Skip to content

C
crawler
Commit 7a951ada authored by litaolemo's avatar litaolemo
Browse files
Options

update

parent f71eea5b
Hide whitespace changes
Inline Side-by-side
Showing with 3 additions and 2 deletions
crawler_sys/site_crawler/crawler_zhihu.py
View file @ 7a951ada
...@@ -48,8 +48,7 @@ class Crawler_zhihu(): ...@@ -48,8 +48,7 @@ class Crawler_zhihu():
self.video_data['platform'] = self.platform self.video_data['platform'] = self.platform
# remove fields that crawled data don't have # remove fields that crawled data don't have
pop_key_Lst = ['channel', 'describe', 'isOriginal', "repost_count", "video_id"] pop_key_Lst = ['channel', 'describe', 'isOriginal', "repost_count", "video_id"]
import pdb
pdb.set_trace()
try: try:
with open('./zhihu.js', 'r', encoding='utf-8') as f: with open('./zhihu.js', 'r', encoding='utf-8') as f:
js = f.read() js = f.read()
...@@ -168,6 +167,8 @@ class Crawler_zhihu(): ...@@ -168,6 +167,8 @@ class Crawler_zhihu():
"d_c0": '"AIDu7_zGrA-PToWVy-siVNLS835i5YXmFCQ=|1562072925"', "d_c0": '"AIDu7_zGrA-PToWVy-siVNLS835i5YXmFCQ=|1562072925"',
"KLBRSID": None "KLBRSID": None
} }
import pdb
pdb.set_trace()
cookies_dict.update(res_cookies_dict) cookies_dict.update(res_cookies_dict)
url = "https://www.zhihu.com/api/v4/search_v3?t=general&q={0}&correction=1&offset=0&limit=20&lc_idx=0&show_all_topics=0".format( url = "https://www.zhihu.com/api/v4/search_v3?t=general&q={0}&correction=1&offset=0&limit=20&lc_idx=0&show_all_topics=0".format(
urllib.parse.quote(keyword)) urllib.parse.quote(keyword))
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment