爬虫永不停息
最近改进上一篇的爬虫,不爬豆瓣了,改爬一爬京东评论,先放几张图研究看看先。
研究了一下,发现商品的id就是链接.html前面的数字。我们把它复制粘贴下拉
1,对上一篇的代表进行修改和添加
class Spider():
def __init__(self):
# score:1为差评;2为中评;3为好评,0为所有评论
# 这链接是京东jsonp回调的数据,我们要给这链接加上商品id和评论页码。
self.start_url = 'https://sclub.jd.com/comment/productPageComments.action?callback=fetchJSON_comment98vv30672&productId={}&score=0&sortType=5&page={}&pageSize=10&isShadowSku=0&rid=0&fold=1'
# 添加一个新的队列
self.pageQurl = Queue()
# 上一篇是list,现在是dict
self.data = dict()
复制代码
2,修改上一篇整个 parse_first函数
def parse_first(self):
if not self.qurl.empty():
goodsid = self.qurl.get()
url = self.start_url.format(goodsid,1)
print('parse_first',url)
try:
r = requests.get(url, headers={'User-Agent': random.choice(self.user_agent)},proxies=self.notproxy,verify=False)
# 编码格式是GBK,不是UTF-8
r.encoding = 'GBK'
if r.status_code == 200:
# 对回调回来的数据进行处理
res = r.text.replace('fetchJSON_comment98vv30672(', '').replace(');', '').replace('false', '0').replace('true','1')
res = json.loads(res)
lastPage = int(res['maxPage'])
# 爬1-5页评论
for i in range(lastPage)[1:5]:
temp = str(goodsid)+ ',' + str(i)
self.pageQurl.put(temp)
arr = []
for j in res['hotCommentTagStatistics']:
arr.append({'name':j['name'],'count':j['count']})
self.data[str(goodsid)] = {
'hotCommentTagStatistics':arr,
'poorCountStr':res['productCommentSummary']['poorCountStr'],
'generalCountStr': res['productCommentSummary']['generalCountStr'],
'goodCountStr': res['productCommentSummary']['goodCountStr'],
'goodRate': res['productCommentSummary']['goodRate'],
'comments': []
}
self.parse_first()
else:
self.first_running = False
print('ip被屏蔽')
except:
self.first_running = False
print('代理ip代理失败')
else:
self.first_running = False
复制代码
3,修改上一篇整个 parse_second函数
def parse_second(self):
while self.first_running or not self.pageQurl.empty():
if not self.pageQurl.empty():
arr = self.pageQurl.get().split(',')
url = self.start_url.format(arr[0],arr[1])
print(url)
try:
r = requests.get(url,headers={'User-Agent': random.choice(self.user_agent)},proxies=self.notproxy,verify=False)
r.encoding = 'GBK'
if r.status_code == 200:
res = r.text.replace('fetchJSON_comment98vv30672(', '').replace(');', '').replace('false','0').replace('true', '1')
try:
res = json.loads(res)
for i in res['comments']:
images = []
videos = []
# 记录用户的评论图片与视频
if i.get('images'):
for j in i['images']:
images.append({'imgUrl': j['imgUrl']})
if i.get('videos'):
for k in i['videos']:
videos.append({'mainUrl': k['mainUrl'], 'remark': k['remark']})
# 记录用户的详细数据
mydict = {
'referenceName': i['referenceName'],
'content': i['content'],
'creationTime': i['creationTime'],
'score': i['score'],
'userImage': i['userImage'],
'nickname': i['nickname'],
'userLevelName': i['userLevelName'],
'productColor': i['productColor'],
'productSize': i['productSize'],
'userClientShow': i['userClientShow'],
'images': images,
'videos': videos
}
self.data[arr[0]]['comments'].append(mydict)
# 线程随机休眠
time.sleep(random.random() * 5)
except:
print('无法编译成对象',res)
except Exception as e:
print('获取失败',str(e))
复制代码
4,修改一部分run函数,
@run_time
def run(self):
# 爬京东商品的ID,用数组对它们进行存放
goodslist = ['6784500','31426982482','7694047']
for i in goodslist:
self.qurl.put(i)
ths = []
th1 = Thread(target=self.parse_first, args=())
th1.start()
ths.append(th1)
for _ in range(self.thread_num):
th = Thread(target=self.parse_second)
th.start()
ths.append(th)
for th in ths:
# 等待线程终止
th.join()
s = json.dumps(self.data, ensure_ascii=False, indent=4)
with open('jdComment.json', 'w', encoding='utf-8') as f:
f.write(s)
print('Data crawling is finished.')
复制代码
5,最后爬出来的数据是,这只是部分代码,对上一篇代码进行替换即可运行。
京东原版数据:
爬出来的数据格式:
京东原版评论:
爬出来的数据格式:
下面是个人写的小程序,数据也是爬虫得来的,希望大家看看,给点意见。