爱奇艺、腾讯电视剧解析采集

import re
import urllib
import urllib.request
import  pymysql

def getHtml(url):
    page = urllib.request.urlopen(url)
    html = page.read()
    return html

# iqiyi:<a data-pb=""  href="(http://www.iqiyi.com/v_[\s\S]*?html)"[\s\S]*?title="([\s\S]*?)"
# tencent：<a\s*href="(http://v\.qq\.com/x/cover.*?html)"\s*target="_blank[\s\S]*?<span[\s\S]*?episodeNumber">([\s\S]*?)</span>
def parse(url,regular):
    html = getHtml(url)
    html=html.decode(‘utf-8‘)
    urls = re.findall(regular, html, re.I)
    lst={}
    for  u in urls:
        key=u[1]
        value=u[0]
        lst[str(key)]=str(value)
    result=""

    for v,k in lst.items():
        result+="第{v}集${k}#".format(v=v,k=k)
    # print(result)
    result = result[:-1]
    return result,len(lst)

def exceDB(url,id,regular):
    result,len=parse(url,regular)
    len="同步更新至{len}集".format(len=len)
    conn = pymysql.connect("localhost","root","sa","m8",use_unicode=True,charset="utf8")
    cur = conn.cursor()
    sql = "update  mac_vod set d_remarks=%s,d_playurl=%s where d_id=%s"
    sta=cur.execute(sql,(len,result,id))
    print(sta)
    cur.close()
    conn.commit()
    conn.close()

# 鬼吹灯之牧野诡事  每周一、周二20:00各更新1集
url = "http://www.iqiyi.com/lib/m_211070614.html"
id = 39097
regular = ‘<a data-pb=""  href="(http://www.iqiyi.com/v_[\s\S]*?html)"[\s\S]*?title="([\s\S]*?)"‘
exceDB(url,id,regular)

# 双世宠妃 每周一二20点每天更新2集
url = "http://v.qq.com/detail/4/47xswolfi4iamlx.html"
id = 21271
regular = ‘<a\s*href="(http://v\.qq\.com/x/cover.*?html)"\s*target="_blank[\s\S]*?<span[\s\S]*?episodeNumber">([\s\S]*?)</span>‘
exceDB(url,id,regular)

使用python3.6.1+pymysql

pymysql 使用pip pymysql install命令安装即可

采集后展示效果见：www.shurua.com

优酷的采集为了省事直接用了火车头，此处暂不介绍了