Fetch GitHub PRs by User and Date Range

README.md

Fetch GitHub PRs by User and Date Range

This script retrieves pull requests created by a specific GitHub user within a date range across multiple repositories. It outputs a Markdown file containing:

• PR Title & Link
• Description
• Full Diff (optional in script)
• Review Comments (with file context)
• Issue Discussion Threads

---

✅ Requirements

• GitHub CLI (gh)
• jq

---

▶ Usage

1. Make the script executable:

   chmod +x fetch_prs.sh

fetch_prs.sh

#!/bin/bash

# Script: fetch_prs.sh
# Description: Fetch pull requests created by a GitHub user in specified repositories and date range,
# and save them into a Markdown file with PR details, diffs, review comments, and discussions.
# Requirements: GitHub CLI (gh), jq

# Prompt for inputs
read -p "GitHub username: " GH_USER
read -p "Repository list (space-separated, e.g. org/repo1 org/repo2): " REPOS
read -p "Start date (YYYY-MM-DD): " START_DATE
read -p "End date (YYYY-MM-DD): " END_DATE
read -p "Output file name (default: prs_${START_DATE}_to_${END_DATE}.md): " OUTPUT_FILE

# Default output filename
OUTPUT_FILE=${OUTPUT_FILE:-prs_${START_DATE}_to_${END_DATE}.md}

# Validate date format (basic)
DATE_REGEX="^[0-9]{4}-[0-9]{2}-[0-9]{2}$"
if [[ ! $START_DATE =~ $DATE_REGEX ]] || [[ ! $END_DATE =~ $DATE_REGEX ]]; then
  echo "❌ Invalid date format. Use YYYY-MM-DD."
  exit 1
fi

# Check if gh CLI exists
if ! command -v gh &> /dev/null; then
  echo "❌ GitHub CLI (gh) is not installed. Install from https://cli.github.com/"
  exit 1
fi

echo "# Pull Requests from $START_DATE to $END_DATE" > "$OUTPUT_FILE"
echo "" >> "$OUTPUT_FILE"

echo "Fetching PRs for $GH_USER between $START_DATE and $END_DATE..."
echo "Repos: $REPOS"
echo "Output: $OUTPUT_FILE"
echo ""

for repo in $REPOS; do
  echo "Processing repository: $repo"
  
  PR_URLS=$(gh api \
    -H "Accept: application/vnd.github+json" \
    "/search/issues?q=is:pr+author:$GH_USER+repo:$repo+created:$START_DATE..$END_DATE&per_page=100" \
    --paginate --jq '.items[].pull_request.url')

  if [ -z "$PR_URLS" ]; then
    echo "No PRs found for $repo."
    continue
  fi

  for url in $PR_URLS; do
    echo "Fetching PR details: $url"
    
    PR_DATA=$(gh api "$url")
    NUMBER=$(echo "$PR_DATA" | jq .number)
    TITLE=$(echo "$PR_DATA" | jq -r .title)
    BODY=$(echo "$PR_DATA" | jq -r .body)
    HTML_URL=$(echo "$PR_DATA" | jq -r .html_url)

    echo -e "\n## [$repo] PR #$NUMBER: $TITLE" >> "$OUTPUT_FILE"
    echo -e "**Link:** [$HTML_URL]($HTML_URL)" >> "$OUTPUT_FILE"
    if [ -n "$BODY" ] && [ "$BODY" != "null" ]; then
      echo -e "\n**Description:**\n$BODY\n" >> "$OUTPUT_FILE"
    fi

    # Fetch diff
    echo -e "\n**Diff:**\n\`\`\`diff" >> "$OUTPUT_FILE"
    gh api "$url" -H "Accept: application/vnd.github.v3.diff" >> "$OUTPUT_FILE"
    echo -e "\n\`\`\`\n" >> "$OUTPUT_FILE"

    # Fetch review comments
    OWNER=$(echo $repo | cut -d'/' -f1)
    REPO=$(echo $repo | cut -d'/' -f2)

    COMMENTS=$(gh api "/repos/$OWNER/$REPO/pulls/$NUMBER/comments" --jq '.[] | "- \(.path): \(.body)"')
    if [ ! -z "$COMMENTS" ]; then
      echo -e "**Review Comments:**" >> "$OUTPUT_FILE"
      echo "$COMMENTS" >> "$OUTPUT_FILE"
      echo "" >> "$OUTPUT_FILE"
    fi

    # Fetch issue discussion comments (main PR thread)
    DISCUSSIONS=$(gh api "/repos/$OWNER/$REPO/issues/$NUMBER/comments" --jq '.[] | "- \(.body)"')
    if [ ! -z "$DISCUSSIONS" ]; then
      echo -e "**Discussion Threads:**" >> "$OUTPUT_FILE"
      echo "$DISCUSSIONS" >> "$OUTPUT_FILE"
      echo "" >> "$OUTPUT_FILE"
    fi

    sleep 1 # avoid hitting rate limits
  done
done

echo "✅ Done! All PR data saved to $OUTPUT_FILE"