lh_hebine的博客

# ！user/bin/env python3# -*-coding: utf-8 -*-__author__ = '闻名'from selenium import webdriverfrom selenium.webdriver.support.ui import WebDriverWaitfrom selenium.webdriver.support import expected_conditions as ECfrom selenium.webdriver.common.by impo

file = open(r'国产注册.txt','r', encoding='ISO-8859-1')data = file.read()content = eval(data)print(len(content))import xlwtwookbook = xlwt.Workbook(encoding='utf-8')wooksheet = wookbook.add_sheet('sheet')title = ['注册证编号', '注册人名称', '注册人住所 ', '生产地址 ', .

import requestsimport timefrom lxml import etreeimport reimport xlwtimport randomimport xlrdfrom multiprocessing import Processclass Yimaitong(): def __init__(self): # 请求的url self.url = 'http://disease.medlive.cn/wiki/list/1.

import requests # 获取网页数据from bs4 import BeautifulSoup # 解析网页数据import time # 设置爬虫等待时间import xlwt# 获取豆瓣网址并解析数据def get_douban_books(url, num): headers = { 'user-agent': 'Mozilla/5.0...

# ！/user/bin/python3# -*- coding:utf-8 -*-import requestsfrom lxml import etreeclass Tiebasprite(): def __init__(self, tieba_name): self.tieba_name = tieba_name self.post_url ...

# ！/user/bin/python3# -*- coding:utf-8 -*-import requestsimport refrom urllib import requestdef get_picture_list(keyword, biggest_pages): all_picture_list = [] for page in range(bigges...

USER_AGENT_LIST=[ "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1", "Mozilla/5.0 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11 (KHTM...

# ！/user/bin/python3# -*- coding:utf-8 -*-import requestsimport osimport re # 使用正则表达式def getManyPages(keyword, pages): params=[] # 分页请求地址拼接 每页显示60个图片 for i in range(0, 30*pages+30,...