摘要：import requests import re import json import time from openpyxl import workbook from openpyxl import load_workbook from pymongo import MongoClient from requests.exceptions import RequestException impo 阅读全文

摘要：import requests from urllib.parse import urlencode import os from hashlib import md5 from multiprocessing.pool import Pool def get_page(offset): headers={ 'user-agent':'Mozilla/5.0 (Windows NT 10.0; W 阅读全文

摘要：import requests import re import time import json from requests.exceptions import RequestException def get_html_page(url): try: headers = { 'User-Agent': 'Mozilla/5.0 (Windows... 阅读全文

摘要：import requests import re from requests.exceptions import RequestException import json from multiprocessing import Pool def get_one_page(url): headers = { 'User-Agent':'Mozilla/5.0 (Windows N... 阅读全文