├── .gitignore ├── LICENSE ├── README.md ├── configuration.xml ├── info.log ├── people ├── __init__.py └── candidate.py ├── res ├── FZZDXJW.TTF ├── stop_words.txt └── user_dict.txt ├── results ├── Presentation.pptx ├── Visualize.xlsx ├── female-bj.png ├── female-hb.png ├── female-intro.png ├── female-sc.png ├── male-intro.png ├── male_bj.png ├── male_hb.png ├── male_sc.png └── 世纪佳缘用户画像.docx ├── spider ├── __init__.py ├── avatar_downloader.py └── jiayuanspider.py └── util ├── __init__.py ├── config_helper.py ├── text_segment.py └── toexcel.py /.gitignore: -------------------------------------------------------------------------------- 1 | .idea -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucasxlu/JiaYuan/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucasxlu/JiaYuan/HEAD/README.md -------------------------------------------------------------------------------- /configuration.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucasxlu/JiaYuan/HEAD/configuration.xml -------------------------------------------------------------------------------- /info.log: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /people/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /people/candidate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucasxlu/JiaYuan/HEAD/people/candidate.py -------------------------------------------------------------------------------- /res/FZZDXJW.TTF: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucasxlu/JiaYuan/HEAD/res/FZZDXJW.TTF -------------------------------------------------------------------------------- /res/stop_words.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucasxlu/JiaYuan/HEAD/res/stop_words.txt -------------------------------------------------------------------------------- /res/user_dict.txt: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /results/Presentation.pptx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucasxlu/JiaYuan/HEAD/results/Presentation.pptx -------------------------------------------------------------------------------- /results/Visualize.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucasxlu/JiaYuan/HEAD/results/Visualize.xlsx -------------------------------------------------------------------------------- /results/female-bj.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucasxlu/JiaYuan/HEAD/results/female-bj.png -------------------------------------------------------------------------------- /results/female-hb.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucasxlu/JiaYuan/HEAD/results/female-hb.png -------------------------------------------------------------------------------- /results/female-intro.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucasxlu/JiaYuan/HEAD/results/female-intro.png -------------------------------------------------------------------------------- /results/female-sc.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucasxlu/JiaYuan/HEAD/results/female-sc.png -------------------------------------------------------------------------------- /results/male-intro.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucasxlu/JiaYuan/HEAD/results/male-intro.png -------------------------------------------------------------------------------- /results/male_bj.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucasxlu/JiaYuan/HEAD/results/male_bj.png -------------------------------------------------------------------------------- /results/male_hb.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucasxlu/JiaYuan/HEAD/results/male_hb.png -------------------------------------------------------------------------------- /results/male_sc.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucasxlu/JiaYuan/HEAD/results/male_sc.png -------------------------------------------------------------------------------- /results/世纪佳缘用户画像.docx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucasxlu/JiaYuan/HEAD/results/世纪佳缘用户画像.docx -------------------------------------------------------------------------------- /spider/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /spider/avatar_downloader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucasxlu/JiaYuan/HEAD/spider/avatar_downloader.py -------------------------------------------------------------------------------- /spider/jiayuanspider.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucasxlu/JiaYuan/HEAD/spider/jiayuanspider.py -------------------------------------------------------------------------------- /util/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /util/config_helper.py: -------------------------------------------------------------------------------- 1 | import lxml 2 | 3 | -------------------------------------------------------------------------------- /util/text_segment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucasxlu/JiaYuan/HEAD/util/text_segment.py -------------------------------------------------------------------------------- /util/toexcel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lucasxlu/JiaYuan/HEAD/util/toexcel.py --------------------------------------------------------------------------------