python爬虫小练习——爬取豆瓣电影top250
import requests
from bs4 import BeautifulSoup
import pprint
import json
import pandas as pd
import time
# 构造分页数字列表
page_indexs = range(0, 250, 25)
list(page_indexs)
# 请求头
headers = {
'User-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/1'
}
# 下载所有的网页然后交给下一个函数处理
def download_all_htmls():
htmls = []
for idx in page_indexs:
url = "https://movie.douban.com/top250?start={}&filter=".format(idx)
print("craw html", url)
r = requests.get(url, headers=headers)
if r.status_code != 200:
raise Exception("error")
htmls.append(r.text)
time.sleep(0.5)
return htmls
# 解析HTML得到数据
def parse_single_html(html):
# 使用BeautifulSoup处理网页，传入参数html，使用html.parser模式处理
soup = BeautifulSoup(html, 'html.parser')
# 使用BeautifulSoup匹配想要的内容，使用find函数
article_items = (
soup.find("div", class_="article")
.find("ol", class_="grid_view")
.find_all("div", class_="item")
)
datas = []
# 内容比较多分步提取内容
for article_item in article_items:
rank = article_item.find("div", class_="pic").find("em").get_text()
info = article_item.find("div", class_="info")
title = info.find("div", class_="hd").find("span", class_="title").get_text()
stars = (
info.find("div", class_="bd")
.find("div", class_="star")
.find_all("span")
)
rating_star = stars[0]["class"][0]
rating_num = stars[1].get_text()
comments = stars[3].get_text()
datas.append({
"rank": rank,
"title": title,
"rating_star": rating_star.replace("rating", "").replace("-t", ""),
"rating_num": rating_num,
"comments": comments.replace("人评价", "")
})
return datas
pprint.pprint()
if __name__ == '__main__':
# 下载所有的网页内容
htmls = download_all_htmls()
# pprint.pprint(parse_single_html(htmls[0]))
# 解析网页内容并追到all_datas的列表中
all_datas = []
for html in htmls:
all_datas.extend(parse_single_html(html))
# 使用pandas模块，批量导入到表格中
df = pd.DataFrame(all_datas)
df.to_excel("doubanTOP250.xlsx")