diff --git a/.idea/.gitignore b/.idea/.gitignore new file mode 100644 index 0000000..26d3352 --- /dev/null +++ b/.idea/.gitignore @@ -0,0 +1,3 @@ +# Default ignored files +/shelf/ +/workspace.xml diff --git a/.idea/.name b/.idea/.name new file mode 100644 index 0000000..7602925 --- /dev/null +++ b/.idea/.name @@ -0,0 +1 @@ +dxq.py \ No newline at end of file diff --git a/.idea/inspectionProfiles/profiles_settings.xml b/.idea/inspectionProfiles/profiles_settings.xml new file mode 100644 index 0000000..105ce2d --- /dev/null +++ b/.idea/inspectionProfiles/profiles_settings.xml @@ -0,0 +1,6 @@ + + + + \ No newline at end of file diff --git a/.idea/misc.xml b/.idea/misc.xml new file mode 100644 index 0000000..d1e22ec --- /dev/null +++ b/.idea/misc.xml @@ -0,0 +1,4 @@ + + + + \ No newline at end of file diff --git a/.idea/modules.xml b/.idea/modules.xml new file mode 100644 index 0000000..2dbaab4 --- /dev/null +++ b/.idea/modules.xml @@ -0,0 +1,8 @@ + + + + + + + + \ No newline at end of file diff --git a/.idea/task-2-4-regular-expression.iml b/.idea/task-2-4-regular-expression.iml new file mode 100644 index 0000000..d0876a7 --- /dev/null +++ b/.idea/task-2-4-regular-expression.iml @@ -0,0 +1,8 @@ + + + + + + + + \ No newline at end of file diff --git a/.idea/vcs.xml b/.idea/vcs.xml new file mode 100644 index 0000000..35eb1dd --- /dev/null +++ b/.idea/vcs.xml @@ -0,0 +1,6 @@ + + + + + + \ No newline at end of file diff --git a/dxq.py b/dxq.py new file mode 100644 index 0000000..0e29844 --- /dev/null +++ b/dxq.py @@ -0,0 +1,29 @@ +import requests +from bs4 import BeautifulSoup + +url = f"https://movie.douban.com/top250" + +headers = { + Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36 + } + +print('开始爬取豆瓣电影Top250...') +response = requests.get(url, headers=headers) +print(f'状态码: {response.status_code}') +print(f'内容长度: {len(response.text)} 字符') + +# 找到所有电影标题 +html = response.text + +# 匹配 电影名 +title_pattern = r'([^<]+)' +titles = re.findall(title_pattern, html) + +# 过滤掉英文名(以/开头) +chinese_titles = [t for t in titles if not t.startswith('/')] + +print('电影名称(前10部):') +for i, title in enumerate(chinese_titles[:10], 1): + print(f'{i}. {title}') + + \ No newline at end of file