import requestsimport refrom bs4 import BeautifulSoupfrom lxml import etreeimport tracebackimport csv#定义一个函数获取豆瓣电影第一页def get_one_page(url,code = 'utf-8'):    headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.90 Safari/537.36'}    try:        r = requests.get(url,headers = headers)        if r.status_code == 200:            r.encoding = code            return r.text        else:            print("相应失败")            return None    except:        traceback.print_exc()def process(raw):    right = raw.split("@")    return right[0]def area(a):    if a[-1] == ")":        return a[16:]    else:        return None
def parse_one_page(slst,html):    #正则表达式    # rank = re.findall('
.*?',html,re.S)    # name = re.findall('
(.*?)',html,re.S)    # star = re.findall('
(.*?)
',html,re.S)    # time = re.findall('
(.*?)
',html,re.S)    # print(time)    #正则表达式别忘了加上r,防止转义,否则会报错    # 把上面的正则表达式合在一起    pattern = re.compile(r'
.*?.*?
(.*?).*?
(.*?)
.*?
(.*?)
.*?
<.*?>(.*?)(.*?)
',re.S)    items = re.findall(pattern,html)    #print(items)    for item in items:        #yield就相当于return的功能，但也有所不同，yield语句把程序编程迭代器        yield {            'rank':item[0],            'img':process(item[1]),            'MovieName':item[2],            "star":item[3].strip()[3:],            "time":item[4].strip()[5:15],            "area":area(item[4].strip()),            "score":str(item[5]) + str(item[6])        }    # return ""def write_to_file(item):    with open("猫眼top100.csv",'a',encoding = "utf_8_sig",newline="") as f:        #a追加模式 newline区分换行符        fieldnames = ['rank','img','MovieName','star','time','area','score']        w = csv.DictWriter(f,fieldnames = fieldnames)  #字典写入到csv        # w.writeheader()        w.writerow(item)     return ""def down_img(name,url,num):    try:        response = requests.get(url)        with open('C:/Users/HUAWEI/Desktop/py/爬虫/douban/'+name+'.jpg','wb') as f:            f.write(response.content)            print("第%s张图片下载完毕"%str(num))            print("="*20)    except Exception as e:        print(e.__class__.__name__) #打印错误类型名称def main(i):    num = 0    url = 'https://maoyan.com/board/4?offset=' + str(i)    html = get_one_page(url)    #print(html)    lst = [] #这个在这里没啥用，但以后若要单独存储某类信息，可是这样写，后面再对应加上函数参数    iterator = parse_one_page(lst,html)    for a in iterator:        #print(a)        num += 1        write_to_file(a)        down_img(a['MovieName'],a['img'],num)                # if __name__ == '__main__':#     for i in range(10):#         main(i)        #多线程抓取 from multiprocessing import Poolif __name__ == '__main__':    pool = Pool()    pool.map(main,[i * 10 for i in range(10)])