用python爬虫批量下载pdf_爬虫 采集 批量下载 pdf文件

mport os

import re

from uuid import uuid1

import requests

from bs4 import BeautifulSoup

from random import choice

import urllib3

import json

# 获取随机请求头

def get_headers():

file = open('../../tools/user_agent.txt', 'r')

user_agent_list = file.readlines()

user_agent = str(choice(user_agent_list)).replace('\n', '')

user_agent = 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:39.0) Gecko/20100101 Firefox/39.0' if len(

user_agent) < 10 else user_agent

headers = {

"User-Agent": user_agent,

}

return headers

# 负责下载图片

def download(url, end,fileName):

try:

headers = get_headers()

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

# 获取的文本实际上是图片的二进制文本

img = response.content

path = "c:/pdf-2020-10-9/" + fileName + end

print(url)

# 将他拷贝到本地文件 w 写  b 二进制  wb代表写入二进制文本

with open(path, 'wb') as f:

f.write(img)

except Exception as e:

print(str(e))

pass

def requests_get(url):

try:

url_prefix='http://static.sse.com.cn'

headers = get_headers()

# 请求页面

__http = urllib3.PoolManager()

headers={'Content-Type': 'application/json','Referer':''}

resp = __http.request('get', targetUrl,headers=headers)

# 解析

dataDic =json.loads(resp.data.decode('utf-8'))

pdf_list=dataDic['pageHelp']['data']

for pdf in pdf_list:

print(pdf)

# 获取图片链接

code= pdf['SECURITY_CODE']

name = pdf["SECURITY_NAME"]

url = pdf["URL"]

url = url_prefix+url

ssedate = pdf['SSEDATE']

title = pdf['TITLE']

title = re.sub(r'[/\:*?"<>|]', '', title)

# 获取图片后缀

fullFileName = os.path.split(url)[1]

fileName=os.path.splitext(fullFileName)[0]

end = os.path.splitext(url)[1]

if url and end:

# 去除特殊字符

end = re.sub(r'[，。?？,/\\·*]', '', end)

# 调用下载函数

download(url, end,fileName+"_"+title)

else:

pass

except Exception as e:

print(e)

pass

if __name__ == '__main__':

targetUrl = '/security/stock/queryCompanyBulletin.do?isPagination=true&productId=&keyWord=&securityType=0101%2C120100%2C020100%2C020200%2C120200&reportType2=&reportType=ALL&beginDate=2020-10-9&endDate=2020-10-9&pageHelp.pageSize=25&pageHelp.pageCount=50&pageHelp.pageNo=1&pageHelp.beginPage=1&pageHelp.cacheSize=1&pageHelp.endPage=5&_=1603242152949'

requests_get(targetUrl)