腾讯爬虫python_python 腾讯视频评论爬虫

>>> import urllib.request

>>> import re

>>> import urllib.error

#防浏览器

>>> headers=(

"User-Agent","Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36")

>>> openner=urllib.request.build_opener()

>>> openner.addheaders=[headers]

#设置全局头部

>>> urllib.request.install_opener(openner)

#这个是一个标示，用于改变更多评论的标示

>>> comid="6513803733931374872"

>>> url="https://video.coral.qq.com/varticle/3794242979/comment/v2?callback=_varticle3794242979commentv2&orinum=10&oriorder=o&pageflag=1&cursor="+comid+"&scorecursor=0&orirepnum=2&reporder=o&reppageflag=1&source=132&_=1557526541245"

for i in range(1,10):

data=urllib.request.urlopen(url).read().decode("utf-8")

patnext='"last":"(.*?)"'

nextid=re.compile(patnext).findall(data)[0]

patcom='"content":"(.*?)"'

comdata=re.compile(patcom).findall(data)

for j in range(len(comdata)):

#这个是这里要注意的 是 单引号 u 双引号 单引号  +commdata[j]+单引号 双引号  单引号

print(eval('u"'+comdata[j]+'"'))

改变url进行下一次的爬虫

url="https://video.coral.qq.com/varticle/3794242979/comment/v2?callback=_varticle3794242979commentv2&orinum=10&oriorder=o&pageflag=1&cursor="+nextid+"&scorecursor=0&orirepnum=2&reporder=o&reppageflag=1&source=132&_=1557526541245"