目的
快速的從豆瓣獲取電影的評(píng)分情況
方案
直接訪問https://www.douban.com/search?q={movie_name}，獲取網(wǎng)頁相關(guān)內(nèi)容，終端直接輸出。
借此步驟，以后配合alfred做快速信息瀏覽儡遮，美滋滋。
依賴庫安裝
pip3 install bs4 requests
執(zhí)行效果
~ python3 douban.py 四體
[電影] 4.9 144人評(píng)價(jià) 2004 四體
[電影] 6.3 21288人評(píng)價(jià) 2005 美國派(番外篇)4：集體露營(yíng)
支持開源
#! /usr/bin/env python3
# -*- coding:utf-8 -*-
import requests
import bs4
import sys
"""
python3 {douban.py} {movie_name}
"""
def get_web(url):
header = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.114 Safari/537.36 Edg/91.0.864.59"
}
res = requests.get(url, headers=header, timeout=5)
return res.text
def parse_city_date(soup):
location = soup.find("div", class_="crumbs fl")
date = soup.find("h1", class_="clearfix city")
return (
location.text.strip().replace("\n", "").replace(" ", ""),
date.i.text.strip()[:16],
)
def temp_string(high, low):
return f"{high} / {low}" if high and low else f"{high}{low}"
def format_infos(*infos):
datas = list(*infos)
return f"%-6s\t%s\t%s" % (datas[0], datas[1], "\t".join(datas[2:]))
def parse_content(e):
def text_or_empty(o):
return o.text if o else ""
def sub_cast_year(o):
return o.split("/")[-1].strip() if o else ""
def format_rating_person(s):
return s[1:-1]
type = text_or_empty(e.h3.span)
name = text_or_empty(e.h3.a)
rating_info = e.div
rating_nums = text_or_empty(rating_info.find("span", class_="rating_nums"))
sub_cast = text_or_empty(rating_info.find("span", class_="subject-cast"))
year = sub_cast_year(sub_cast)
rating_person_nums = format_rating_person(
text_or_empty(rating_info.find("span", class_=None))
)
return type, rating_nums, rating_person_nums, year, name
def parse_contents(soup):
def filter(infos):
for i in range(len(infos) - 1, -1, -1):
if (
infos[i].find("[小組]") == 0
or infos[i].find(" ") == 0
or infos[i].find("[日記]") == 0
):
infos.pop(i)
return infos
contents = soup.find_all("div", class_="title")
return filter([format_infos(parse_content(content)) for content in contents])
def print_weather(day, weather, tem, wind):
for i in range(0, 7):
print(f"{day[i]:<10}{tem[i]:^15}{wind[i]:<10}\t{weather[i]}")
def create_soup(movie_name):
return bs4.BeautifulSoup(
get_web(f"https://www.douban.com/search?q={movie_name}"), "lxml"
)
if __name__ == "__main__":
if len(sys.argv) < 2:
print("please input movie name")
exit(0)
movie_name = sys.argv[1]
soup = create_soup(movie_name)
contents = parse_contents(soup)
print(*contents, sep="\n")
感覺好玩的就來個(gè)贊呀暗赶！
