:58:45
如何捕获人家站点的页面?
2009-11-11 19:19:00
python 在mysql中插入null空值的操作
2022-09-24 09:48:40
PHP中使用addslashes函数转义的安全性原理分析
2023-08-16 10:31:22
Python使用xpath实现图片爬取
2023-07-10 16:45:42
python 读写、创建 文件的方法(必看)
2023-08-07 11:37:40
Python迭代和迭代器详解
2023-11-20 08:52:28
ASP看代码学习CASE的用法
2008-04-13 06:36:00
Pytorch搭建SRGAN平台提升图片超分辨率
2022-10-03 14:02:01
Access中实现case when功能
2009-04-28 13:02:00
教你轻松了解MySQL数据库中的结果字符串
2009-02-23 17:29:00
javascript对象概念大全
2009-05-22 18:24:00