百度文库爬虫（爬取需要下载券的文档）

import requests
import re
import json
import os

session = requests.session()

def fetch_url(url):
    return session.get(url).content.decode('gbk')

def get_doc_id(url):
    return re.findall('view/(.*).html', url)[0]

def parse_type(content):
    return re.findall(r"docType.*?\:.*?\'(.*?)\'\,", content)[0]

def parse_title(content):
    return re.findall(r"title.*?\:.*?\'(.*?)\'\,", content)[0]

def parse_doc(content):
    result = ''
    url_list = re.findall('(https.*?0.json.*?)\\\\x22}', content)
    url_list = [addr.replace("\\\\\\/", "/") for addr in url_list]
    for url in url_list[:-5]:
        content = fetch_url(url)
        y = 0
        txtlists = re.findall('"c":"(.*?)".*?"y":