python--(爬虫-re模块)

python--(爬虫-re模块)

re模块四大核心功能:

    1.findall 查找所有,返回list

import re
lst = re.findall("m", "mai le fo len, mai ni mei!")
print(lst) # ['m', 'm', 'm']

lst = re.findall(r"\d+", "5点之前. 你要给我5000")
print(lst) # ['5' '5000']

    2.search 会进行匹配,但如果匹配到了第一个结果,就会返回这个结果,
如果匹配不上search返回的则是None

import re
ret = re.search(r'\d', '5点之前. 你要给我5000万').group()
print(ret) #

    3. match 只能从字符串的开头进⾏匹配

import re
ret = re.match('a', 'abc').group()
print(ret) # a

    4. finditer 和findall差不多. 只不过这时返回的是迭代器

import re
it = re.finditer("m", "mai le fo len, mai ni mei!")
for el in it:
 print(el.group()) # 依然需要分组

　　　　5.re模块相关操作

import re

#   split  切割. 按照正则切割.
# lst = re.split(r"[ab]", "abcdefghahahehedebade")
# print(lst)

#   sub 替换.
# result = re.sub("250", "__sb__", "alex250taibai250taihei250ritian250liuwei")
# print(result)

# result = re.subn("250", "__sb__", "alex250taibai250taihei250ritian250liuwei")
# print(result)

# obj = re.compile(r"\d+")
# lst = obj.findall("大阳哥昨天赚了5000块")
# lst2 = obj.findall("银行流水5000， 花了6000")
# print(lst)
# print(lst2)

# obj = re.compile(r"(?P<id>\d+)(?P<zimu>e{3})")
# ret = obj.search("abcdefg123456eeeee") # ((123456)(eee))
# print(ret.group())
# print(ret.group("id"))
# print(ret.group("zimu"))

# ret = re.findall('www.(baidu|oldboy).com', 'www.oldboy.com')
# print(ret) # 这是因为findall会优先把匹配结果组⾥内容返回,如果想要匹配结果,取消权限即可
# ret = re.findall('www.(?:baidu|oldboy).com', 'www.oldboy.com') # ?: 当前的（）不分组
# print(ret) # ['www.oldboy.com']

# ret=re.split("sb","alexsbwusirsbtaibaisbliuwei")
# print(ret)

爬虫重点:爬取豆瓣网站相关信息===>

import re
from urllib.request import urlopen  # 打开一个链接. 读取源代码
import ssl
# 干掉数字签名证书
ssl._create_default_https_context = ssl._create_unverified_context

def getPage(url):
    response = urlopen(url) # 和网页链接
    return response.read().decode('utf-8') # 返回正常的页面源代码. 一大堆HTML
def parsePage(s): # s 是页面源代码
    ret = re.findall('<div class="item">.*?<div class="pic">.*?<em .*?>(?P<id>\d+).*?'+
        '<span class="title">(?P<title>.*?)</span>'+
        '.*?<span class="rating_num" .*?>(?P<rating_num>.*?)</span>.*?<span>'+
        '(?P<comment_num>.*?)评价</span>', s, re.S)
    return ret # id,title, rating_num, comment_num

def main(num):
    url = 'https://movie.douban.com/top250?start=%s&filter=' % num
    response_html = getPage(url) # response_html是页面源代码
    ret = parsePage(response_html)
    print(ret) # id,title, rating_num, comment_num

count = 0
for i in range(10): #
    main(count)
    count += 25

方法一

import re
from urllib.request import urlopen  # 打开一个链接. 读取源代码
import ssl
# 干掉数字签名证书
ssl._create_default_https_context = ssl._create_unverified_context

def getPage(url):
    response = urlopen(url) # 和网页链接
    return response.read().decode('utf-8') # 返回正常的页面源代码. 一大堆HTML

def parsePage(s):
    com = re.compile(
        '<div class="item">.*?<div class="pic">.*?<em .*?>(?P<id>\d+).*?' +
        '<span class="title">(?P<title>.*?)</span>' +
        '.*?<span class="rating_num" .*?>(?P<rating_num>.*?)</span>.*?<span>' +
        '(?P<comment_num>.*?)评价</span>', re.S)
    ret = com.finditer(s)
    for i in ret:
        yield {
            "id": i.group("id"),
            "title": i.group("title"),
            "rating_num": i.group("rating_num"),
            "comment_num": i.group("comment_num"),
        }

def main(num):
    url = 'https://movie.douban.com/top250?start=%s&filter='
    response_html = getPage(url)
    print(response_html)
    ret = parsePage(response_html)
    # print(ret)
    f = open("move_info7", "a", encoding="utf8")
    for obj in ret:
        print(obj)
        data = str(obj)
        f.write(data + "\n")

count = 0
for i in range(10): #
    main(count)
    count += 25

爬取并写入文件