我的第一个爬虫小程序之利用requests和lxml库爬取豆瓣电影新片top10

利用requests和lxml库爬取豆瓣电影新片top10,并写入txt文档和Excel中

代码部分：

import requests
import pandas as pd
from lxml import etree

# parser = etree.HTMLParser('encoding = utf-8')
# html = etree.parse('tencent.html',parser=parser)
# # 1.获取所有的tr标签，xpath返回的是一个列表
# trs = html.xpath("//tr")
# for tr in trs:
#     print(etree.tostring(tr,encoding = 'utf-8').decode("utf-8"))

url = 'https://movie.douban.com/chart'
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.132 Safari/537.36'}
resp = requests.get(url=url, headers=headers)
with open('douban.html', 'w', encoding='utf-8') as pt:
    pt.write(resp.content.decode('utf-8'))
text = resp.text
print(resp.text)

html = etree.HTML(text)
trs