[已解决]python爬虫

一枚丶学渣

以下是我按照教程所写的代码，运行之后没有反馈，求大佬指点，


import urllib.request
import re

def open_url(url):
    req = urllib.request.Request(url)
    req.add_header('User-Agent','Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 Safari/537.36 Edge/18.18362')
    page = urllib.request.urlopen(req)
    html = page.read().decode('utf-8')

    return html

def get_img(html):
    p=r'<img width="560" height="860" class="BDE_Image" style="cursor: url(//tb2.bdstatic.com/tb/static-pb/img/cur_zin.cur), pointer;" src=[^"]+\.jpg"'
    imglist = re.findall(p,html)
    n=1
    for each in imglist:
        n += 1
        if n==5:
            break
        print("++++++++")
        print(each)

if __name__ == '__main__':
    url="https://tieba.baidu.com/p/6769674730"
    get_img(open_url(url))

最佳答案

月排行榜 / 总排行榜

Twilight6

2020-8-9 16:23:29

正则没提取到数据，改成这样吧：

import urllib.request
import re

def open_url(url):
    req = urllib.request.Request(url)
    req.add_header('User-Agent','Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 Safari/537.36 Edge/18.18362')
    page = urllib.request.urlopen(req)
    html = page.read().decode('utf-8')

    return html

def get_img(html):
    p=r'<img class="BDE_Image" src="(.+?)"'
    imglist = re.findall(p,html)
    n=1
    for each in imglist:
        n += 1
        if n==5:
            break
        print("++++++++")
        print(each)

if __name__ == '__main__':
    url="https://tieba.baidu.com/p/6769674730"
    get_img(open_url(url))

跳转到最佳答案楼层

Twilight6

正则没提取到数据，改成这样吧：

import urllib.request
import re

def open_url(url):
    req = urllib.request.Request(url)
    req.add_header('User-Agent','Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 Safari/537.36 Edge/18.18362')
    page = urllib.request.urlopen(req)
    html = page.read().decode('utf-8')

    return html

def get_img(html):
    p=r'<img class="BDE_Image" src="(.+?)"'
    imglist = re.findall(p,html)
    n=1
    for each in imglist:
        n += 1
        if n==5:
            break
        print("++++++++")
        print(each)

if __name__ == '__main__':
    url="https://tieba.baidu.com/p/6769674730"
    get_img(open_url(url))

极品召唤兽

Twilight6 发表于 2020-8-9 16:23
正则没提取到数据，改成这样吧：

我去...这是真的厉害...