python导入txt数据 第一个数据带有双引号_求教为何python写入csv文件,用txt方式打开,发现头尾各多了一个双引号"!谢谢!...

#目标:用多协程爬到薄荷网的食物热量数据。

from gevent import monkey

monkey.patch_all

from bs4 import BeautifulSoup

from gevent.queue import Queue

import gevent,time,csv,requests

#时间戳

sta=time.time()

#c创建文档

file=open(r’food_calorie1.csv’,‘w’,newline=’’,encoding=‘utf-8’)

writer=csv.writer(file)

#获得网址,创建队列,添加网址

work=Queue()

i=‘view_menu’

for j in range(1,4):

url=‘http://www.boohee.com/food/’+str(i)+’?page=’+str(j)

work.put_nowait(url)

for i in range(1,4):

for j in range(1,4):

work.put_nowait(url)

print(len(work))

#定义函数,获得数据,解析数据

def crawler():

while not work.empty():

url=work.get_nowait()

raw_headers=’’‘Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,/;q=0.8,application/signed-exchange;v=b3;q=0.9

Accept-Encoding: gzip, deflate

Accept-Language: zh-CN,zh;q=0.9

Cache-Control: max-age=0

Connection: keep-alive

Cookie: Hm_lvt_7263598dfd4db0dc29539a51f116b23a=1582730871; Hm_lpvt_7263598dfd4db0dc29539a51f116b23a=1582789371

Host: www.boohee.com

If-None-Match: W/“a0cb03e4a0f2cc41604f1d79ed253f5b”

Referer: http://www.boohee.com/food/group/1

Upgrade-Insecure-Requests: 1

User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.122 Safari/537.36’’’

headers=dict([line.split(": “,1) for line in raw_headers.split(”\n")])

res=requests.get(url,headers=headers)

print(res.status_code)

foods=BeautifulSoup(res.text,‘html.parser’).find_all(class_=‘item clearfix’)

food=’’

for i in foods:

name=i.find_all(‘a’)[1][‘title’]

calo=i.find(‘p’).text

href_part=i.find_all(‘a’)[1][‘href’]

href=‘http://www.boohee.com/shiwu’+href_part

# food+=’’’

# -----------------------

# 食物:{}

# {}

# 链接:{}

# ‘’’.format(name,calo,href)

food+=’-----------------------\n食物:%s\n%s\n链接:%s\n’%(name,calo,href)

writer.writerow([food])

#创建任务,添加任务,执行任务

tasks=[]

for i in range(4):

task=gevent.spawn(crawler)

tasks.append(task)

gevent.joinall(tasks)

#时间戳,计算耗时

end=time.time()

print(end-sta)

以下是用记事本打开csv文件的样子

watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80NjQyNDI5Mg==,size_16,color_FFFFFF,t_70

表情包
插入表情
评论将由博主筛选后显示,对所有人可见 | 还能输入1000个字符
©️2020 CSDN 皮肤主题: 数字20 设计师:CSDN官方博客 返回首页