day04 python

概述01text """变量：变化的量 1、变量值 value 2、变量的内存地址 id 3、变量的数据类型 type"""# import numpy as np# arr = np.arange(10)# print(type(arr))# print(arr)## l1 = [1, 2, 3, 4, 5]# print(typ 01text

"""变量：变化的量    1、变量值 value    2、变量的内存地址 ID    3、变量的数据类型 type"""# import numpy as np# arr = np.arange(10)# print(type(arr))# print(arr)## l1 = [1,2,3,4,5]# print(type(l1))# print(l1)# import requests## header = {#     ‘User-Agent‘: ‘Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_3) AppleWebKit/537.36 (KHTML,like Gecko) Chrome/76.0.3809.132 Safari/537.36‘# }## res = requests.get(‘https://www.bilibili.com/vIDeo/av68746541/?spm_ID_from=333.334.b_63686965665f7265636f6d6d656e64.16‘,#                    headers=header)# res.enCoding = res.apparent_enCoding# print(res.text)# for i in range(0,100,25):#     print(i)import reprint(re.findall(‘a.*?c‘,‘a123c456dsdadac‘))

02模拟浏览器登陆

import requestsheader = {    ‘User-Agent‘: ‘Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_3) AppleWebKit/537.36 (KHTML,like Gecko) Chrome/76.0.3809.132 Safari/537.36‘}res = requests.get(‘https://dig.chouti.com/‘,headers=header)data = res.textprint(data)

03爬豆瓣again

‘‘‘爬取豆瓣电影top250第一页：https://movIE.douban.com/top250?start=0&filter=第二页：https://movIE.douban.com/top250?start=25&filter=requests:请求库re:正则表达式‘‘‘import requestsimport re# 拼接电影爬去地址urlfor line in range(0,25):    url = f‘https://movIE.douban.com/top250?start={line}&filter=‘    response = requests.get(url)    # data = response.text    # 3.解析并提取数据    data = re.findall(        ‘<div >.*?<a href="(.*?)">.*?<span >(.*?)</span>.*?<span  property="v:average">(.*?)</span>.*?<span>(.*?)人评价</span>‘,response.text,re.S)  # re.S忽略换行    for d in data:        url,name,point,count = d        movIE_data = ‘‘‘            电影名称: %s            电影地址: %s            电影评分: %s            评价人数: %s            \n            ‘‘‘ % (name,url,count)        print(movIE_data)        with open(‘豆瓣.txt‘,‘a‘,enCoding=‘utf-8‘) as f:            f.write(movIE_data)# print(url)# 往拼接好的ulr地址发送请求获取数据# response = requests.get(url)# # print(response.text)  # 获取文本数据# # 3.解析并提取数据# # 电影名称、电影地址、电影评分、评价人数# # re.findall(‘匹配文本的规则‘,‘匹配的文本‘,‘匹配模式‘)  # 解析提取文本数据中 想要的数据# # .*?: 过滤不想要的数据，直到想要的数据出现# #  (.*?): 提取想要的数据# # 匹配规则# # <div class="item">.*?<a href="(.*?)">.*?<span class="Title">(.*?)</span>.*?<span class="rating_num" property="v:average">(.*?)</span>.*?<span>(.*?)人评价</span># data = re.findall(#     ‘<div >.*?<a href="(.*?)">.*?<span >(.*?)</span>.*?<span  property="v:average">(.*?)</span>.*?<span>(.*?)人评价</span>‘,#     response.text,re.S)  # re.S忽略换行# # print(data)# for d in data:#     # print(d)##     url,count = d##     movIE_data = ‘‘‘#     电影名称: %s#     电影地址: %s#     电影评分: %s#     评价人数: %s#     \n#     ‘‘‘ % (name,count)##     print(movIE_data)##     # 4.保存数据#     # a: append#     with open(‘豆瓣.txt‘,enCoding=‘utf-8‘) as f:#         f.write(movIE_data)

04友好爬豆瓣

import requests# import refrom bs4 import BeautifulSoupfrom openpyxl import Workbookimport timewb = Workbook()sheet = wb.activecount = 1# 拼接电影爬去地址urlfor line in range(0,100,25):    url = f‘https://movIE.douban.com/top250?start={line}&filter=‘    # 向对方服务器发送请求，获取响应数据    response = requests.get(url)    # 拿到文本数据    data = response.text    # 通过‘HTML.parser‘解析器解析数据    soup = BeautifulSoup(data,‘HTML.parser‘)    # 找到类名为：grID_vIEw的ol标签    ol = soup.find(name="ol",attrs={‘class‘: ‘grID_vIEw‘})    # 拿到中间的25个li标签，存入列表中    li_List = ol.find_all(name=‘li‘)    sheet.Title = ‘好评电影‘    sheet[‘A1‘].value = ‘序号‘    sheet[‘B1‘].value = ‘电影名称‘    sheet[‘C1‘].value = ‘电影评分‘    sheet[‘D1‘].value = ‘电影链接‘    sheet[‘E1‘].value = ‘电影图片‘    for li in li_List:        # 找到类名为：Title的span标签        name = li.find(name=‘span‘,attrs={‘class‘: ‘Title‘})        url = li.find(name=‘a‘)        rat = li.find(name=‘span‘,attrs={‘class‘: ‘rating_num‘})        img = li.find(name=‘img‘)        count = count + 1        sheet[‘A%s‘ % (count)].value = count - 1        sheet[‘B%s‘ % (count)].value = name.text        sheet[‘C%s‘ % (count)].value = rat.text        sheet[‘D%s‘ % (count)].value = url[‘href‘]        sheet[‘E%s‘ % (count)].value = img[‘src‘]    time.sleep(1)wb.save(‘好评电影.xlsx‘)

05金山词霸翻译

import requestsimport Jsondef main(key=""):    header = {        ‘User-Agent‘: ‘Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_3) AppleWebKit/537.36 (KHTML,like Gecko) Chrome/76.0.3809.132 Safari/537.36‘    }    url = ‘http://fy.iciba.com/AJAX.PHP?a=fy‘    data = {        ‘f‘: ‘auto‘,‘t‘: ‘auto‘,‘w‘: key    }    # 向对方服务器发送post请求，带上headers，数据data    res = requests.post(url=url,headers=header,data=data)    data = res.text    # 将二进制数据反序列化    data_List = Json.loads(data)    # print(data_List)    try:        val = data_List[‘content‘][‘word_mean‘]    except:        val = data_List[‘content‘][‘out‘]    return valif __name__ == ‘__main__‘:    # 接收用户输入    key = input(‘请输入要翻译的词语：‘).strip()    # 判断如果输入为空将要执行的代码    if not key:        print(‘输入为空‘)    else:        data = main(key=key)        print(data)

总结

以上是内存溢出为你收集整理的day04 python全部内容，希望文章能够帮你解决day04 python所遇到的程序开发问题。

如果觉得内存溢出网站内容还不错，欢迎将内存溢出网站推荐给程序员好友。