2019-02-01 Python爬虫爬取豆瓣Top250

这几天学了一点爬虫后写了个爬取电影top250的代码，分别用requests库和urllib库，想看看自己能不能搞出个啥东西，虽然很简单但还是小开心。

import requests
import re

# https://movie.douban.com/top250?start=25&filter=
# <span class="title">勇士</span>

count = 1


def getdata(url):
    data = requests.get(url)
    return data.text


def showdata(data):
    global count
    regex = re.compile(r"<span class="title">(.*?)</span>")
    data = regex.findall(data)
    newdata = data.copy()
    for dataa in newdata:
        if "nbsp" in dataa:
            data.remove(dataa)
    for i in data:
        print(count, i)
        count = count + 1


for i in range(0, 10):
    i = i * 25
    url = "https://movie.douban.com/top250?start={}&filter=".format(str(i))
    data = getdata(url)
    showdata(data)

# 用requests来实现,正则表达式解析网页

import urllib
import urllib.request
import re
#https://movie.douban.com/top250?start=25&filter=
#<span class="title">勇士</span>

count = 1
def getdata(url):
    data = urllib.request.urlopen(url).read().decode("utf-8")
    return data


def showdata(data):
    global count
    regex = re.compile(r"<span class="title">(.*?)</span>")
    data = regex.findall(data)
    newdata = data.copy()
    for dataa in newdata:
        if "nbsp" in dataa:
            data.remove(dataa)
    for i in data:
        print(count,i)
        count = count+1


for i in range(0,10):
    i = i*25
    url = "https://movie.douban.com/top250?start={}&filter=".format(str(i))
    data = getdata(url)
    showdata(data)

#用urllib来实现，正则表达式解析网页

---

emmmmmmm