python xpath 爬取豆瓣電腦版電影案例

標籤：圖片   mac os   python   sts   chart   chrome   har   tle   path   

from lxml import etreeimport requestsurl = ‘https://movie.douban.com/chart‘headers = {"User-Agent":"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.84 Safari/537.36" }response = requests.get(url,headers=headers)html_str = response.content.decode()# print(html_str)# 使用etree來處理資料html = etree.HTML(html_str)# 擷取電影的url地址url_list = html.xpath("//div[@class=‘indent‘]/div/table//div[@class=‘pl2‘]/a/@href")#print(url_list)# 擷取電影圖片地址img_list = html.xpath("//div[@class=‘indent‘]/div/table//a[@class=‘nbg‘]/img/@src")#print(img_list)# 把每一部電影組成一個字典,字典中是電影的資料    # 1.分組    # 2.每一組提取資料rets = html.xpath("//div[@class=‘indent‘]/div/table")for table in rets:    item = {}    item[‘title‘] = table.xpath(".//div[@class=‘pl2‘]/a/text()")[0].replace("/","").strip()    item[‘href‘] = table.xpath(".//div[@class=‘pl2‘]/a/@href")[0]    item[‘img‘] = table.xpath(".//a[@class=‘nbg‘]/img/@src")[0]    item[‘comment_num‘] = table.xpath(".//div[@class=‘pl2‘]/div//span[@class=‘pl‘]/text()")[0]    item[‘rating_num‘] = table.xpath(".//div[@class=‘pl2‘]/div//span[@class=‘rating_nums‘]/text()")[0]    print(item)

 

python xpath 爬取豆瓣電腦版電影案例