[python](爬虫)如何使用正确的姿势欣赏知乎的“长的XXX是怎样体验”这一类中的图片

#coding=utf-8
import urllib
import re

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

def getImg(html):
    reg = r‘original="([0-9a-zA-Z:/._]+?)" data-actualsrc‘
    imgre = re.compile(reg)
    imglist = re.findall(imgre,html)
    x = 0
    for imgurl in imglist:
        print imgurl
        subreg = r‘\.([a-z]+?$)‘
        subre  = re.compile(subreg)
        subs2  = re.findall(subre,imgurl)
        name = ‘e://pics/%s.%s‘ % (x, subs2[0])
        urllib.urlretrieve(imgurl, name)
        x += 1

def getPage(text):
    reg  = r‘data-pagesize="([0-9]+?)"‘
    rec  = re.compile(reg)
    list = re.findall(rec,text)
    return list[0]

url = "https://www.zhihu.com/question/****"     # 把问题url贴到这里
html = getHtml(url)
getImg(html)
print "page=%s" % getPage(html)
print "done!"

#coding=utf-8
import requests
import shutil
import re
import urllib
import ast

count=0
def getHtml(url):
    r = requests.get(url)
    return r.text

def saveImage(url, path):
    r = requests.get(url, stream=True)
    if r.status_code == 200:
        with open(path, ‘wb‘) as f:
            r.raw.decode_content = True
            shutil.copyfileobj(r.raw, f)
    del r
    return 0

def getImg(html):
    global count
    reg = r‘original="([0-9a-zA-Z:/._]+?)" data-actualsrc‘
    imgre = re.compile(reg)
    imglist = re.findall(imgre,html)
    for imgurl in imglist:
        count += 1
        subreg = r‘\.([a-z]+?$)‘
        subre  = re.compile(subreg)
        subs2  = re.findall(subre,imgurl)
        path = ‘e://pics/%s.%s‘ % (count, subs2[0])
        I = saveImage(imgurl, path)
        print ‘%s --> %s ‘ % (count, imgurl)

def getPage(text):
    reg  = r‘data-pagesize="([0-9]+?)"‘
    rec  = re.compile(reg)
    list = re.findall(rec,text)
    return list[0]

question = 27203***          # 问题ID
url = "https://www.zhihu.com/question/%s" % (question)
html = getHtml(url)
getImg(html)

page = int(getPage(html))
next_url = "https://www.zhihu.com/node/QuestionAnswerListV2"

if page > 1:
    for i_page in range(2, page):
        next_page = i_page * 10
        params = ‘{"url_token":%s, "pagesize":%s, "offset": %s}‘ % (question, page, next_page)
        post_data = {‘method‘:‘next‘, ‘params‘:params, ‘_xsrf‘: ‘521beffc0ca2d5747d6d981c6cc25dea‘}
        data=urllib.urlencode(post_data)
        headers = {‘Content-Type‘:‘application/x-www-form-urlencoded‘}
        r = requests.post(next_url, data=data, headers=headers)
        text = r.text
        text = ast.literal_eval(text)
        text = text[‘msg‘]
        text = ‘‘.join(text)
        text = text.replace(‘\\‘, ‘‘)
        getImg(text)

print "page=%s" % page
print "Down %s pics !!!" % count