#腾讯视频爬取评论 import urllib.request import re import urllib.error import ssl #当使用urllib.urlopen打开一个 https 链接时,会验证一次 SSL 证书.全局取消证书验证 ssl._create_default_https_context = ssl._create_unverified_context headers=('User-Agent','Mozilla/5.0 (Windows NT 6.1; WOW64; rv:59.0) Gecko/20100101 Firefox/59.0') #User agent opener=urllib.request.build_opener()#添加对应的报头信息 opener.addheaders=[headers] urllib.request.install_opener(opener)#设opener为全局 comid='6365504907156083559' url='https://video.coral.qq.com/varticle/1909645650/comment/v2?callback=_varticle1909645650commentv2&orinum=10&oriorder=o&pageflag=1&cursor='+comid+'&scorecursor=0&orirepnum=2&reporder=o&reppageflag=1&source=9&_=1523451466201' for i in range(0,2): try: data=urllib.request.urlopen(url).read().decode() patnext='"last":"(.*?)"' nextid=re.compile(patnext).findall(data)[0] patcom='"content":"(.*?)",' comdata=re.compile(patcom).findall(data) for j in range(0,len(comdata)): print('.....第'+str(i)+str(j)+'条评论内容是:') print (eval("u'"+comdata[j]+"'")) #运行U后面的内容,u是将unicode转为文字.eval("u('("+comdata[j]+")')")#最外层引号是函数本身“ ”,内层引号u‘ ’用于将unicode翻译为中文,最内层是将文字显示出来 url='https://video.coral.qq.com/varticle/1909645650/comment/v2?callback=_varticle1909645650commentv2&orinum=10&oriorder=o&pageflag=1&cursor='+nextid+'&scorecursor=0&orirepnum=2&reporder=o&reppageflag=1&source=9&_=1523451466201' except urllib.error.URLError as e: if hasattr(e,'code'): #判断对象是否包含对应属性 print(e.code) if hasattr(e,'reason'): print(e.reason)
腾讯视频爬取评论
猜你喜欢
转载自blog.csdn.net/weixin_41988628/article/details/79919556
今日推荐
周排行